Search results for: residual neural networks

Authors: Yan Yu, Wang Yu, Chen Xintong, Liu Yi, Zhang Yanzhong, Wang Yanji, Chen Xingyu, Zhang Miaocheng, Tong Yi

Abstract:

Neuromorphic computing based on spiking neural networks (SNNs) has emerged as a promising avenue for building the next generation of intelligent computing systems. Owing to its high-density integration, low power, and outstanding nonlinearity, memristors have attracted emerging attention on achieving SNNs. However, fabricating a low-power and robust memristor-based spiking neuron without extra electrical components is still a challenge for brain-inspired systems. In this work, we demonstrate a TiO₂-based threshold switching (TS) memristor to emulate a leaky integrate-and-fire (LIF) neuron without auxiliary circuits, used to realize single layer fully connected (FC) SNNs. Moreover, our TiO₂-based resistive switching (RS) memristors realize spiking-time-dependent-plasticity (STDP), originating from the Ag diffusion-based filamentary mechanism. This work demonstrates that TiO2-based memristors may provide an efficient method to construct hardware neuromorphic computing systems.

Keywords: leaky integrate-and-fire, memristor, spiking neural networks, spiking-time-dependent-plasticity

Procedia PDF Downloads 96

Authors: Michael Fundator

Abstract:

Groundbreaking application of biomathematical and biochemical research in neural networks processes to formation of non-canonical bases, islands, and analog bases in DNA and mRNA at or near the transcription that contradicts the long anticipated statistical assumptions for the distribution of bases and analog bases compounds is implemented through statistical and stochastic methods apparatus with addition of quantum principles, where the usual transience of Poisson spike train becomes very instrumental tool for finding even almost periodical type of solutions to Fokker-Plank stochastic differential equation. Present article develops new multidimensional methods of finding solutions to stochastic differential equations based on more rigorous approach to mathematical apparatus through Kolmogorov-Chentsov continuity theorem that allows the stochastic processes with jumps under certain conditions to have γ-Holder continuous modification that is used as basis for finding analogous parallels in dynamics of neutral networks and formation of analog bases and transcription in DNA.

Keywords: Fokker-Plank stochastic differential equation, Kolmogorov-Chentsov continuity theorem, neural networks, translation and transcription

Procedia PDF Downloads 370

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: Sonia Perez-Gamboa, Qingquan Sun, Yan Zhang

Abstract:

Non-intrusive sensor-based human activity recognition (HAR) is utilized in a spectrum of applications, including fitness tracking devices, gaming, health care monitoring, and smartphone applications. Deep learning models such as convolutional neural networks (CNNs) and long short term memory (LSTM) recurrent neural networks (RNNs) provide a way to achieve HAR accurately and effectively. In this paper, we design a multi-layer hybrid architecture with CNN and LSTM and explore a variety of multi-layer combinations. Based on the exploration, we present a lightweight, hybrid, and multi-layer model, which can improve the recognition performance by integrating local features and scale-invariant with dependencies of activities. The experimental results demonstrate the efficacy of the proposed model, which can achieve a 94.7% activity recognition rate on a benchmark human activity dataset. This model outperforms traditional machine learning and other deep learning methods. Additionally, our implementation achieves a balance between recognition rate and training time consumption.

Keywords: deep learning, LSTM, CNN, human activity recognition, inertial sensor

Procedia PDF Downloads 117

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: Redhouane Ghernaout, Amira Fredj, Boualem Remini

Abstract:

Suspended sediment transport is a serious problem worldwide, but it is much more worrying in certain regions of the world, as is the case in the Maghreb and more particularly in Algeria. It continues to take disturbing proportions in Northern Algeria due to the variability of rains in time and in space and constant deterioration of vegetation. Its prediction is essential in order to identify its intensity and define the necessary actions for its reduction. The purpose of this study is to analyze the concentration data of suspended sediment measured at Wadi El-Abtal Hydrometric Station. It also aims to find and highlight regressive power relationships, which can explain the suspended solid flow by the measured liquid flow. The study strives to find models of artificial neural networks linking the flow, month and precipitation parameters with solid flow. The obtained results show that the power function of the solid transport rating curve and the models of artificial neural networks are appropriate methods for analysing and estimating suspended sediment transport in Wadi Mina at Wadi El-Abtal Hydrometric Station. They made it possible to identify in a fairly conclusive manner the model of neural networks with four input parameters: the liquid flow Q, the month and the daily precipitation measured at the representative stations (Frenda 013002 and Ain El-Hadid 013004 ) of the watershed. The model thus obtained makes it possible to estimate the daily solid flows (interpolate and extrapolate) even beyond the period of observation of solid flows (1985/86 to 1999/00), given the availability of the average daily liquid flows and daily precipitation since 1953/1954.

Keywords: suspended sediment, concentration, regression, liquid flow, solid flow, artificial neural network, modeling, mina, algeria

Procedia PDF Downloads 71

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: 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: Xuemei Yang, Xin Sun, Cheng Fu, Qiong Lan, Chao Han

Abstract:

Residual stresses, which can be produced during the manufacturing process of plastic bonded explosive (PBX), play an important role in weapon system security and reliability. Residual stresses can and do change in service. This paper mainly studies the influence of vibratory stress relief (VSR) and thermal aging on residual stress of explosives. Firstly, the residual stress relaxation of PBX via different physical condition of VSR, such as vibration time, amplitude and dynamic strain, were studied by drill-hole technique. The result indicated that the vibratory amplitude, time and dynamic strain had a significant influence on the residual stress relief of PBX. The rate of residual stress relief of PBX increases first and then decreases with the increase of dynamic strain, amplitude and time, because the activation energy is too small to make the PBX yield plastic deformation at first. Then the dynamic strain, time and amplitude exceed a certain threshold, the residual stress changes show the same rule and decrease sharply, this sharply drop of residual stress relief rate may have been caused by over vibration. Meanwhile, the comparison between VSR and thermal aging was also studied. The conclusion is that the reduction ratio of residual stress after VSR process with applicable vibratory parameters could be equivalent to 73% of thermal aging with 7 days. In addition, the density attenuation rate, mechanical property, and dimensional stability with 3 months after VSR process was almost the same compared with thermal aging. However, compared with traditional thermal aging, VSR only takes a very short time, which greatly improves the efficiency of aging treatment for explosive materials. Therefore, the VSR could be a potential alternative technique in the industry of residual stress relaxation of PBX explosives.

Keywords: explosives, residual stresses, thermal aging, vibratory stress relief, VSR

Procedia PDF Downloads 126

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: 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: Chico Horacio Jose Sambo

Abstract:

Recently neural network has gained popularity when come to solve complex nonlinear problems. Permeability is one of fundamental reservoir characteristics system that are anisotropic distributed and non-linear manner. For this reason, permeability prediction from well log data is well suited by using neural networks and other computer-based techniques. The main goal of this paper is to predict reservoir permeability from well logs data by using neural network approach. A multi-layered perceptron trained by back propagation algorithm was used to build the predictive model. The performance of the model on net results was measured by correlation coefficient. The correlation coefficient from testing, training, validation and all data sets was evaluated. The results show that neural network was capable of reproducing permeability with accuracy in all cases, so that the calculated correlation coefficients for training, testing and validation permeability were 0.96273, 0.89991 and 0.87858, respectively. The generalization of the results to other field can be made after examining new data, and a regional study might be possible to study reservoir properties with cheap and very fast constructed models.

Keywords: neural network, permeability, multilayer perceptron, well log

Procedia PDF Downloads 365

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: Mikheil Kalmakhelidze

Abstract:

Record linkage (RL) problem has become more and more important in recent years due to the growing interest towards big data analysis. The problem can be formulated in a very simple way: Given two entries a and b of a database, decide whether they represent the same object or not. There are two classical deterministic and probabilistic ways of solving the RL problem. Using simple Bayes classifier in many cases produces useful results but sometimes they show to be poor. In recent years several successful approaches have been made towards solving specific RL problems by neural network algorithms including single layer perception, multilayer back propagation network etc. In our work, we model the RL problem for specific dataset of student applications in fuzzy description logic (FDL) where linkage of specific pair (a,b) depends on the truth value of corresponding formula A(a,b) in a canonical FDL model. As a main result, we build neural network for deciding truth value of FDL formulas in a canonical model and thus link RL problem to machine learning. We apply the approach to dataset with 10000 entries and also compare to classical RL solving approaches. The results show to be more accurate than standard probabilistic approach.

Keywords: description logic, fuzzy logic, neural networks, record linkage

Procedia PDF Downloads 245

Authors: Michael Munther, Keivan Davami

Abstract:

One significant roadblock for additively manufactured (AM) parts is the buildup of residual tensile stresses during the fabrication process. These residual stresses are formed due to the intense localized thermal gradients and high cooling rates that cause non-uniform material expansion/contraction and mismatched strain profiles during powder-bed fusion techniques, such as direct metal laser sintering (DMLS). The residual stresses adversely affect the fatigue life of the AM parts. Moreover, if the residual stresses become higher than the material’s yield strength, they will lead to acute geometric distortion. These are limiting the applications and acceptance of AM components for safety-critical applications. Herein, we discuss laser shock peening method as an advanced technique for the manipulation of the residual stresses in AM parts. An X-ray diffraction technique is used for the measurements of the residual stresses before and after the laser shock peening process. Also, the hardness of the structures is measured using a nanoindentation technique. Maps of nanohardness and modulus are obtained from the nanoindentation, and a correlation is made between the residual stresses and the mechanical properties. The results indicate that laser shock peening is able to induce compressive residual stresses in the structure that mitigate the tensile residual stresses and increase the hardness of AM IN718, a superalloy, almost 20%. No significant changes were observed in the modulus after laser shock peening. The results strongly suggest that laser shock peening can be used as an advanced post-processing technique to optimize the service lives of critical components for various applications.

Keywords: additive manufacturing, Inconel 718, laser shock peening, residual stresses

Procedia PDF Downloads 99

Authors: Abebe Mulugojam Negash, Yongbin Yu, Ekong Favour, Bekalu Nigus Dawit, Molla Woretaw Teshome, Aynalem Birtukan Yirga

Abstract:

Breast cancer remains a significant health concern, necessitating advancements in diagnostic methodologies. Addressing this, our paper confronts the notable challenges in breast cancer classification, particularly the imbalance in datasets and the constraints in the accuracy and interpretability of prevailing deep learning approaches. We proposed an attention-based residual neural network (ResNet), which effectively combines the robust features of ResNet with an advanced attention mechanism. Enhanced through strategic data augmentation and positive weight adjustments, this approach specifically targets the issue of data imbalance. The proposed model is tested on the BreakHis dataset and achieved accuracies of 99.00%, 99.04%, 98.67%, and 98.08% in different magnifications (40X, 100X, 200X, and 400X), respectively. We evaluated the performance by using different evaluation metrics such as precision, recall, and F1-Score and made comparisons with other state-of-the-art methods. Our experiments demonstrate that the proposed model outperforms existing approaches, achieving higher accuracy in breast cancer classification.

Keywords: residual neural network, attention mechanism, positive weight, data augmentation

Procedia PDF Downloads 42

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: Giselle Maggie-Fer Castañeda Lozano

Abstract:

The main objective of this research was to explore the role of neural network architectures in simulating behavioral phenomena as a potential explanation for selective associations, specifically related to biological constraints on learning. Biological constraints on learning refer to the limitations observed in conditioning procedures, where learning is expected to occur. The study involved simulations of five different experiments exploring various phenomena and sources of biological constraints in learning. These simulations included the interaction between response and reinforcer, stimulus and reinforcer, specificity of stimulus-reinforcer associations, species differences, neuroanatomical constraints, and learning in uncontrolled conditions. The overall results demonstrated that by manipulating neural network architectures, conditions can be created to model and explain diverse biological constraints frequently reported in comparative psychology literature as learning typicities. Additionally, the simulations offer predictive content worthy of experimental testing in the pursuit of new discoveries regarding the specificity of learning. The implications and limitations of these findings are discussed. Finally, it is suggested that this research could inaugurate a line of inquiry involving the use of neural networks to study biological factors in behavior, fostering the development of more ethical and precise research practices.

Keywords: comparative psychology, connectionism, conditioning, experimental analysis of behavior, neural networks

Procedia PDF Downloads 37

Authors: Mst Shapna Akter, Hossain Shahriar

Abstract:

One of the most important challenges in the field of software code audit is the presence of vulnerabilities in software source code. Every year, more and more software flaws are found, either internally in proprietary code or revealed publicly. These flaws are highly likely exploited and lead to system compromise, data leakage, or denial of service. C and C++ open-source code are now available in order to create a largescale, machine-learning system for function-level vulnerability identification. We assembled a sizable dataset of millions of opensource functions that point to potential exploits. We developed an efficient and scalable vulnerability detection method based on deep neural network models that learn features extracted from the source codes. The source code is first converted into a minimal intermediate representation to remove the pointless components and shorten the dependency. Moreover, we keep the semantic and syntactic information using state-of-the-art word embedding algorithms such as glove and fastText. The embedded vectors are subsequently fed into deep learning networks such as LSTM, BilSTM, LSTM-Autoencoder, word2vec, BERT, and GPT-2 to classify the possible vulnerabilities. Furthermore, we proposed a neural network model which can overcome issues associated with traditional neural networks. Evaluation metrics such as f1 score, precision, recall, accuracy, and total execution time have been used to measure the performance. We made a comparative analysis between results derived from features containing a minimal text representation and semantic and syntactic information. We found that all of the deep learning models provide comparatively higher accuracy when we use semantic and syntactic information as the features but require higher execution time as the word embedding the algorithm puts on a bit of complexity to the overall system.

Keywords: cyber security, vulnerability detection, neural networks, feature extraction

Procedia PDF Downloads 45

Authors: Osamu Takakuwa, Yuta Mano, Hitoshi Soyama

Abstract:

This paper reveals the interaction between hydrogen and surface stress in austenitic stainless steel by X-ray diffraction stress measurement and thermal desorption analysis before and after being charged with hydrogen. The surface residual stress was varied by surface finishing using several disc polishing agents. The obtained results show that the residual stress near surface had a significant effect on hydrogen absorption behavior, that is, tensile residual stress promoted the hydrogen absorption and compressive one did opposite. Also, hydrogen induced equi-biaxial stress and this stress has a linear correlation with hydrogen content.

Keywords: hydrogen embrittlement, residual stress, surface finishing, stainless steel

Procedia PDF Downloads 350

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: Masoumeh Mofarrah, Amir NahanMoghadam

Abstract:

Higher oil prices and increasing oil demand are main reasons for great attention to Enhanced Oil Recovery (EOR). Comprehensive researches have been accomplished to develop, appraise, and improve EOR methods and their application. Recently, Artificial Intelligence (AI) gained popularity in petroleum industry that can help petroleum engineers to solve some fundamental petroleum engineering problems such as reservoir simulation, EOR project risk analysis, well log interpretation and well test model selection. This study presents a historical overview of most popular AI tools including neural networks, genetic algorithms, fuzzy logic, and expert systems in petroleum industry and discusses two case studies to represent the application of two mentioned AI methods for selecting an appropriate EOR method based on reservoir characterization infeasible and effective way.

Keywords: artificial intelligence, EOR, neural networks, expert systems

Procedia PDF Downloads 462

Authors: Paola Causin, Andrea Aspri, Alessandro Benfenati

Abstract:

Diffuse Optical Tomography (DOT) is an emergent medical imaging technique which employs NIR light to estimate the spatial distribution of optical coefficients in biological tissues for diagnostic purposes, in a noninvasive and non-ionizing manner. DOT reconstruction is a severely ill-conditioned problem due to prevalent scattering of light in the tissue. In this contribution, we present our research in adopting hybrid knowledgedriven/data-driven approaches which exploit the existence of well assessed physical models and build upon them neural networks integrating the availability of data. Namely, since in this context regularization procedures are mandatory to obtain a reasonable reconstruction [1], we explore the use of neural networks as tools to include prior information on the solution. 2. Materials and Methods The idea underlying our approach is to leverage neural networks to solve PDE-constrained inverse problems of the form 𝒒 ∗ = 𝒂𝒓𝒈 𝒎𝒊𝒏𝒒 𝐃(𝒚, 𝒚̃), (1) where D is a loss function which typically contains a discrepancy measure (or data fidelity) term plus other possible ad-hoc designed terms enforcing specific constraints. In the context of inverse problems like (1), one seeks the optimal set of physical parameters q, given the set of observations y. Moreover, 𝑦̃ is the computable approximation of y, which may be as well obtained from a neural network but also in a classic way via the resolution of a PDE with given input coefficients (forward problem, Fig.1 box ). Due to the severe ill conditioning of the reconstruction problem, we adopt a two-fold approach: i) we restrict the solutions (optical coefficients) to lie in a lower-dimensional subspace generated by auto-decoder type networks. This procedure forms priors of the solution (Fig.1 box ); ii) we use regularization procedures of type 𝒒̂ ∗ = 𝒂𝒓𝒈𝒎𝒊𝒏𝒒 𝐃(𝒚, 𝒚̃)+ 𝑹(𝒒), where 𝑹(𝒒) is a regularization functional depending on regularization parameters which can be fixed a-priori or learned via a neural network in a data-driven modality. To further improve the generalizability of the proposed framework, we also infuse physics knowledge via soft penalty constraints (Fig.1 box ) in the overall optimization procedure (Fig.1 box ). 3. Discussion and Conclusion DOT reconstruction is severely hindered by ill-conditioning. The combined use of data-driven and knowledgedriven elements is beneficial and allows to obtain improved results, especially with a restricted dataset and in presence of variable sources of noise.

Keywords: inverse problem in tomography, deep learning, diffuse optical tomography, regularization

Procedia PDF Downloads 44

Authors: Guilherme F. Guimaraes, Alfredo R. De Faria, Ronnie R. Rego, Andre L. R. D'Oliveira

Abstract:

The development of methods for predicting manufacturing phenomena steadily grows due to their high potential to contribute to the component’s performance and durability. One of the most relevant phenomena in manufacturing is the residual stress state development through the manufacturing chain. In most cases, the residual stresses have their origin due to heterogenous plastifications produced by the processes. Although a few manufacturing processes have been successfully approached by numerical modeling, there is still a lack of understanding on how these processes' interactions will affect the final stress state. The objective of this work is to analyze the influence of previous stresses on the residual stress state induced by plastic deformation of a quasi-static indentation. The model consists of a simplified approach of shot peening, modeling four cases with variations in indenter size and force. This model was validated through topography, measured by optical 3D focus-variation, and residual stress, measured with the X-ray diffraction technique. The validated model was then exposed to several initial stress states, and the effect on the final residual stress was analyzed.

Keywords: plasticity, residual stress, finite element method, manufacturing

Procedia PDF Downloads 176

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 183

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 496

Authors: Nestor A. Garcia Fragoso, Tetyana Baydyk, Ernst Kussul

Abstract:

This article contains information from our investigation in the field of voice recognition. For this purpose, we created a voice database that contains different phrases in two languages, English and Spanish, for men and women. As a classifier, the LIRA (Limited Receptive Area) grayscale neural classifier was selected. The LIRA grayscale neural classifier was developed for image recognition tasks and demonstrated good results. Therefore, we decided to develop a recognition system using this classifier for voice recognition. From a specific set of speakers, we can recognize the speaker’s voice. For this purpose, the system uses spectrograms of the voice signals as input to the system, extracts the characteristics and identifies the speaker. The results are described and analyzed in this article. The classifier can be used for speaker identification in security system or smart buildings for different types of intelligent devices.

Keywords: extreme learning, LIRA neural classifier, speaker identification, voice recognition

Procedia PDF Downloads 142

Authors: Shuen-Tai Wang, Fang-An Kuo, Chau-Yi Chou, Yu-Bin Fang

Abstract:

2016 has become the year of the Artificial Intelligence explosion. AI technologies are getting more and more matured that most world well-known tech giants are making large investment to increase the capabilities in AI. Machine learning is the science of getting computers to act without being explicitly programmed, and deep learning is a subset of machine learning that uses deep neural network to train a machine to learn  features directly from data. Deep learning realizes many machine learning applications which expand the field of AI. At the present time, deep learning frameworks have been widely deployed on servers for deep learning applications in both academia and industry. In training deep neural networks, there are many standard processes or algorithms, but the performance of different frameworks might be different. In this paper we evaluate the running performance of two state-of-the-art distributed deep learning frameworks that are running training calculation in parallel over multi GPU and multi nodes in our cloud environment. We evaluate the training performance of the frameworks with ResNet-50 convolutional neural network, and we analyze what factors that result in the performance among both distributed frameworks as well. Through the experimental analysis, we identify the overheads which could be further optimized. The main contribution is that the evaluation results provide further optimization directions in both performance tuning and algorithmic design.

Keywords: artificial intelligence, machine learning, deep learning, convolutional neural networks

Procedia PDF Downloads 174

Authors: Zeina Merabi, Arij Dao

Abstract:

The temporal order of information processing in the brain is an important code in many acoustic signals, including speech, music, and animal vocalizations. Despite its significance, surprisingly little is known about its underlying cellular mechanisms and network manifestations. In the songbird telencephalic nucleus HVC, a subset of neurons shows temporal combination sensitivity (TCS). These neurons show a high temporal specificity, responding differently to distinct patterns of spectral elements and their combinations. HVC neuron types include basal-ganglia-projecting HVCX, forebrain-projecting HVCRA, and interneurons (HVC¬INT), each exhibiting distinct cellular, electrophysiological and functional properties. In this work, we develop conductance-based neural network models connecting the different classes of HVC neurons via different wiring scenarios, aiming to explore possible neural mechanisms that orchestrate the combination sensitivity property exhibited by HVCX, as well as replicating in vivo firing patterns observed when TCS neurons are presented with various auditory stimuli. The ionic and synaptic currents for each class of neurons that are presented in our networks and are based on pharmacological studies, rendering our networks biologically plausible. We present for the first time several realistic scenarios in which the different types of HVC neurons can interact to produce this behavior. The different networks highlight neural mechanisms that could potentially help to explain some aspects of combination sensitivity, including 1) interplay between inhibitory interneurons’ activity and the post inhibitory firing of the HVCX neurons enabled by T-type Ca2+ and H currents, 2) temporal summation of synaptic inputs at the TCS site of opposing signals that are time-and frequency- dependent, and 3) reciprocal inhibitory and excitatory loops as a potent mechanism to encode information over many milliseconds. The result is a plausible network model characterizing auditory processing in HVC. Our next step is to test the predictions of the model.

Keywords: combination sensitivity, songbirds, neural networks, spatiotemporal integration

Procedia PDF Downloads 37