Search results for: neural network training

Authors: Elias Nemer, Greg Vines

Abstract:

Time-frequency transformation and spectral representations of audio signals are commonly used in various machine learning applications. Training networks on frequency features such as the Mel-Spectrogram or Cochleogram have been proven more effective and convenient than training on-time samples. In practical realizations, these features are created on a different processor and/or pre-computed and stored on disk, requiring additional efforts and making it difficult to experiment with different features. In this paper, we provide a PyTorch framework for creating various spectral features as well as time-frequency transformation and time-domain filter-banks using the built-in trainable conv1d() layer. This allows computing these features on the fly as part of a larger network and enabling easier experimentation with various combinations and parameters. Our work extends the work in the literature developed for that end: First, by adding more of these features and also by allowing the possibility of either starting from initialized kernels or training them from random values. The code is written as a template of classes and scripts that users may integrate into their own PyTorch classes or simply use as is and add more layers for various applications.

Keywords: neural networks Mel-Spectrogram, chromagram, cochleogram, discrete Fourrier transform, PyTorch conv1d()

Procedia PDF Downloads 201

Authors: Sergey Ermolin, Olga Ermolin

Abstract:

A Deep Convolution Neural Network with Triplet Loss is used to identify duplicate images in real-estate advertisements in the presence of image artifacts such as watermarking, cropping, hue/brightness adjustment, and others. The effects of batch normalization, spatial dropout, and various convergence methodologies on the resulting detection accuracy are discussed. For comparative Return-on-Investment study (per industry request), end-2-end performance is benchmarked on both Nvidia Titan GPUs and Intel’s Xeon CPUs. A new real-estate dataset from San Francisco Bay Area is used for this work. Sufficient duplicate detection accuracy is achieved to supplement other database-grounded methods of duplicate removal. The implemented method is used in a Proof-of-Concept project in the real-estate industry.

Keywords: visual recognition, convolutional neural networks, triplet loss, spatial batch normalization with dropout, duplicate removal, advertisement technologies, performance benchmarking

Procedia PDF Downloads 307

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 317

Authors: Yasser F. Hassan

Abstract:

The reduction or removal of noise in a color image is an essential part of image processing, whether the final information is used for human perception or for an automatic inspection and analysis. This paper describes the modeling system based on the rough neural network model to adaptive cellular automata for various image processing tasks and noise remover. In this paper, we consider the problem of object processing in colored image using rough neural networks to help deriving the rules which will be used in cellular automata for noise image. The proposed method is compared with some classical and recent methods. The results demonstrate that the new model is capable of being trained to perform many different tasks, and that the quality of these results is comparable or better than established specialized algorithms.

Keywords: rough sets, rough neural networks, cellular automata, image processing

Procedia PDF Downloads 403

Authors: B. R. Campomanes-Alvarez, P. Quiros, B. Fernandez

Abstract:

Automatic Speech Recognition (ASR) is a machine-based process of decoding and transcribing oral speech. A typical ASR system receives acoustic input from a speaker or an audio file, analyzes it using algorithms, and produces an output in the form of a text. Some speech recognition systems use Hidden Markov Models (HMMs) to deal with the temporal variability of speech and Gaussian Mixture Models (GMMs) to determine how well each state of each HMM fits a short window of frames of coefficients that represents the acoustic input. Another way to evaluate the fit is to use a feed-forward neural network that takes several frames of coefficients as input and produces posterior probabilities over HMM states as output. Deep neural networks (DNNs) that have many hidden layers and are trained using new methods have been shown to outperform GMMs on a variety of speech recognition systems. Acoustic models for state-of-the-art ASR systems are usually training on massive amounts of data. However, audio files with their corresponding transcriptions can be difficult to obtain, especially in the Spanish language. Hence, in the case of these low-resource scenarios, building an ASR model is considered as a complex task due to the lack of labeled data, resulting in an under-trained system. Semi-supervised learning approaches arise as necessary tasks given the high cost of transcribing audio data. The main goal of this proposal is to develop a procedure based on acoustic semi-supervised learning for Spanish ASR systems by using DNNs. This semi-supervised learning approach consists of: (a) Training a seed ASR model with a DNN using a set of audios and their respective transcriptions. A DNN with a one-hidden-layer network was initialized; increasing the number of hidden layers in training, to a five. A refinement, which consisted of the weight matrix plus bias term and a Stochastic Gradient Descent (SGD) training were also performed. The objective function was the cross-entropy criterion. (b) Decoding/testing a set of unlabeled data with the obtained seed model. (c) Selecting a suitable subset of the validated data to retrain the seed model, thereby improving its performance on the target test set. To choose the most precise transcriptions, three confidence scores or metrics, regarding the lattice concept (based on the graph cost, the acoustic cost and a combination of both), was performed as selection technique. The performance of the ASR system will be calculated by means of the Word Error Rate (WER). The test dataset was renewed in order to extract the new transcriptions added to the training dataset. Some experiments were carried out in order to select the best ASR results. A comparison between a GMM-based model without retraining and the DNN proposed system was also made under the same conditions. Results showed that the semi-supervised ASR-model based on DNNs outperformed the GMM-model, in terms of WER, in all tested cases. The best result obtained an improvement of 6% relative WER. Hence, these promising results suggest that the proposed technique could be suitable for building ASR models in low-resource environments.

Keywords: automatic speech recognition, deep neural networks, machine learning, semi-supervised learning

Procedia PDF Downloads 320

Authors: Budhvin T. Withana, Sulochana Rupasinghe

Abstract:

The educational system faces a significant concern with regards to Dyslexia and Dysgraphia, which are learning disabilities impacting reading and writing abilities. This is particularly challenging for children who speak the Sinhala language due to its complexity and uniqueness. Commonly used methods to detect the risk of Dyslexia and Dysgraphia rely on subjective assessments, leading to limited coverage and time-consuming processes. Consequently, delays in diagnoses and missed opportunities for early intervention can occur. To address this issue, the project developed a hybrid model that incorporates various deep learning techniques to detect the risk of Dyslexia and Dysgraphia. Specifically, Resnet50, VGG16, and YOLOv8 models were integrated to identify handwriting issues. The outputs of these models were then combined with other input data and fed into an MLP model. Hyperparameters of the MLP model were fine-tuned using Grid Search CV, enabling the identification of optimal values for the model. This approach proved to be highly effective in accurately predicting the risk of Dyslexia and Dysgraphia, providing a valuable tool for early detection and intervention. The Resnet50 model exhibited a training accuracy of 0.9804 and a validation accuracy of 0.9653. The VGG16 model achieved a training accuracy of 0.9991 and a validation accuracy of 0.9891. The MLP model demonstrated impressive results with a training accuracy of 0.99918, a testing accuracy of 0.99223, and a loss of 0.01371. These outcomes showcase the high accuracy achieved by the proposed hybrid model in predicting the risk of Dyslexia and Dysgraphia.

Keywords: neural networks, risk detection system, dyslexia, dysgraphia, deep learning, learning disabilities, data science

Procedia PDF Downloads 36

Authors: Daniel Fulus Fom, Gau Patrick Damulak

Abstract:

In this study, the Autoregressive Fractional Integrated Moving Average (ARFIMA) and Jordan Recurrent Neural Network (JRNN) models were employed to model the forecasting performance of the daily turbidity flow of White Clay Creek (WCC). The two methods were applied to the log difference series of the daily turbidity flow series of WCC. The measurements of error employed to investigate the forecasting performance of the ARFIMA and JRNN models are the Root Mean Square Error (RMSE) and the Mean Absolute Error (MAE). The outcome of the investigation revealed that the forecasting performance of the JRNN technique is better than the forecasting performance of the ARFIMA technique in the mean square error sense. The results of the ARFIMA and JRNN models were obtained by the simulation of the models using MATLAB version 8.03. The significance of using the log difference series rather than the difference series is that the log difference series stabilizes the turbidity flow series than the difference series on the ARFIMA and JRNN.

Keywords: auto regressive, mean absolute error, neural network, root square mean error

Procedia PDF Downloads 245

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 219

Authors: Vadim Kulikov

Abstract:

The classical Stroop effect is the phenomenon that it takes more time to name the ink color of a printed word if the word denotes a conflicting color than if it denotes the same color. Over the last 80 years, there have been many variations of the experiment revealing various mechanisms behind semantic, attentional, behavioral and perceptual processing. The Stroop task is known to exhibit asymmetry. Reading the words out loud is hardly dependent on the ink color, but naming the ink color is significantly influenced by the incongruent words. This asymmetry is reversed, if instead of naming the color, one has to point at a corresponding color patch. Another debated aspects are the notions of automaticity and how much of the effect is due to semantic and how much due to response stage interference. Is automaticity a continuous or an all-or-none phenomenon? There are many models and theories in the literature tackling these questions which will be discussed in the presentation. None of them, however, seems to capture all the findings at once. A computational model is proposed which is based on the philosophical idea developed by the author that the mind operates as a collection of different information processing modalities such as different sensory and descriptive modalities, which produce emergent phenomena through mutual interaction and coherence. This is the framework theory where ‘framework’ attempts to generalize the concepts of modality, perspective and ‘point of view’. The architecture of this computational model consists of blocks of neurons, each block corresponding to one framework. In the simplest case there are four: visual color processing, text reading, speech production and attention selection modalities. In experiments where button pressing or pointing is required, a corresponding block is added. In the beginning, the weights of the neural connections are mostly set to zero. The network is trained using Hebbian learning to establish connections (corresponding to ‘coherence’ in framework theory) between these different modalities. The amount of data fed into the network is supposed to mimic the amount of practice a human encounters, in particular it is assumed that converting written text into spoken words is a more practiced skill than converting visually perceived colors to spoken color-names. After the training, the network performs the Stroop task. The RT’s are measured in a canonical way, as these are continuous time recurrent neural networks (CTRNN). The above-described aspects of the Stroop phenomenon along with many others are replicated. The model is similar to some existing connectionist models but as will be discussed in the presentation, has many advantages: it predicts more data, the architecture is simpler and biologically more plausible.

Keywords: connectionism, Hebbian learning, artificial neural networks, philosophy of mind, Stroop

Procedia PDF Downloads 244

Authors: Budhvin T. Withana, Sulochana Rupasinghe

Abstract:

The problem of Dyslexia and Dysgraphia, two learning disabilities that affect reading and writing abilities, respectively, is a major concern for the educational system. Due to the complexity and uniqueness of the Sinhala language, these conditions are especially difficult for children who speak it. The traditional risk detection methods for Dyslexia and Dysgraphia frequently rely on subjective assessments, making it difficult to cover a wide range of risk detection and time-consuming. As a result, diagnoses may be delayed and opportunities for early intervention may be lost. The project was approached by developing a hybrid model that utilized various deep learning techniques for detecting risk of Dyslexia and Dysgraphia. Specifically, Resnet50, VGG16 and YOLOv8 were integrated to detect the handwriting issues, and their outputs were fed into an MLP model along with several other input data. The hyperparameters of the MLP model were fine-tuned using Grid Search CV, which allowed for the optimal values to be identified for the model. This approach proved to be effective in accurately predicting the risk of Dyslexia and Dysgraphia, providing a valuable tool for early detection and intervention of these conditions. The Resnet50 model achieved an accuracy of 0.9804 on the training data and 0.9653 on the validation data. The VGG16 model achieved an accuracy of 0.9991 on the training data and 0.9891 on the validation data. The MLP model achieved an impressive training accuracy of 0.99918 and a testing accuracy of 0.99223, with a loss of 0.01371. These results demonstrate that the proposed hybrid model achieved a high level of accuracy in predicting the risk of Dyslexia and Dysgraphia.

Keywords: neural networks, risk detection system, Dyslexia, Dysgraphia, deep learning, learning disabilities, data science

Procedia PDF Downloads 58

Authors: A. M. Khourshid, A. M. El-Kassas, I. Sabry

Abstract:

The objective of this work was to investigate the mechanical properties in order to demonstrate the feasibility of friction stir welding for joining Al 6061 aluminium alloys. Welding was performed on pipe with different thickness (2, 3 and 4 mm), five rotational speeds (485, 710, 910, 1120 and 1400 rpm) and a traverse speed of 4mm/min. This work focuses on two methods which are artificial neural networks using software and Response Surface Methodology (RSM) to predict the tensile strength, the percentage of elongation and hardness of friction stir welded 6061 aluminium alloy. An Artificial Neural Network (ANN) model was developed for the analysis of the friction stir welding parameters of 6061 pipe. Tensile strength, the percentage of elongation and hardness of weld joints were predicted by taking the parameters tool rotation speed, material thickness and axial force as a function. A comparison was made between measured and predicted data. Response Surface Methodology (RSM) was also developed and the values obtained for the response tensile strength, the percentage of elongation and hardness are compared with measured values. The effect of FSW process parameters on mechanical properties of 6061 aluminium alloy has been analysed in detail.

Keywords: friction stir welding, aluminium alloy, response surface methodology, artificial neural network

Procedia PDF Downloads 262

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 243

Authors: Bin Ji, Kai Xu, Shunyu Yao, Jingjing Liu, Ye Pan

Abstract:

Human pose estimation is a popular research area in computer vision for its important application in human-machine interface. In recent years, 2D human pose estimation based on convolution neural network has got great progress and development. However, in more and more practical applications, people often need to deal with tasks based on video. It’s not far-fetched for us to consider how to combine the spatial and temporal information together to achieve a balance between computing cost and accuracy. To address this issue, this study proposes a new spatiotemporal model, namely Spatiotemporal Net (STNet) to combine both temporal and spatial information more rationally. As a result, the predicted keypoints heatmap is potentially more accurate and spatially more precise. Under the condition of ensuring the recognition accuracy, the algorithm deal with spatiotemporal series in a decoupled way, which greatly reduces the computation of the model, thus reducing the resource consumption. This study demonstrate the effectiveness of our network over the Penn Action Dataset, and the results indicate superior performance of our network over the existing methods.

Keywords: convolutional long short-term memory, deep learning, human pose estimation, spatiotemporal series

Procedia PDF Downloads 122

Authors: Tsega Asresa, Getahun Tigistu, Melaku Bayih

Abstract:

Computer vision is a subfield of artificial intelligence that allows computers and systems to extract meaning from digital images and video. It is used in a wide range of fields of study, including self-driving cars, video surveillance, medical diagnosis, manufacturing, law, agriculture, quality control, health care, facial recognition, and military applications. Aromatic medicinal plants are botanical raw materials used in cosmetics, medicines, health foods, essential oils, decoration, cleaning, and other natural health products for therapeutic and Aromatic culinary purposes. These plants and their products not only serve as a valuable source of income for farmers and entrepreneurs but also going to export for valuable foreign currency exchange. In Ethiopia, there is a lack of technologies for the classification and identification of Aromatic medicinal plant parts and disease type cured by aromatic medicinal plants. Farmers, industry personnel, academicians, and pharmacists find it difficult to identify plant parts and disease types cured by plants before ingredient extraction in the laboratory. Manual plant identification is a time-consuming, labor-intensive, and lengthy process. To alleviate these challenges, few studies have been conducted in the area to address these issues. One way to overcome these problems is to develop a deep learning model for efficient identification of Aromatic medicinal plant parts with their corresponding disease type. The objective of the proposed study is to identify the aromatic medicinal plant parts and their disease type classification using computer vision technology. Therefore, this research initiated a model for the classification of aromatic medicinal plant parts and their disease type by exploring computer vision technology. Morphological characteristics are still the most important tools for the identification of plants. Leaves are the most widely used parts of plants besides roots, flowers, fruits, and latex. For this study, the researcher used RGB leaf images with a size of 128x128 x3. In this study, the researchers trained five cutting-edge models: convolutional neural network, Inception V3, Residual Neural Network, Mobile Network, and Visual Geometry Group. Those models were chosen after a comprehensive review of the best-performing models. The 80/20 percentage split is used to evaluate the model, and classification metrics are used to compare models. The pre-trained Inception V3 model outperforms well, with training and validation accuracy of 99.8% and 98.7%, respectively.

Keywords: aromatic medicinal plant, computer vision, convolutional neural network, deep learning, plant classification, residual neural network

Procedia PDF Downloads 144

Authors: Pooja Rani, G. S. Mahapatra, S. K. Pandey

Abstract:

In this paper, we propose a novel approach of Neural Network and Particle Swarm Optimization methods for software reliability prediction. We first explain how to apply compound function in neural network so that we can derive a Flexible Logistic (S-shaped) Growth Curve (FLGC) model. This model mathematically represents software failure as a random process and can be used to evaluate software development status during testing. To avoid trapping in local minima, we have applied Particle Swarm Optimization method to train proposed model using failure test data sets. We drive our proposed model using computational based intelligence modeling. Thus, proposed model becomes Neuro-Particle Swarm Optimization (NPSO) model. We do test result with different inertia weight to update particle and update velocity. We obtain result based on best inertia weight compare along with Personal based oriented PSO (pPSO) help to choose local best in network neighborhood. The applicability of proposed model is demonstrated through real time test data failure set. The results obtained from experiments show that the proposed model has a fairly accurate prediction capability in software reliability.

Keywords: software reliability, flexible logistic growth curve model, software cumulative failure prediction, neural network, particle swarm optimization

Procedia PDF Downloads 325

Authors: Christina Adly, Meena Abdelmeseeh, Tamer Basha

Abstract:

This paper proposes a system for hand movement recognition using multichannel surface EMG(sEMG) signals obtained from 40 subjects using 40 different exercises, which are available on the Ninapro(Non-Invasive Adaptive Prosthetics) database. First, we applied processing methods to the raw sEMG signals to convert them to their amplitudes. Second, we used deep learning methods to solve our problem by passing the preprocessed signals to Fully connected neural networks(FCNN) and recurrent neural networks(RNN) with Long Short Term Memory(LSTM). Using intrasubject evaluation, The accuracy using the FCNN is 72%, with a processing time for training around 76 minutes, and for RNN's accuracy is 79.9%, with 8 minutes and 22 seconds processing time. Third, we applied some postprocessing methods to improve the accuracy, like majority voting(MV) and Movement Error Rate(MER). The accuracy after applying MV is 75% and 86% for FCNN and RNN, respectively. The MER value has an inverse relationship with the prediction delay while varying the window length for measuring the MV. The different part uses the RNN with the intersubject evaluation. The experimental results showed that to get a good accuracy for testing with reasonable processing time, we should use around 20 subjects.

Keywords: hand movement recognition, recurrent neural network, movement error rate, intrasubject evaluation, intersubject evaluation

Procedia PDF Downloads 111

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 353

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 126

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 227

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 387

Authors: Mylena McCoggle, Shyra Wilson, Andrea Rivera, Rocio Alba-Flores

Abstract:

This work introduces the use of EMGs (electromyography) from muscle sensors to develop an Artificial Neural Network (ANN) for pattern recognition to control a small unmanned aerial vehicle. The objective of this endeavor exhibits interfacing drone applications beyond manual control directly. MyoWare Muscle sensor contains three EMG electrodes (dual and single type) used to collect signals from the posterior (extensor) and anterior (flexor) forearm and the bicep. Collection of raw voltages from each sensor were connected to an Arduino Uno and a data processing algorithm was developed with the purpose of interpreting the voltage signals given when performing flexing, resting, and motion of the arm. Each sensor collected eight values over a two-second period for the duration of one minute, per assessment. During each two-second interval, the movements were alternating between a resting reference class and an active motion class, resulting in controlling the motion of the drone with left and right movements. This paper further investigated adding up to three sensors to differentiate between hand gestures to control the principal motions of the drone (left, right, up, and land). The hand gestures chosen to execute these movements were: a resting position, a thumbs up, a hand swipe right motion, and a flexing position. The MATLAB software was utilized to collect, process, and analyze the signals from the sensors. The protocol (machine learning tool) was used to classify the hand gestures. To generate the input vector to the ANN, the mean, root means squared, and standard deviation was processed for every two-second interval of the hand gestures. The neuromuscular information was then trained using an artificial neural network with one hidden layer of 10 neurons to categorize the four targets, one for each hand gesture. Once the machine learning training was completed, the resulting network interpreted the processed inputs and returned the probabilities of each class. Based on the resultant probability of the application process, once an output was greater or equal to 80% of matching a specific target class, the drone would perform the motion expected. Afterward, each movement was sent from the computer to the drone through a Wi-Fi network connection. These procedures have been successfully tested and integrated into trial flights, where the drone has responded successfully in real-time to predefined command inputs with the machine learning algorithm through the MyoWare sensor interface. The full paper will describe in detail the database of the hand gestures, the details of the ANN architecture, and confusion matrices results.

Keywords: artificial neural network, biosensors, electromyography, machine learning, MyoWare muscle sensors, Arduino

Procedia PDF Downloads 148

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 190

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 300

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 189

Authors: Mo-Se Lee, Cheol-Hwi Ahn, Kee-Young Kwahk, Hyunchul Ahn

Abstract:

Over the past decade, deep learning has been in spotlight among various machine learning algorithms. In particular, CNN (Convolutional Neural Network), which is known as effective solution for recognizing and classifying images, has been popularly applied to classification and prediction problems in various fields. In this study, we try to apply CNN to stock market prediction, one of the most challenging tasks in the machine learning research. In specific, we propose to apply CNN as the binary classifier that predicts stock market direction (up or down) by using a graph as its input. That is, our proposal is to build a machine learning algorithm that mimics a person who looks at the graph and predicts whether the trend will go up or down. Our proposed model consists of four steps. In the first step, it divides the dataset into 5 days, 10 days, 15 days, and 20 days. And then, it creates graphs for each interval in step 2. In the next step, CNN classifiers are trained using the graphs generated in the previous step. In step 4, it optimizes the hyper parameters of the trained model by using the validation dataset. To validate our model, we will apply it to the prediction of KOSPI200 for 1,986 days in eight years (from 2009 to 2016). The experimental dataset will include 14 technical indicators such as CCI, Momentum, ROC and daily closing price of KOSPI200 of Korean stock market.

Keywords: convolutional neural network, deep learning, Korean stock market, stock market prediction

Procedia PDF Downloads 407

Authors: Mehrdad Shahrbanozadeh, Gholam Abbas Barani, Saeed Shojaee

Abstract:

In this study, a finite element (Seep3D model) and an artificial neural network (ANN) model were developed to simulate flow through dam foundation. Seep3D model is capable of simulating three-dimensional flow through a heterogeneous and anisotropic, saturated and unsaturated porous media. Flow through the Shahid Abbaspour dam foundation has been used as a case study. The FEM with 24960 triangular elements and 28707 nodes applied to model flow through foundation of this dam. The FEM being made denser in the neighborhood of the curtain screen. The ANN model developed for Shahid Abbaspour dam is a feedforward four layer network employing the sigmoid function as an activator and the back-propagation algorithm for the network learning. The water level elevations of the upstream and downstream of the dam have been used as input variables and the piezometric heads as the target outputs in the ANN model. The two models are calibrated and verified using the Shahid Abbaspour’s dam piezometric data. Results of the models were compared with those measured by the piezometers which are in good agreement. The model results also revealed that the ANN model performed as good as and in some cases better than the FEM.

Keywords: seepage, dam foundation, finite element method, neural network, seep 3D model

Procedia PDF Downloads 449

Authors: Raghavi C. Janaswamy

Abstract:

In the healthcare sector, heterogenous data elements such as patients, diagnosis, symptoms, conditions, observation text from physician notes, and prescriptions form the essentials of the Electronic Health Record (EHR). The data in the form of clear text and images are stored or processed in a relational format in most systems. However, the intrinsic structure restrictions and complex joins of relational databases limit the widespread utility. In this regard, the design and development of realistic mapping and deep connections as real-time objects offer unparallel advantages. Herein, a graph neural network-based classification of EHR data has been developed. The patient conditions have been predicted as a node classification task using a graph-based open source EHR data, Synthea Database, stored in Tigergraph. The Synthea DB dataset is leveraged due to its closer representation of the real-time data and being voluminous. The graph model is built from the EHR heterogeneous data using python modules, namely, pyTigerGraph to get nodes and edges from the Tigergraph database, PyTorch to tensorize the nodes and edges, PyTorch-Geometric (PyG) to train the Graph Neural Network (GNN) and adopt the self-supervised learning techniques with the AutoEncoders to generate the node embeddings and eventually perform the node classifications using the node embeddings. The model predicts patient conditions ranging from common to rare situations. The outcome is deemed to open up opportunities for data querying toward better predictions and accuracy.

Keywords: electronic health record, graph neural network, heterogeneous data, prediction

Procedia PDF Downloads 64

Authors: Abdelkarim M. Ertiame, D. W. Yu, D. L. Yu, J. B. Gomm

Abstract:

In this paper, a new robust fault detection and isolation (FDI) scheme is developed to monitor a multivariable nonlinear chemical process called the Chylla-Haase polymerization reactor when it is under the cascade PI control. The scheme employs a radial basis function neural network (RBFNN) in an independent mode to model the process dynamics and using the weighted sum-squared prediction error as the residual. The recursive orthogonal Least Squares algorithm (ROLS) is employed to train the model to overcome the training difficulty of the independent mode of the network. Then, another RBFNN is used as a fault classifier to isolate faults from different features involved in the residual vector. The several actuator and sensor faults are simulated in a nonlinear simulation of the reactor in Simulink. The scheme is used to detect and isolate the faults on-line. The simulation results show the effectiveness of the scheme even the process is subjected to disturbances and uncertainties including significant changes in the monomer feed rate, fouling factor, impurity factor, ambient temperature and measurement noise. The simulation results are presented to illustrate the effectiveness and robustness of the proposed method.

Keywords: Robust fault detection, cascade control, independent RBF model, RBF neural networks, Chylla-Haase reactor, FDI under closed-loop control

Procedia PDF Downloads 475

Authors: Chi Wu, Dean Wu, Wen-Te Liu, Cheng-Yu Tsai, Shin-Mei Hsu, Yin-Tzu Lin, Ru-Yin Yang

Abstract:

Background: The results of previous studies compared the benefits and risks of receiving insomnia medication. However, the effects between hypnotic drugs used and enhancement of sleep quality were still unclear. Objective: The aim of this study is to establish a prediction model for hypnotic drugs' dosage used for insomnia subjects and associated the relationship between sleep stage ratio change and drug types. Methodologies: According to American Academy of Sleep Medicine (AASM) guideline, sleep stages were classified and transformed to hypnogram via the polysomnography (PSG) in a hospital in New Taipei City (Taiwan). The subjects with diagnosis for insomnia without receiving hypnotic drugs treatment were be set as the comparison group. Conversely, hypnotic drugs dosage within the past three months was obtained from the clinical registration for each subject. Furthermore, the collecting subjects were divided into two groups for training and testing. After training convolution neuron network (CNN) to predict types of hypnotics used and dosages are taken, the test group was used to evaluate the accuracy of classification. Results: We recruited 76 subjects in this study, who had been done PSG for transforming hypnogram from their sleep stages. The accuracy of dosages obtained from confusion matrix on the test group by CNN is 81.94%, and accuracy of hypnotic drug types used is 74.22%. Moreover, the subjects with high ratio of wake stage were correctly classified as requiring medical treatment. Conclusion: CNN with hypnogram was potentially used for adjusting the dosage of hypnotic drugs and providing subjects to pre-screening the types of hypnotic drugs taken.

Keywords: convolution neuron network, hypnotic drugs, insomnia, polysomnography

Procedia PDF Downloads 165

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 360