Search results for: neural network model

Authors: Danladi Ali, Onah Festus Iloabuchi

Abstract:

In this paper, GSM signal strength was measured in order to detect the type of the signal fading phenomenon using one-dimensional multilevel wavelet residual method and neural network clustering to determine the average GSM signal strength received in the study area. The wavelet residual method predicted that the GSM signal experienced slow fading and attenuated with MSE of 3.875dB. The neural network clustering revealed that mostly -75dB, -85dB and -95dB were received. This means that the signal strength received in the study is a weak signal.

Keywords: one-dimensional multilevel wavelets, path loss, GSM signal strength, propagation, urban environment

Procedia PDF Downloads 336

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 290

Authors: Bingquan Shen

Abstract:

Convolutional Neural Networks (CNN) have demonstrated their effectiveness in synthesizing 3D views of object instances at various viewpoints. Given the problem where one have limited viewpoints of a particular object for classification, we present a pose normalization architecture to transform the object to existing viewpoints in the training dataset before classification to yield better classification performance. We have demonstrated that this Pose Normalization Network (PNN) can capture the style of the target object and is able to re-render it to a desired viewpoint. Moreover, we have shown that the PNN improves the classification result for the 3D chairs dataset and ShapeNet airplanes dataset when given only images at limited viewpoint, as compared to a CNN baseline.

Keywords: convolutional neural networks, object classification, pose normalization, viewpoint invariant

Procedia PDF Downloads 351

Authors: Thomas Adi Purnomo Sidhi

Abstract:

Nowadays, network is an essential need in almost every part of human daily activities. People now can seamlessly connect to others through the Internet. With advanced technology, our personal data now can be more easily accessed. One of many components we are concerned for delivering the best network is a security issue. This paper is proposing a method that provides more options for security. This research aims to improve network security by focusing on the physical layer which is the first layer of the OSI model. The layer consists of the basic networking hardware transmission technologies of a network. With the use of observation method, the research produces a schematic design for enhancing the network security through the gray code converter.

Keywords: network, network security, grey code, physical layer

Procedia PDF Downloads 498

Authors: Salim Ouchtati, Aissa Belmeguenai, Mouldi Bedda

Abstract:

In this study, we propose an offline system for the recognition of the fragmented handwritten numeric chains. Firstly, we realized a recognition system of the isolated handwritten digits, in this part; the study is based mainly on the evaluation of neural network performances, trained with the gradient backpropagation algorithm. The used parameters to form the input vector of the neural network are extracted from the binary images of the isolated handwritten digit by several methods: the distribution sequence, sondes application, the Barr features, and the centered moments of the different projections and profiles. Secondly, the study is extended for the reading of the fragmented handwritten numeric chains constituted of a variable number of digits. The vertical projection was used to segment the numeric chain at isolated digits and every digit (or segment) was presented separately to the entry of the system achieved in the first part (recognition system of the isolated handwritten digits).

Keywords: features extraction, handwritten numeric chains, image processing, neural networks

Procedia PDF Downloads 265

Authors: Reza Rezaeipour Honarmandzad

Abstract:

In this paper we propose an ANN for detection and localization of fatigue damage in aircraft structures. We used network of piezoelectric transducers for Lamb-wave measurements in order to calculate damage indices. Data gathered by the sensors was given to neural network classifier. A set of neural network electors of different architecture cooperates to achieve consensus concerning the state of each monitored path. Sensed signal variations in the ROI, detected by the networks at each path, were used to assess the state of the structure as well as to localize detected damage and to filter out ambient changes. The classifier has been extensively tested on large data sets acquired in the tests of specimens with artificially introduced notches as well as the results of numerous fatigue experiments. Effect of the classifier structure and test data used for training on the results was evaluated.

Keywords: ANN, fatigue damage, aircraft structures, piezoelectric transducers, lamb-wave measurements

Procedia PDF Downloads 417

Authors: Sakir Tasdemir, Mustafa Altin, Gamze Fahriye Pehlivan, Sadiye Didem Boztepe Erkis, Ismail Saritas, Selma Tasdemir

Abstract:

Artificial intelligence applications are commonly used in industry in many fields in parallel with the developments in the computer technology. In this study, a fire room was prepared for the resistance of wooden construction elements and with the mechanism here, the experiments of polished materials were carried out. By utilizing from the experimental data, an artificial neural network (ANN) was modeled in order to evaluate the final cross sections of the wooden samples remaining from the fire. In modelling, experimental data obtained from the fire room were used. In the system developed, the first weight of samples (ws-gr), preliminary cross-section (pcs-mm2), fire time (ft-minute), fire temperature (t-oC) as input parameters and final cross-section (fcs-mm2) as output parameter were taken. When the results obtained from ANN and experimental data are compared after making statistical analyses, the data of two groups are determined to be coherent and seen to have no meaning difference between them. As a result, it is seen that ANN can be safely used in determining cross sections of wooden materials after fire and it prevents many disadvantages.

Keywords: artificial neural network, final cross-section, fire retardant polishes, fire safety, wood resistance.

Procedia PDF Downloads 383

Authors: Ismail Abubakar, Hamid Mehrabi, Reg Morton

Abstract:

Currently, extensive signal analysis is performed in order to evaluate structural health of turbomachinery blades. This approach is affected by constraints of time and the availability of qualified personnel. Thus, new approaches to blade dynamics identification that provide faster and more accurate results are sought after. Generally, modal analysis is employed in acquiring dynamic properties of a vibrating turbomachinery blade and is widely adopted in condition monitoring of blades. The analysis provides useful information on the different modes of vibration and natural frequencies by exploring different shapes that can be taken up during vibration since all mode shapes have their corresponding natural frequencies. Experimental modal testing and finite element analysis are the traditional methods used to evaluate mode shapes with limited application to real live scenario to facilitate a robust condition monitoring scheme. For a real time mode shape evaluation, rapid evaluation and low computational cost is required and traditional techniques are unsuitable. In this study, artificial neural network is developed to evaluate the mode shape of a lab scale rotating blade assembly by using result from finite element modal analysis as training data. The network performance evaluation shows that artificial neural network (ANN) is capable of mapping the correlation between natural frequencies and mode shapes. This is achieved without the need of extensive signal analysis. The approach offers advantage from the perspective that the network is able to classify mode shapes and can be employed in real time including simplicity in implementation and accuracy of the prediction. The work paves the way for further development of robust condition monitoring system that incorporates real time mode shape evaluation.

Keywords: modal analysis, artificial neural network, mode shape, natural frequencies, pattern recognition

Procedia PDF Downloads 156

Authors: Syed Mahbubuz Zaman, A. B. M. Abrar Haque, Mehedi Hassan Nayeem, Misbah Uddin Sagor

Abstract:

Everyday e-mails are being used by millions of people as an effective form of communication over the Internet. Although e-mails allow high-speed communication, there is a constant threat known as spam. Spam e-mail is often called junk e-mails which are unsolicited and sent in bulk. These unsolicited emails cause security concerns among internet users because they are being exposed to inappropriate content. There is no guaranteed way to stop spammers who use static filters as they are bypassed very easily. In this paper, a smart system is proposed that will be using neural networks to approach spam in a different way, and meanwhile, this will also detect the most relevant features that will help to design the spam filter. Also, a comparison of different parameters for different neural network models has been shown to determine which model works best within suitable parameters.

Keywords: long short-term memory, bidirectional long short-term memory, gated recurrent unit, natural language processing, natural language processing

Procedia PDF Downloads 204

Authors: Busra Mutlu Ipek, Merve Mutlu, Ahmet Mutlu

Abstract:

Novel coronavirus COVID-19, which has recently influenced the world, poses a great threat to humanity. In order to overcome this challenging situation, scientists are working on developing effective vaccine against coronavirus. Many experts and researchers have also produced articles and done studies on this highly important subject. In this direction, this special topic was chosen for article to make a contribution to this area. The purpose of this article is to perform RNA sequence analysis of selected virus forms in the Coronaviridae family and predict/classify SARS-CoV-2 (COVID-19) from other selected complete genomes in coronaviridae family using proposed Artificial Neural Network(ANN) algorithm.

Keywords: Coronaviridae family, COVID-19, RNA sequencing, ANN, neural network

Procedia PDF Downloads 142

Authors: Zsolt János Viharos, Krisztián Balázs Kis, Imre Paniti, Gábor Belső, Péter Németh, János Farkas

Abstract:

The paper presents the results and industrial applications in the production setup period estimation based on industrial data inherited from the field of polymer cutting. The literature of polymer cutting is very limited considering the number of publications. The first polymer cutting machine is known since the second half of the 20th century; however, the production of polymer parts with this kind of technology is still a challenging research topic. The products of the applying industrial partner must met high technical requirements, as they are used in medical, measurement instrumentation and painting industry branches. Typically, 20% of these parts are new work, which means every five years almost the entire product portfolio is replaced in their low series manufacturing environment. Consequently, it requires a flexible production system, where the estimation of the frequent setup periods' lengths is one of the key success factors. In the investigation, several (input) parameters have been studied and grouped to create an adequate training information set for an artificial neural network as a base for the estimation of the individual setup periods. In the first group, product information is collected such as the product name and number of items. The second group contains material data like material type and colour. In the third group, surface quality and tolerance information are collected including the finest surface and tightest (or narrowest) tolerance. The fourth group contains the setup data like machine type and work shift. One source of these parameters is the Manufacturing Execution System (MES) but some data were also collected from Computer Aided Design (CAD) drawings. The number of the applied tools is one of the key factors on which the industrial partners’ estimations were based previously. The artificial neural network model was trained on several thousands of real industrial data. The mean estimation accuracy of the setup periods' lengths was improved by 30%, and in the same time the deviation of the prognosis was also improved by 50%. Furthermore, an investigation on the mentioned parameter groups considering the manufacturing order was also researched. The paper also highlights the manufacturing introduction experiences and further improvements of the proposed methods, both on the shop floor and on the quotation preparation fields. Every week more than 100 real industrial setup events are given and the related data are collected.

Keywords: artificial neural network, low series manufacturing, polymer cutting, setup period estimation

Procedia PDF Downloads 243

Authors: Gaetano Zazzaro, Angelo Martone, Roberto V. Montaquila, Luigi Pavone

Abstract:

Seizure is the main factor that affects the quality of life of epileptic patients. The diagnosis of epilepsy, and hence the identification of epileptogenic zone, is commonly made by using continuous Electroencephalogram (EEG) signal monitoring. Seizure identification on EEG signals is made manually by epileptologists and this process is usually very long and error prone. The aim of this paper is to describe an automated method able to detect seizures in EEG signals, using knowledge discovery in database process and data mining methods and algorithms, which can support physicians during the seizure detection process. Our detection method is based on Artificial Neural Network classifier, trained by applying the multilayer perceptron algorithm, and by using a software application, called Training Builder that has been developed for the massive extraction of features from EEG signals. This tool is able to cover all the data preparation steps ranging from signal processing to data analysis techniques, including the sliding window paradigm, the dimensionality reduction algorithms, information theory, and feature selection measures. The final model shows excellent performances, reaching an accuracy of over 99% during tests on data of a single patient retrieved from a publicly available EEG dataset.

Keywords: artificial neural network, data mining, electroencephalogram, epilepsy, feature extraction, seizure detection, signal processing

Procedia PDF Downloads 187

Authors: Mustafa Tosun, Kevser Dincer

Abstract:

In this study, analysis on whether the lightweight concrete walled structures used in four climatic regions of Turkey are also capable of insulating sound was conducted. As a new approach, first the wall’s thermal insulation sufficiency’s were calculated and then, artificial neural network (ANN) modeling was used on their cross sections to check if they are sound transmitters too. The ANN was trained and tested by using MATLAB toolbox on a personal computer. ANN input parameters that used were thickness of lightweight concrete wall, frequency and density of lightweight concrete wall, while the transmitted sound was the output parameter. When the results of the TS analysis and those of ANN modeling are evaluated together, it is found from this study, that sound transmit loss increases at higher frequencies, higher wall densities and with larger wall cross sections.

Keywords: artificial neuron network, lightweight concrete, sound insulation, sound transmit loss

Procedia PDF Downloads 251

Authors: Berkan Ural, Arif Eser, Sinan Apaydin

Abstract:

Medical image processing is generally become a challenging task nowadays. Indeed, processing of brain MRI images is one of the difficult parts of this area. This study proposes a hybrid well-defined approach which is consisted from tumor detection, extraction and analyzing steps. This approach is mainly consisted from a computer aided diagnostics system for identifying and detecting the tumor formation in any region of the brain and this system is commonly used for early prediction of brain tumor using advanced image processing and probabilistic neural network methods, respectively. For this approach, generally, some advanced noise removal functions, image processing methods such as automatic segmentation and morphological operations are used to detect the brain tumor boundaries and to obtain the important feature parameters of the tumor region. All stages of the approach are done specifically with using MATLAB software. Generally, for this approach, firstly tumor is successfully detected and the tumor area is contoured with a specific colored circle by the computer aided diagnostics program. Then, the tumor is segmented and some morphological processes are achieved to increase the visibility of the tumor area. Moreover, while this process continues, the tumor area and important shape based features are also calculated. Finally, with using the probabilistic neural network method and with using some advanced classification steps, tumor area and the type of the tumor are clearly obtained. Also, the future aim of this study is to detect the severity of lesions through classes of brain tumor which is achieved through advanced multi classification and neural network stages and creating a user friendly environment using GUI in MATLAB. In the experimental part of the study, generally, 100 images are used to train the diagnostics system and 100 out of sample images are also used to test and to check the whole results. The preliminary results demonstrate the high classification accuracy for the neural network structure. Finally, according to the results, this situation also motivates us to extend this framework to detect and localize the tumors in the other organs.

Keywords: image processing algorithms, magnetic resonance imaging, neural network, pattern recognition

Procedia PDF Downloads 416

Authors: Kamyar Fakhr, Roozbeh Salmani

Abstract:

Alphonse Bertillon developed the first biometric security system in the 1800s. Today, many governments and giant companies are considering or have procured biometrically enabled security schemes. Iris is a kaleidoscope of patterns and colors. Each individual holds a set of irises more unique than their thumbprint. Every single day, giant companies like Google and Apple are experimenting with reliable biometric systems. Now, after almost 200 years of improvements, face ID does not work with masks, it gives access to fake 3D images, and there is no global usage of biometric recognition systems as national identity (ID) card. The goal of this paper is to demonstrate the advantages of iris recognition overall biometric recognition systems. It make two extensions: first, we illustrate how a very large amount of internet fraud and cyber abuse is happening due to bugs in face recognition systems and in a very large dataset of 3.4M people; second, we discuss how establishing a secure global network of iris recognition devices connected to authoritative convolutional neural networks could be the safest solution to this dilemma. Another aim of this study is to provide a system that will prevent system infiltration caused by cyber-attacks and will block all wireframes to the data until the main user ceases the procedure.

Keywords: biometric system, convolutional neural network, cyber-attack, secure

Procedia PDF Downloads 217

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 331

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 249

Authors: H. Bonakdari, I. Ebtehaj

Abstract:

The prediction of scour depth around bridge piers is frequently considered in river engineering. One of the key aspects in efficient and optimum bridge structure design is considered to be scour depth estimation around bridge piers. In this study, scour depth around bridge piers is estimated using two methods, namely the Adaptive Neuro-Fuzzy Inference System (ANFIS) and Artificial Neural Network (ANN). Therefore, the effective parameters in scour depth prediction are determined using the ANN and ANFIS methods via dimensional analysis, and subsequently, the parameters are predicted. In the current study, the methods’ performances are compared with the nonlinear regression (NLR) method. The results show that both methods presented in this study outperform existing methods. Moreover, using the ratio of pier length to flow depth, ratio of median diameter of particles to flow depth, ratio of pier width to flow depth, the Froude number and standard deviation of bed grain size parameters leads to optimal performance in scour depth estimation.

Keywords: adaptive neuro-fuzzy inference system (ANFIS), artificial neural network (ANN), bridge pier, scour depth, nonlinear regression (NLR)

Procedia PDF Downloads 217

Authors: Kyung-Jin You, Kiwon Rhee, Marc H. Schieber, Nitish V. Thakor, Hyun-Chool Shin

Abstract:

It remains unknown whether M1 neurons encode multi-finger movements independently or as a certain neural network of single finger movements although multi-finger movements are physically a combination of single finger movements. We present an evidence of correlation between single and multi-finger movements and also attempt a challenging task of semi-blind decoding of neural data with minimum training of the neural decoder. Data were collected from 115 task-related neurons in M1 of a trained rhesus monkey performing flexion and extension of each finger and the wrist (12 single and 6 two-finger-movements). By exploiting correlation of temporal firing pattern between movements, we found that correlation coefficient for physically related movements pairs is greater than others; neurons tuned to single finger movements increased their firing rate when multi-finger commands were instructed. According to this knowledge, neural semi-blind decoding is done by choosing the greatest and the second greatest likelihood for canonical candidates. We achieved a decoding accuracy about 60% for multiple finger movement without corresponding training data set. this results suggest that only with the neural activities on single finger movements can be exploited to control dexterous multi-fingered neuroprosthetics.

Keywords: finger movement, neural activity, blind decoding, M1

Procedia PDF Downloads 318

Authors: Muhamad Aris Burhanudin, Angga Firmansyas, Bagus Jaya Santosa

Abstract:

Earthquakes are natural hazard that can trigger the most dangerous hazard, tsunami. 26 December 2004, a giant earthquake occurred in north-west Andalas Island. It made giant tsunami which crushed Sumatra, Bangladesh, India, Sri Lanka, Malaysia and Singapore. More than twenty thousand people dead. The occurrence of earthquake and tsunami can not be avoided. But this hazard can be mitigated by earthquake forecasting. Early preparation is the key factor to reduce its damages and consequences. We aim to investigate quantitatively on pattern of earthquake. Then, we can know the trend. We study about earthquake which has happened in Andalas island, Indonesia one last decade. Andalas is island which has high seismicity, more than a thousand event occur in a year. It is because Andalas island is in tectonic subduction zone of Hindia sea plate and Eurasia plate. A tsunami forecasting is needed to mitigation action. Thus, a Tsunami Forecasting Method is presented in this work. Neutral Network has used widely in many research to estimate earthquake and it is convinced that by using Backpropagation Method, earthquake can be predicted. At first, ANN is trained to predict Tsunami 26 December 2004 by using earthquake data before it. Then after we get trained ANN, we apply to predict the next earthquake. Not all earthquake will trigger Tsunami, there are some characteristics of earthquake that can cause Tsunami. Wrong decision can cause other problem in the society. Then, we need a method to reduce possibility of wrong decision. Fuzzy TOPSIS is a statistical method that is widely used to be decision seconder referring to given parameters. Fuzzy TOPSIS method can make the best decision whether it cause Tsunami or not. This work combines earthquake prediction using neural network method and using Fuzzy TOPSIS to determine the decision that the earthquake triggers Tsunami wave or not. Neural Network model is capable to capture non-linear relationship and Fuzzy TOPSIS is capable to determine the best decision better than other statistical method in tsunami prediction.

Keywords: earthquake, fuzzy TOPSIS, neural network, tsunami

Procedia PDF Downloads 489

Authors: Pavan K. Rallabandi, Kailash C. Patidar

Abstract:

In this paper, we present an optimization technique or a learning algorithm using the hybrid architecture by combining the most popular sequence recognition models such as Recurrent Neural Networks (RNNs) and Hidden Markov models (HMMs). In order to improve the sequence or pattern recognition/ classification performance by applying a hybrid/neural symbolic approach, a gradient descent learning algorithm is developed using the Real Time Recurrent Learning of Recurrent Neural Network for processing the knowledge represented in trained Hidden Markov Models. The developed hybrid algorithm is implemented on automata theory as a sample test beds and the performance of the designed algorithm is demonstrated and evaluated on learning the deterministic finite state automata.

Keywords: hybrid systems, hidden markov models, recurrent neural networks, deterministic finite state automata

Procedia PDF Downloads 387

Authors: Gong Zhilin, Jing Yang, Jian Yin

Abstract:

The purpose of this paper is to develop a novel system for credit card fraud detection based on sequential modeling of data using hybrid deep learning models. The projected model encapsulates five major phases are pre-processing, imbalance-data handling, feature extraction, optimal feature selection, and fraud detection with an ensemble classifier. The collected raw data (input) is pre-processed to enhance the quality of the data through alleviation of the missing data, noisy data as well as null values. The pre-processed data are class imbalanced in nature, and therefore they are handled effectively with the K-means clustering-based SMOTE model. From the balanced class data, the most relevant features like improved Principal Component Analysis (PCA), statistical features (mean, median, standard deviation) and higher-order statistical features (skewness and kurtosis). Among the extracted features, the most optimal features are selected with the Self-improved Arithmetic Optimization Algorithm (SI-AOA). This SI-AOA model is the conceptual improvement of the standard Arithmetic Optimization Algorithm. The deep learning models like Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN), and optimized Quantum Deep Neural Network (QDNN). The LSTM and CNN are trained with the extracted optimal features. The outcomes from LSTM and CNN will enter as input to optimized QDNN that provides the final detection outcome. Since the QDNN is the ultimate detector, its weight function is fine-tuned with the Self-improved Arithmetic Optimization Algorithm (SI-AOA).

Keywords: credit card, data mining, fraud detection, money transactions

Procedia PDF Downloads 128

Authors: Lizhi Ma, Dan Liu

Abstract:

Pipeline parallelism has been widely used to accelerate distributed deep learning to alleviate GPU memory bottlenecks and to ensure that models can be trained and deployed smoothly under limited graphics memory conditions. However, in highly heterogeneous distributed clusters, traditional model partitioning methods are not able to achieve load balancing. The overlap of communication and computation is also a big challenge. In this paper, HePipe is proposed, an efficient pipeline parallel training method for highly heterogeneous clusters. According to the characteristics of the neural network model pipeline training task, oriented to the 2-level heterogeneous cluster computing topology, a training method based on the 2-level stage division of neural network modeling and partitioning is designed to improve the parallelism. Additionally, a multi-forward 1F1B scheduling strategy is designed to accelerate the training time of each stage by executing the computation units in advance to maximize the overlap between the forward propagation communication and backward propagation computation. Finally, a dynamic recomputation strategy based on task memory requirement prediction is proposed to improve the fitness ratio of task and memory, which improves the throughput of the cluster and solves the memory shortfall problem caused by memory differences in heterogeneous clusters. The empirical results show that HePipe improves the training speed by 1.6×−2.2× over the existing asynchronous pipeline baselines.

Keywords: pipeline parallelism, heterogeneous cluster, model training, 2-level stage partitioning

Procedia PDF Downloads 16

Authors: S. Mehrab Amiri, Nasser Talebbeydokhti

Abstract:

Modeling sediment transport processes by means of numerical approach often poses severe challenges. In this way, a number of techniques have been suggested to solve flow and sediment equations in decoupled, semi-coupled or fully coupled forms. Furthermore, in order to capture flow discontinuities, a number of techniques, like artificial viscosity and shock fitting, have been proposed for solving these equations which are mostly required careful calibration processes. In this research, a numerical scheme for solving shallow water and Exner equations in fully coupled form is presented. First-Order Centered scheme is applied for producing required numerical fluxes and the reconstruction process is carried out toward using Monotonic Upstream Scheme for Conservation Laws to achieve a high order scheme.  In order to satisfy C-property of the scheme in presence of bed topography, Surface Gradient Method is proposed. Combining the presented scheme with fourth order Runge-Kutta algorithm for time integration yields a competent numerical scheme. In addition, to handle non-prismatic channels problems, Cartesian Cut Cell Method is employed. A trained Multi-Layer Perceptron Artificial Neural Network which is of Feed Forward Back Propagation (FFBP) type estimates sediment flow discharge in the model rather than usual empirical formulas. Hydrodynamic part of the model is tested for showing its capability in simulation of flow discontinuities, transcritical flows, wetting/drying conditions and non-prismatic channel flows. In this end, dam-break flow onto a locally non-prismatic converging-diverging channel with initially dry bed conditions is modeled. The morphodynamic part of the model is verified simulating dam break on a dry movable bed and bed level variations in an alluvial junction. The results show that the model is capable in capturing the flow discontinuities, solving wetting/drying problems even in non-prismatic channels and presenting proper results for movable bed situations. It can also be deducted that applying Artificial Neural Network, instead of common empirical formulas for estimating sediment flow discharge, leads to more accurate results.

Keywords: artificial neural network, morphodynamic model, sediment continuity equation, shallow water equations

Procedia PDF Downloads 185

Authors: K. Padmavathi, K. Sri Ramakrishna

Abstract:

This study describes a procedure for the detection of Left and Right Bundle Branch Block (LBBB and RBBB) ECG patterns using spectral Coherence(SC) technique and LM Neural Network. The Coherence function finds common frequencies between two signals and evaluate the similarity of the two signals. The QT variations of Bundle Blocks are observed in lead V1 of ECG. Spectral Coherence technique uses Welch method for calculating PSD. For the detection of normal and Bundle block beats, SC output values are given as the input features for the LMNN classifier. Overall accuracy of LMNN classifier is 99.5 percent. The data was collected from MIT-BIH Arrhythmia database.

Keywords: bundle block, SC, LMNN classifier, welch method, PSD, MIT-BIH, arrhythmia database

Procedia PDF Downloads 280

Authors: Sanjeev Kumar Sharma, Arnab Mondal, Ranjit Kumar Upadhyay

Abstract:

Excitable cells often produce different oscillatory activities that help us to understand the transmitting and processing of signals in the neural system. We consider a FitzHugh-Rinzel (FH-R) model and studied the different dynamics of the model by considering the parameter c as the predominant parameter. The model exhibits different types of neuronal responses such as regular spiking, mixed-mode bursting oscillations (MMBOs), elliptic bursting, etc. Based on the bifurcation diagram, we consider the three regimes (MMBOs, elliptic bursting, and quiescent state). An analytical treatment for the occurrence of the supercritical Hopf bifurcation is studied. Further, we extend our study to a network of a hundred neurons by considering the bi-directional synaptic coupling between them. In this article, we investigate the alternation of spiking propagation and bursting phenomena of an uncoupled and coupled FH-R neurons. We explore that the complete graph of heterogenous desynchronized neurons can exhibit different types of bursting oscillations for certain coupling strength. For higher coupling strength, all the neurons in the network show complete synchronization.

Keywords: excitable neuron model, spiking-bursting, stability and bifurcation, synchronization networks

Procedia PDF Downloads 126

Authors: René A. Sørensen, Søren Skovsen, Peter Christiansen, Henrik Karstoft

Abstract:

Autonomous agricultural machines act in stochastic surroundings and therefore, must be able to perceive the surroundings in real time. This perception can be achieved using image sensors combined with advanced machine learning, in particular Deep Learning. Deep convolutional neural networks excel in labeling and perceiving color images and since the cost of high-quality RGB-cameras is low, the hardware cost of good perception depends heavily on memory and computation power. This paper investigates the possibility of designing lightweight convolutional neural networks for semantic segmentation (pixel wise classification) with reduced hardware requirements, to allow for embedded usage in autonomous agricultural machines. Using compression techniques, a lightweight convolutional neural network is designed to perform real-time semantic segmentation on an embedded platform. The network is trained on two large datasets, ImageNet and Pascal Context, to recognize up to 400 individual classes. The 400 classes are remapped into agricultural superclasses (e.g. human, animal, sky, road, field, shelterbelt and obstacle) and the ability to provide accurate real-time perception of agricultural surroundings is studied. The network is applied to the case of autonomous grass mowing using the NVIDIA Tegra X1 embedded platform. Feeding case-specific images to the network results in a fully segmented map of the superclasses in the image. As the network is still being designed and optimized, only a qualitative analysis of the method is complete at the abstract submission deadline. Proceeding this deadline, the finalized design is quantitatively evaluated on 20 annotated grass mowing images. Lightweight convolutional neural networks for semantic segmentation can be implemented on an embedded platform and show competitive performance with regards to accuracy and speed. It is feasible to provide cost-efficient perceptive capabilities related to semantic segmentation for autonomous agricultural machines.

Keywords: autonomous agricultural machines, deep learning, safety, visual perception

Procedia PDF Downloads 394

Authors: Tanmay Bisen, Aastha Shayla, Susham Biswas

Abstract:

Oil spills from tankers can cause significant harm to the environment and local communities, as well as have economic consequences. Early predictions of oil spills can help to minimize these impacts. Our proposed system uses machine learning and neural networks to predict potential oil spills by monitoring data from ship Automatic Identification Systems (AIS). The model analyzes ship movements, speeds, and changes in direction to identify patterns that deviate from the norm and could indicate a potential spill. Our approach not only identifies anomalies but also predicts spills before they occur, providing early detection and mitigation measures. This can prevent or minimize damage to the reputation of the company responsible and the country where the spill takes place. The model's performance on the MV Wakashio oil spill provides insight into its ability to detect and respond to real-world oil spills, highlighting areas for improvement and further research.

Keywords: Anomaly Detection, Oil Spill Prediction, Machine Learning, Image Processing, Graph Neural Network (GNN)

Procedia PDF Downloads 72

Authors: Jingling Li, Yi Zhang, Wei Liang, Tao Cui, Jun Li

Abstract:

Compared with terrestrial network, the traffic of spatial information network has both self-similarity and short correlation characteristics. By studying its traffic prediction method, the resource utilization of spatial information network can be improved, and the method can provide an important basis for traffic planning of a spatial information network. In this paper, considering the accuracy and complexity of the algorithm, the spatial information network traffic is decomposed into approximate component with long correlation and detail component with short correlation, and a time series hybrid prediction model based on wavelet decomposition is proposed to predict the spatial network traffic. Firstly, the original traffic data are decomposed to approximate components and detail components by using wavelet decomposition algorithm. According to the autocorrelation and partial correlation smearing and truncation characteristics of each component, the corresponding model (AR/MA/ARMA) of each detail component can be directly established, while the type of approximate component modeling can be established by ARIMA model after smoothing. Finally, the prediction results of the multiple models are fitted to obtain the prediction results of the original data. The method not only considers the self-similarity of a spatial information network, but also takes into account the short correlation caused by network burst information, which is verified by using the measured data of a certain back bone network released by the MAWI working group in 2018. Compared with the typical time series model, the predicted data of hybrid model is closer to the real traffic data and has a smaller relative root means square error, which is more suitable for a spatial information network.

Keywords: spatial information network, traffic prediction, wavelet decomposition, time series model

Procedia PDF Downloads 144

Authors: Massimo Miccoli, Luca Marangoni, Alberto Aniello Scaringi, Alessandro Marceddu, Alessandro Amicone

Abstract:

The susceptibility of deep neural networks (DNNs) to adversarial manipulations is a recognized challenge within the computer vision domain. Adversarial examples, crafted by adding subtle yet malicious alterations to benign images, exploit this vulnerability. Various defense strategies have been proposed to safeguard DNNs against such attacks, stemming from diverse research hypotheses. Building upon prior work, our approach involves the utilization of autoencoder models. Autoencoders, a type of neural network, are trained to learn representations of training data and reconstruct inputs from these representations, typically minimizing reconstruction errors like mean squared error (MSE). Our autoencoder was trained on a dataset of benign examples; learning features specific to them. Consequently, when presented with significantly perturbed adversarial examples, the autoencoder exhibited high reconstruction errors. The architecture of the autoencoder was tailored to the dimensions of the images under evaluation. We considered various image sizes, constructing models differently for 256x256 and 512x512 images. Moreover, the choice of the computer vision model is crucial, as most adversarial attacks are designed with specific AI structures in mind. To mitigate this, we proposed a method to replace image-specific dimensions with a structure independent of both dimensions and neural network models, thereby enhancing robustness. Our multi-modal autoencoder reconstructs the spectral representation of images across the red-green-blue (RGB) color channels. To validate our approach, we conducted experiments using diverse datasets and subjected them to adversarial attacks using models such as ResNet50 and ViT_L_16 from the torch vision library. The autoencoder extracted features used in a classification model, resulting in an MSE (RGB) of 0.014, a classification accuracy of 97.33%, and a precision of 99%.

Keywords: adversarial attacks, malicious images detector, binary classifier, multimodal transformer autoencoder

Procedia PDF Downloads 111