Search results for: LIRA neural classifier

Authors: Vaidehi Murarka, Sneha Mehta, Dishant Upadhyay

Abstract:

Our project topic is “Alphabet Recognition using pixel probability distribution”. The project uses techniques of Image Processing and Machine Learning in Computer Vision. Alphabet recognition is the mechanical or electronic translation of scanned images of handwritten, typewritten or printed text into machine-encoded text. It is widely used to convert books and documents into electronic files etc. Alphabet Recognition based OCR application is sometimes used in signature recognition which is used in bank and other high security buildings. One of the popular mobile applications includes reading a visiting card and directly storing it to the contacts. OCR's are known to be used in radar systems for reading speeders license plates and lots of other things. The implementation of our project has been done using Visual Studio and Open CV (Open Source Computer Vision). Our algorithm is based on Neural Networks (machine learning). The project was implemented in three modules: (1) Training: This module aims “Database Generation”. Database was generated using two methods: (a) Run-time generation included database generation at compilation time using inbuilt fonts of OpenCV library. Human intervention is not necessary for generating this database. (b) Contour–detection: ‘jpeg’ template containing different fonts of an alphabet is converted to the weighted matrix using specialized functions (contour detection and blob detection) of OpenCV. The main advantage of this type of database generation is that the algorithm becomes self-learning and the final database requires little memory to be stored (119kb precisely). (2) Preprocessing: Input image is pre-processed using image processing concepts such as adaptive thresholding, binarizing, dilating etc. and is made ready for segmentation. “Segmentation” includes extraction of lines, words, and letters from the processed text image. (3) Testing and prediction: The extracted letters are classified and predicted using the neural networks algorithm. The algorithm recognizes an alphabet based on certain mathematical parameters calculated using the database and weight matrix of the segmented image.

Keywords: contour-detection, neural networks, pre-processing, recognition coefficient, runtime-template generation, segmentation, weight matrix

Procedia PDF Downloads 390

Authors: Chien-kuo Chang, Bo-wei Wu, Yi-yun Tang, Min-chiu Wu

Abstract:

This paper proposes a power equipment diagnosis system based on partial discharge (PD), which is characterized by increasing the readability of experimental data and the convenience of operation. This system integrates a variety of analysis programs of different data formats and different programming languages and then establishes a set of interfaces that can follow and expand the structure, which is also helpful for subsequent maintenance and innovation. This study shows a case of using the developed Convolutional Neural Networks (CNN) to integrate with this system, using the designed model architecture to simplify the complex training process. It is expected that the simplified training process can be used to establish an adaptive deep learning experimental structure. By selecting different test data for repeated training, the accuracy of the identification system can be enhanced. On this platform, the measurement status and partial discharge pattern of each equipment can be checked in real time, and the function of real-time identification can be set, and various training models can be used to carry out real-time partial discharge insulation defect identification and insulation state diagnosis. When the electric power equipment entering the dangerous period, replace equipment early to avoid unexpected electrical accidents.

Keywords: partial discharge, convolutional neural network, partial discharge analysis platform, adaptive deep learning

Procedia PDF Downloads 79

Authors: Bin Mu, Site Li, Shijin Yuan

Abstract:

Under the circumstance of environment deterioration, people are increasingly concerned about the quality of the environment, especially air quality. As a result, it is of great value to give accurate and timely forecast of AQI (air quality index). In order to simplify influencing factors of air quality in a city, and forecast the city’s AQI tomorrow, this study used MATLAB software and adopted the method of constructing a mathematic model of PCA-GABP to provide a solution. To be specific, this study firstly made principal component analysis (PCA) of influencing factors of AQI tomorrow including aspects of weather, industry waste gas and IAQI data today. Then, we used the back propagation neural network model (BP), which is optimized by genetic algorithm (GA), to give forecast of AQI tomorrow. In order to verify validity and accuracy of PCA-GABP model’s forecast capability. The study uses two statistical indices to evaluate AQI forecast results (normalized mean square error and fractional bias). Eventually, this study reduces mean square error by optimizing individual gene structure in genetic algorithm and adjusting the parameters of back propagation model. To conclude, the performance of the model to forecast AQI is comparatively convincing and the model is expected to take positive effect in AQI forecast in the future.

Keywords: AQI forecast, principal component analysis, genetic algorithm, back propagation neural network model

Procedia PDF Downloads 231

Authors: Piyush Samant, Ravinder Agarwal

Abstract:

Complementary and Alternative Medicine (CAM) techniques are quite popular and effective for chronic diseases. Iridology is more than 150 years old CAM technique which analyzes the patterns, tissue weakness, color, shape, structure, etc. for disease diagnosis. The objective of this paper is to validate the use of iridology for the diagnosis of the diabetes. The suggested model was applied in a systemic disease with ocular effects. 200 subject data of 100 each diabetic and non-diabetic were evaluated. Complete procedure was kept very simple and free from the involvement of any iridologist. From the normalized iris, the region of interest was cropped. All 63 features were extracted using statistical, texture analysis, and two-dimensional discrete wavelet transformation. A comparison of accuracies of six different classifiers has been presented. The result shows 89.66% accuracy by the random forest classifier.

Keywords: complementary and alternative medicine, classification, iridology, iris, feature extraction, disease prediction

Procedia PDF Downloads 408

Authors: Shiuh-Jer Huang, Chen-Zon Yan, C. K. Huang, Chun-Chien Ting

Abstract:

Since the vision system application in industrial environment for autonomous purposes is required intensely, the image recognition technique becomes an important research topic. Here, deep learning algorithm is employed in image system to recognize the industrial object and integrate with a 7A6 Series Manipulator for object automatic gripping task. PC and Graphic Processing Unit (GPU) are chosen to construct the 3D Vision Recognition System. Depth Camera (Intel RealSense SR300) is employed to extract the image for object recognition and coordinate derivation. The YOLOv2 scheme is adopted in Convolution neural network (CNN) structure for object classification and center point prediction. Additionally, image processing strategy is used to find the object contour for calculating the object orientation angle. Then, the specified object location and orientation information are sent to robotic controller. Finally, a six-axis manipulator can grasp the specific object in a random environment based on the user command and the extracted image information. The experimental results show that YOLOv2 has been successfully employed to detect the object location and category with confidence near 0.9 and 3D position error less than 0.4 mm. It is useful for future intelligent robotic application in industrial 4.0 environment.

Keywords: deep learning, image processing, convolution neural network, YOLOv2, 7A6 series manipulator

Procedia PDF Downloads 250

Authors: Olumuyiwa Ojo, Masengo Ilunga

Abstract:

Artificial neural network (ANN) has broken the bounds of the convention programming, which is actually a function of garbage in garbage out by its ability to mimic the human brain. Its ability to adopt, adapt, adjust, evaluate, learn and recognize the relationship, behavior, and pattern of a series of data set administered to it, is tailored after the human reasoning and learning mechanism. Thus, the study aimed at modeling wastewater treatment process in order to accurately diagnose water control problems for effective treatment. For this study, a stage ANN model development and evaluation methodology were employed. The source data analysis stage involved a statistical analysis of the data used in modeling in the model development stage, candidate ANN architecture development and then evaluated using a historical data set. The model was developed using historical data obtained from Daspoort Wastewater Treatment plant South Africa. The resultant designed dimensions and model for wastewater treatment plant provided good results. Parameters considered were temperature, pH value, colour, turbidity, amount of solids and acidity. Others are total hardness, Ca hardness, Mg hardness, and chloride. This enables the ANN to handle and represent more complex problems that conventional programming is incapable of performing.

Keywords: ANN, artificial neural network, wastewater treatment, model, development

Procedia PDF Downloads 150

Authors: Loai Abdallah, Malik Yousef

Abstract:

A domain space for the data should reflect the actual similarity between objects. Since objects belonging to the same cluster usually share some common traits even though their geometric distance might be relatively large. In general, the Euclidean distance of data points that represented by large number of features is not capturing the actual relation between those points. In this study, we propose a new method to construct a different space that is based on clustering to form a new distance metric. The new distance space is based on ensemble clustering (EC). The EC distance space is defined by tracking the membership of the points over multiple runs of clustering algorithm metric. Over this distance, we train the decision trees classifier (DT-EC). The results obtained by applying DT-EC on 10 datasets confirm our hypotheses that embedding the EC space as a distance metric would improve the performance.

Keywords: ensemble clustering, decision trees, classification, K nearest neighbors

Procedia PDF Downloads 191

Authors: Abdul Mannan Akhtar

Abstract:

In this paper a novel concept of a self learning smart personalized computer assistant (ACPCA) is established which is a context aware system. Based on user habits, moods, and other routines/situational reactions the system will manage various services and suggestions at appropriate times including what schedule to follow, what to watch, what software to be used, what should be deleted etc. This system will utilize a hybrid fuzzyNeural model to predict what the user will do next and support his actions. This will be done by establishing fuzzy sets of user activities, choices, preferences etc. and utilizing their combinations to predict his moods and immediate preferences. Various application of context aware systems exist separately e.g. on certain websites for music or multimedia suggestions but a personalized autonomous system that could adapt to user’s personality does not exist at present. Due to the novelty and massiveness of this concept, this paper will primarily focus on the problem establishment, product features and its functionality; however a small mini case is also implemented on MATLAB to demonstrate some of the aspects of ACPCA. The mini case involves prediction of user moods, activity, routine and food preference using a hybrid fuzzy-Neural soft computing technique.

Keywords: context aware systems, APCPCA, soft computing techniques, artificial intelligence, fuzzy logic, neural network, mood detection, face detection, activity detection

Procedia PDF Downloads 464

Authors: Stephen L. Green, Alexander N. Gorban, Ivan Y. Tyukin

Abstract:

Within the past decade, using Convolutional Neural Networks (CNN)’s to create Deep Learning systems capable of translating Sign Language into text has been a breakthrough in breaking the communication barrier for deaf-mute people. Conventional research on this subject has been concerned with training the network to recognize the fingerspelling gestures of a given language and produce their corresponding alphanumerics. One of the problems with the current developing technology is that images are scarce, with little variations in the gestures being presented to the recognition program, often skewed towards single skin tones and hand sizes that makes a percentage of the population’s fingerspelling harder to detect. Along with this, current gesture detection programs are only trained on one finger spelling language despite there being one hundred and forty-two known variants so far. All of this presents a limitation for traditional exploitation for the state of current technologies such as CNN’s, due to their large number of required parameters. This work aims to present a technology that aims to resolve this issue by combining a pretrained legacy AI system for a generic object recognition task with a corrector method to uptrain the legacy network. This is a computationally efficient procedure that does not require large volumes of data even when covering a broad range of sign languages such as American Sign Language, British Sign Language and Chinese Sign Language (Pinyin). Implementing recent results on method concentration, namely the stochastic separation theorem, an AI system is supposed as an operate mapping an input present in the set of images u ∈ U to an output that exists in a set of predicted class labels q ∈ Q of the alphanumeric that q represents and the language it comes from. These inputs and outputs, along with the interval variables z ∈ Z represent the system’s current state which implies a mapping that assigns an element x ∈ ℝⁿ to the triple (u, z, q). As all xi are i.i.d vectors drawn from a product mean distribution, over a period of time the AI generates a large set of measurements xi called S that are grouped into two categories: the correct predictions M and the incorrect predictions Y. Once the network has made its predictions, a corrector can then be applied through centering S and Y by subtracting their means. The data is then regularized by applying the Kaiser rule to the resulting eigenmatrix and then whitened before being split into pairwise, positively correlated clusters. Each of these clusters produces a unique hyperplane and if any element x falls outside the region bounded by these lines then it is reported as an error. As a result of this methodology, a self-correcting recognition process is created that can identify fingerspelling from a variety of sign language and successfully identify the corresponding alphanumeric and what language the gesture originates from which no other neural network has been able to replicate.

Keywords: convolutional neural networks, deep learning, shallow correctors, sign language

Procedia PDF Downloads 101

Authors: Moein Izadi, Ali Mohammadzadeh

Abstract:

Detection of damaged parts of roads after earthquake is essential for coordinating rescuers. In this study, an approach is presented for the semi-automatic detection of damaged roads in a city using pre-event vector maps and both pre- and post-earthquake QuickBird satellite images. Damage is defined in this study as the debris of damaged buildings adjacent to the roads. Some spectral and texture features are considered for SVM classification step to detect damages. Finally, the proposed method is tested on QuickBird pan-sharpened images from the Bam City earthquake and the results show that an overall accuracy of 81% and a kappa coefficient of 0.71 are achieved for the damage detection. The obtained results indicate the efficiency and accuracy of the proposed approach.

Keywords: SVM classifier, disaster management, road damage detection, quickBird images

Procedia PDF Downloads 623

Authors: Osung Im, Neha Yadav, Eui Hoon Lee, Joong Hoon Kim

Abstract:

Artificial Neural Network (ANN) approach is commonly used in lots of fields for forecasting. In water resources engineering, forecast of water level or inflow of reservoir is useful for various kind of purposes. Due to advantages of ANN, many papers were written for inflow prediction in river networks, but in this study, ANN is used in urban sewer networks. The growth of severe rain storm in Korea has increased flood damage severely, and the precipitation distribution is getting more erratic. Therefore, effective pump operation in pump station is an essential task for the reduction in urban area. If real time inflow of pump station reservoir can be predicted, it is possible to operate pump effectively for reducing the flood damage. This study used ANN model for pump station reservoir inflow prediction using upstream sewer depth data. For this study, rainfall events, sewer depth, and inflow into Banpo pump station reservoir between years of 2013-2014 were considered. Feed – Forward Back Propagation (FFBF), Cascade – Forward Back Propagation (CFBP), Elman Back Propagation (EBP) and Nonlinear Autoregressive Exogenous (NARX) were used as ANN model for prediction. A comparison of results with ANN model suggests that ANN is a powerful tool for inflow prediction using the sewer depth data.

Keywords: artificial neural network, forecasting, reservoir inflow, sewer depth

Procedia PDF Downloads 318

Authors: Jui-Chien Hsieh

Abstract:

Background:12-lead electrocardiography(ECG) is one of frequently-used tools to detect atrial fibrillation (AF), which might degenerate into life-threaten stroke, in clinical Practice. Based on this study, the AF detection by the clinically-used 12-lead ECG device has only 0.73~0.77 positive predictive value (ppv). Objective: It is on great demand to develop a new algorithm to improve the precision of AF detection using 12-lead ECG. Due to the progress on artificial intelligence (AI), we develop an ECG deep model that has the ability to recognize AF patterns and reduce false-positive errors. Methods: In this study, (1) 570-sample 12-lead ECG reports whose computer interpretation by the ECG device was AF were collected as the training dataset. The ECG reports were interpreted by 2 senior cardiologists, and confirmed that the precision of AF detection by the ECG device is 0.73.; (2) 88 12-lead ECG reports whose computer interpretation generated by the ECG device was AF were used as test dataset. Cardiologist confirmed that 68 cases of 88 reports were AF, and others were not AF. The precision of AF detection by ECG device is about 0.77; (3) A parallel 4-layer 1 dimensional convolutional neural network (CNN) was developed to identify AF based on limb-lead ECGs and chest-lead ECGs. Results: The results indicated that this model has better performance on AF detection than traditional computer interpretation of the ECG device in 88 test samples with 0.94 ppv, 0.98 sensitivity, 0.80 specificity. Conclusions: As compared to the clinical ECG device, this AI ECG model promotes the precision of AF detection from 0.77 to 0.94, and can generate impacts on clinical applications.

Keywords: 12-lead ECG, atrial fibrillation, deep learning, convolutional neural network

Procedia PDF Downloads 114

Authors: Shahrzad Zolfagharnassab, Abdul Rashid Mohamed Shariff, Siti Khairunniza Bejo

Abstract:

Conventional methods for nutrient soil mapping are based on laboratory tests of samples that are obtained from surveys. The time and cost involved in gathering and analyzing soil samples are the reasons that researchers use Predictive Soil Mapping (PSM). PSM can be defined as the development of a numerical or statistical model of the relationship among environmental variables and soil properties, which is then applied to a geographic database to create a predictive map. Kriging is a group of geostatistical techniques to spatially interpolate point values at an unobserved location from observations of values at nearby locations. The main problem with using kriging as an interpolator is that it is excessively data-dependent and requires a large number of closely spaced data points. Hence, there is a need to minimize the number of data points without sacrificing the accuracy of the results. In this paper, an Artificial Neural Networks (ANN) scheme was used to predict macronutrient values at un-sampled points. ANN has become a popular tool for prediction as it eliminates certain difficulties in soil property prediction, such as non-linear relationships and non-normality. Back-propagation multilayer feed-forward network structures were used to predict nitrogen, phosphorous and potassium values in the soil of the study area. A limited number of samples were used in the training, validation and testing phases of ANN (pattern reconstruction structures) to classify soil properties and the trained network was used for prediction. The soil analysis results of samples collected from the soil survey of block C of Sawah Sempadan, Tanjung Karang rice irrigation project at Selangor of Malaysia were used. Soil maps were produced by the Kriging method using 236 samples (or values) that were a combination of actual values (obtained from real samples) and virtual values (neural network predicted values). For each macronutrient element, three types of maps were generated with 118 actual and 118 virtual values, 59 actual and 177 virtual values, and 30 actual and 206 virtual values, respectively. To evaluate the performance of the proposed method, for each macronutrient element, a base map using 236 actual samples and test maps using 118, 59 and 30 actual samples respectively produced by the Kriging method. A set of parameters was defined to measure the similarity of the maps that were generated with the proposed method, termed the sample reduction method. The results show that the maps that were generated through the sample reduction method were more accurate than the corresponding base maps produced through a smaller number of real samples. For example, nitrogen maps that were produced from 118, 59 and 30 real samples have 78%, 62%, 41% similarity, respectively with the base map (236 samples) and the sample reduction method increased similarity to 87%, 77%, 71%, respectively. Hence, this method can reduce the number of real samples and substitute ANN predictive samples to achieve the specified level of accuracy.

Keywords: artificial neural network, kriging, macro nutrient, pattern recognition, precision farming, soil mapping

Procedia PDF Downloads 71

Authors: Magdy B. Eteiba, Wael Ismael Wahba, Shimaa Barakat

Abstract:

This paper presents a fault identification, classification and fault location estimation method based on Discrete Wavelet Transform and Adaptive Network Fuzzy Inference System (ANFIS) for medium voltage cable in the distribution system. Different faults and locations are simulated by ATP/EMTP, and then certain selected features of the wavelet transformed signals are used as an input for a training process on the ANFIS. Then an accurate fault classifier and locator algorithm was designed, trained and tested using current samples only. The results obtained from ANFIS output were compared with the real output. From the results, it was found that the percentage error between ANFIS output and real output is less than three percent. Hence, it can be concluded that the proposed technique is able to offer high accuracy in both of the fault classification and fault location.

Keywords: ANFIS, fault location, underground cable, wavelet transform

Procedia PDF Downloads 515

Authors: Shogo Nagano, Yusuke Tanigaki, Hirokazu Fukuda

Abstract:

Vegetables harvested early in the morning or late in the afternoon are valued in plant production, and so the time of harvest is important. The biological functions known as circadian clocks have a significant effect on this harvest timing. The purpose of this study was to non-destructively estimate the circadian clock and so construct a method for determining a suitable harvest time. We took eight samples of green busil (Perilla frutescens var. crispa) every 4 hours, six times for 1 day and analyzed all samples at the same time. A hyperspectral camera was used to collect spectrum intensities at 141 different wavelengths (350–1050 nm). Calculation of correlations between spectrum intensity of each wavelength and harvest time suggested the suitability of the hyperspectral camera for non-destructive estimation. However, even the highest correlated wavelength had a weak correlation, so we used machine learning to raise the accuracy of estimation and constructed a machine learning model to estimate the internal time of the circadian clock. Artificial neural networks (ANN) were used for machine learning because this is an effective analysis method for large amounts of data. Using the estimation model resulted in an error between estimated and real times of 3 min. The estimations were made in less than 2 hours. Thus, we successfully demonstrated this method of non-destructively estimating internal time.

Keywords: artificial neural network (ANN), circadian clock, green busil, hyperspectral camera, non-destructive evaluation

Procedia PDF Downloads 300

Authors: Shital Suresh Borse, Vijayalaxmi Kadroli

Abstract:

E-commerce industries nowadays implement the latest AI, ML Techniques to improve their own performance and prediction accuracy. This helps to gain a huge profit from the online market. Ant Colony Optimization, Genetic algorithm, Particle Swarm Optimization, Neural Network & GWO help many e-commerce industries for up-gradation of their predictive performance. These algorithms are providing optimum results in various applications, such as stock price prediction, prediction of drug-target interaction & user ratings of similar products in e-commerce sites, etc. In this study, customer reviews will play an important role in prediction analysis. People showing much interest in buying a lot of services& products suggested by other customers. This ultimately increases net profit. In this work, a convolution neural network (CNN) is proposed which further is useful to optimize the prediction accuracy of an e-commerce website. This method shows that CNN is used to optimize hyperparameters of GWO algorithm using an appropriate coding scheme. Accurate model results are verified by comparing them to PSO results whose hyperparameters have been optimized by CNN in Amazon's customer review dataset. Here, experimental outcome proves that this proposed system using the GWO algorithm achieves superior execution in terms of accuracy, precision, recovery, etc. in prediction analysis compared to the existing systems.

Keywords: prediction analysis, e-commerce, machine learning, grey wolf optimization, particle swarm optimization, CNN

Procedia PDF Downloads 113

Authors: Pranav Gunhal., Krish Jhurani

Abstract:

This study tackles the significant computational challenge of predicting excited state dynamics in organic photovoltaic (OPV) materials—a pivotal factor in the performance of solar energy solutions. Time-dependent density functional theory (TDDFT), though effective, is computationally prohibitive for larger and more complex molecules. As a solution, the research explores the application of transformer neural networks, a type of artificial intelligence (AI) model known for its superior performance in natural language processing, to predict excited state dynamics in OPV materials. The methodology involves a two-fold process. First, the transformer model is trained on an extensive dataset comprising over 10,000 TDDFT calculations of excited state dynamics from a diverse set of OPV materials. Each training example includes a molecular structure and the corresponding TDDFT-calculated excited state lifetimes and key electronic transitions. Second, the trained model is tested on a separate set of molecules, and its predictions are rigorously compared to independent TDDFT calculations. The results indicate a remarkable degree of predictive accuracy. Specifically, for a test set of 1,000 OPV materials, the transformer model predicted excited state lifetimes with a mean absolute error of 0.15 picoseconds, a negligible deviation from TDDFT-calculated values. The model also correctly identified key electronic transitions contributing to the excited state dynamics in 92% of the test cases, signifying a substantial concordance with the results obtained via conventional quantum chemistry calculations. The practical integration of the transformer model with existing quantum chemistry software was also realized, demonstrating its potential as a powerful tool in the arsenal of materials scientists and chemists. The implementation of this AI model is estimated to reduce the computational cost of predicting excited state dynamics by two orders of magnitude compared to conventional TDDFT calculations. The successful utilization of transformer neural networks to accurately predict excited state dynamics provides an efficient computational pathway for the accelerated discovery and design of new OPV materials, potentially catalyzing advancements in the realm of sustainable energy solutions.

Keywords: transformer neural networks, organic photovoltaic materials, excited state dynamics, time-dependent density functional theory, predictive modeling

Procedia PDF Downloads 121

Authors: A. Degale Desta, Cheng Jian

Abstract:

Deep learning application in computer vision is rapidly advancing, giving it the ability to monitor the public and quickly identify potentially anomalous behaviour from crowd scenes. Therefore, the purpose of the current work is to improve the performance of safety of people in crowd events from panic behaviour through introducing the innovative idea of Aggregation of Ensembles (AOE), which makes use of the pre-trained ConvNets and a pool of classifiers to find anomalies in video data with packed scenes. According to the theory of algorithms that applied K-means, KNN, CNN, SVD, and Faster-CNN, YOLOv5 architectures learn different levels of semantic representation from crowd videos; the proposed approach leverages an ensemble of various fine-tuned convolutional neural networks (CNN), allowing for the extraction of enriched feature sets. In addition to the above algorithms, a long short-term memory neural network to forecast future feature values and a handmade feature that takes into consideration the peculiarities of the crowd to understand human behavior. On well-known datasets of panic situations, experiments are run to assess the effectiveness and precision of the suggested method. Results reveal that, compared to state-of-the-art methodologies, the system produces better and more promising results in terms of accuracy and processing speed.

Keywords: action recognition, computer vision, crowd detecting and tracking, deep learning

Procedia PDF Downloads 165

Authors: Ashish Jaiswal, Ashwin Ramesh Babu, Mohammad Zaki Zadeh, Fillia Makedon, Glenn Wylie

Abstract:

Functional magnetic resonance imaging (fMRI) is a neuroimaging technique that records neural activations in the brain by capturing the blood oxygen level in different regions based on the task performed by a subject. Given fMRI data, the problem of predicting the state of cognitive fatigue in a person has not been investigated to its full extent. This paper proposes tackling this issue as a multi-class classification problem by dividing the state of cognitive fatigue into six different levels, ranging from no-fatigue to extreme fatigue conditions. We built a spatio-temporal model that uses convolutional neural networks (CNN) for spatial feature extraction and a long short-term memory (LSTM) network for temporal modeling of 4D fMRI scans. We also applied a self-supervised method called MoCo (Momentum Contrast) to pre-train our model on a public dataset BOLD5000 and fine-tuned it on our labeled dataset to predict cognitive fatigue. Our novel dataset contains fMRI scans from Traumatic Brain Injury (TBI) patients and healthy controls (HCs) while performing a series of N-back cognitive tasks. This method establishes a state-of-the-art technique to analyze cognitive fatigue from fMRI data and beats previous approaches to solve this problem.

Keywords: fMRI, brain imaging, deep learning, self-supervised learning, contrastive learning, cognitive fatigue

Procedia PDF Downloads 191

Authors: Muqdad Al-Juboori, Bithin Datta

Abstract:

Hydraulic structures such as gravity dams are classified as essential structures, and have the vital role in providing strong and safe water resource management. Three major aspects must be considered to achieve an effective design of such a structure: 1) The building cost, 2) safety, and 3) accurate analysis of seepage characteristics. Due to the complexity and non-linearity relationships of the seepage process, many approximation theories have been developed; however, the application of these theories results in noticeable errors. The analytical solution, which includes the difficult conformal mapping procedure, could be applied for a simple and symmetrical problem only. Therefore, the objectives of this paper are to: 1) develop a surrogate model based on numerical simulated data using SEEPW software to approximately simulate seepage process related to a hydraulic structure, 2) develop and solve a linked simulation-optimization model based on the developed surrogate model to describe the seepage occurring under a concrete gravity dam, in order to obtain optimum and safe design at minimum cost. The result shows that the linked simulation-optimization model provides an efficient and optimum design of concrete gravity dams.

Keywords: artificial neural network, concrete gravity dam, genetic algorithm, seepage analysis

Procedia PDF Downloads 225

Authors: Feng Yang

Abstract:

Machine learning (ML), especially deep learning (DL), has been extensively applied to many applications in recently years and gained great success in solving different problems, including scientific problems. However, conventional ML/DL methodologies are purely data-driven which have the limitations, such as need of ample amount of labelled training data, lack of consistency to physical principles, and lack of generalizability to new problems/domains. Recently, there is a growing consensus that ML models need to further take advantage of prior knowledge to deal with these limitations. Physics-informed machine learning, aiming at integration of physics/domain knowledge into ML, has been recognized as an emerging area of research, especially in the recent 2 to 3 years. In this work, physics-informed ML, specifically physics-informed neural network (NN), is employed and implemented to estimate the displacements at x, y, z directions in a solid mechanics problem that is controlled by equilibrium equations with boundary conditions. By incorporating the physics (i.e. the equilibrium equations) into the learning process of NN, it is showed that the NN can be trained very efficiently with a small set of labelled training data. Experiments with different settings of the NN model and the amount of labelled training data were conducted, and the results show that very high accuracy can be achieved in fulfilling the equilibrium equations as well as in predicting the displacements, e.g. in setting the overall displacement of 0.1, a root mean square error (RMSE) of 2.09 × 10−4 was achieved.

Keywords: deep learning, neural network, physics-informed machine learning, solid mechanics

Procedia PDF Downloads 150

Authors: Krishna Mohan Bathula, Fatou Bintou Loucoubar, FNU Kaleemunnisa, Christelle Scharff, Mark Anthony De Castro

Abstract:

Voice recognition algorithms such as automatic speech recognition and text-to-speech systems with African languages can play an important role in bridging the digital divide of Artificial Intelligence in Africa, contributing to the establishment of a fully inclusive information society. This paper proposes a Deep Learning model that can classify the user responses as inputs for an interactive voice response system. A dataset with Wolof language words ‘yes’ and ‘no’ is collected as audio recordings. A two stage Data Augmentation approach is adopted for enhancing the dataset size required by the deep neural network. Data preprocessing and feature engineering with Mel-Frequency Cepstral Coefficients are implemented. Convolutional Neural Networks (CNNs) have proven to be very powerful in image classification and are promising for audio processing when sounds are transformed into spectra. For performing voice response classification, the recordings are transformed into sound frequency feature spectra and then applied image classification methodology using a deep CNN model. The inference model of this trained and reusable Wolof voice response recognition system can be integrated with many applications associated with both web and mobile platforms.

Keywords: automatic speech recognition, interactive voice response, voice response recognition, wolof word classification

Procedia PDF Downloads 118

Authors: Maria Isabel Garcia-Planas, Maria Victoria Garcia-Camba

Abstract:

Recent advances in cognitive neuroscience have allowed a step forward in perceiving the processes involved in learning from the point of view of the acquisition of new information or the modification of existing mental content. The evoked potentials technique reveals how basic brain processes interact to achieve adequate and flexible behaviours. The objective of this work, using evoked potentials, is to study if it is possible to distinguish if a patient suffers a specific type of learning disorder to decide the possible therapies to follow. The methodology used, is the analysis of the dynamics of different areas of the brain during a cognitive activity to find the relationships between the different areas analyzed in order to better understand the functioning of neural networks. Also, the latest advances in neuroscience have revealed the existence of different brain activity in the learning process that can be highlighted through the use of non-invasive, innocuous, low-cost and easy-access techniques such as, among others, the evoked potentials that can help to detect early possible neuro-developmental difficulties for their subsequent assessment and cure. From the study of the amplitudes and latencies of the evoked potentials, it is possible to detect brain alterations in the learning process specifically in dyscalculia, to achieve specific corrective measures for the application of personalized psycho pedagogical plans that allow obtaining an optimal integral development of the affected people.

Keywords: dyscalculia, neurodevelopment, evoked potentials, Learning disabilities, neural networks

Procedia PDF Downloads 142

Authors: Dongju Kim, Youngjoo Suh, Hyojin Kim, Gyeongyeong Kim

Abstract:

Acoustic Emission Testing (AET) is widely used to test the structural integrity of an operational hydrogen storage container, and clustering algorithms are frequently used in pattern recognition methods to interpret AET results. However, the interpretation of AET results can vary from user to user as the tuning of the relevant parameters relies on the user's experience and knowledge of AET. Therefore, it is necessary to use a deep learning model to identify patterns in acoustic emission (AE) signal data that can be used to classify defects instead. In this paper, a deep learning-based model for classifying the types of defects in hydrogen storage tanks, using AE sensor waveforms, is proposed. As hydrogen storage tanks are commonly constructed using carbon fiber reinforced polymer composite (CFRP), a defect classification dataset is collected through a tensile test on a specimen of CFRP with an AE sensor attached. The performance of the classification model, using one-dimensional convolutional neural network (1-D CNN) and synthetic minority oversampling technique (SMOTE) data augmentation, achieved 91.09% accuracy for each defect. It is expected that the deep learning classification model in this paper, used with AET, will help in evaluating the operational safety of hydrogen storage containers.

Keywords: acoustic emission testing, carbon fiber reinforced polymer composite, one-dimensional convolutional neural network, smote data augmentation

Procedia PDF Downloads 95

Authors: Ons Slimene, Aroua Taamallah, Maha Khemaja

Abstract:

In recent years, human activity recognition (HAR) has been a key area of research due to its diverse applications. It has garnered increasing attention in the field of computer vision. HAR plays an important role in people’s daily lives as it has the ability to learn advanced knowledge about human activities from data. In HAR, activities are usually represented by exploiting different types of sensors, such as embedded sensors or visual sensors. However, these sensors have limitations, such as local obstacles, image-related obstacles, sensor unreliability, and consumer concerns. Recently, several deep learning-based approaches have been proposed for HAR and these approaches are classified into two categories based on the type of data used: vision-based approaches and sensor-based approaches. This research paper highlights the importance of multimodal data fusion from skeleton data obtained from videos and data generated by embedded sensors using deep neural networks for achieving HAR. We propose a deep multimodal fusion network based on a twostream architecture. These two streams use the Convolutional Neural Network combined with the Bidirectional LSTM (CNN BILSTM) to process skeleton data and data generated by embedded sensors and the fusion at the feature level is considered. The proposed model was evaluated on a public OPPORTUNITY++ dataset and produced a accuracy of 96.77%.

Keywords: human activity recognition, action recognition, sensors, vision, human-centric sensing, deep learning, context-awareness

Procedia PDF Downloads 102

Authors: G. Singer, M. Golan

Abstract:

Providing students with learning disabilities (LD) with extra time to grant them equal access to the exam is a necessary but insufficient condition to compensate for their LD; there should also be a clear indication that the additional time was actually used. For example, if students with LD use more time than students without LD and yet receive lower grades, this may indicate that a different accommodation is required. If they achieve higher grades but use the same amount of time, then the effectiveness of the accommodation has not been demonstrated. The main goal of this study is to evaluate the effect of including parameters related to LD and extended exam time, along with other commonly-used characteristics (e.g., student background and ability measures such as high-school grades), on the ability of ordinal decision-tree algorithms to predict exam performance. We use naturally-occurring data collected from hundreds of undergraduate engineering students. The sub-goals are i) to examine the improvement in prediction accuracy when the indicator of exam performance includes 'actual time used' in addition to the conventional indicator (exam grade) employed in most research; ii) to explore the effectiveness of extended exam time on exam performance for different courses and for LD students with different profiles (i.e., sets of characteristics). This is achieved by using the patterns (i.e., subgroups) generated by the algorithms to identify pairs of subgroups that differ in just one characteristic (e.g., course or type of LD) but have different outcomes in terms of exam performance (grade and time used). Since grade and time used to exhibit an ordering form, we propose a method based on ordinal decision-trees, which applies a weighted information-gain ratio (WIGR) measure for selecting the classifying attributes. Unlike other known ordinal algorithms, our method does not assume monotonicity in the data. The proposed WIGR is an extension of an information-theoretic measure, in the sense that it adjusts to the case of an ordinal target and takes into account the error severity between two different target classes. Specifically, we use ordinal C4.5, random-forest, and AdaBoost algorithms, as well as an ensemble technique composed of ordinal and non-ordinal classifiers. Firstly, we find that the inclusion of LD and extended exam-time parameters improves prediction of exam performance (compared to specifications of the algorithms that do not include these variables). Secondly, when the indicator of exam performance includes 'actual time used' together with grade (as opposed to grade only), the prediction accuracy improves. Thirdly, our subgroup analyses show clear differences in the effect of extended exam time on exam performance among different courses and different student profiles. From a methodological perspective, we find that the ordinal decision-tree based algorithms outperform their conventional, non-ordinal counterparts. Further, we demonstrate that the ensemble-based approach leverages the strengths of each type of classifier (ordinal and non-ordinal) and yields better performance than each classifier individually.

Keywords: actual exam time usage, ensemble learning, learning disabilities, ordinal classification, time extension

Procedia PDF Downloads 101

Authors: Stelios A. Mitilineos, Nicolas-Alexander Tatlas, Georgia Korompili, Lampros Kokkalas, Stelios M. Potirakis

Abstract:

Obstructive Sleep Apnea Hypopnea Syndrome (OSAHS) is a widespread chronic disease that mostly remains undetected, mainly due to the fact that it is diagnosed via polysomnography which is a time and resource-intensive procedure. Screening the disease’s symptoms at home could be used as an alternative approach in order to alert individuals that potentially suffer from OSAHS without compromising their everyday routine. Since snoring is usually linked to OSAHS, developing a snore detector is appealing as an enabling technology for screening OSAHS at home using ubiquitous equipment like commodity microphones (included in, e.g., smartphones). In this context, this study developed a snore detection tool and herein present the approach and selection of specific sound features that discriminate snoring vs. environmental sounds, as well as the performance of the proposed tool. Furthermore, a Real-Time Snore Detector (RTSD) is built upon the snore detection tool and employed in whole-night sleep sound recordings resulting to a large dataset of snoring sound excerpts that are made freely available to the public. The RTSD may be used either as a stand-alone tool that offers insight to an individual’s sleep quality or as an independent component of OSAHS screening applications in future developments.

Keywords: obstructive sleep apnea hypopnea syndrome, apnea screening, snoring detection, machine learning, neural networks

Procedia PDF Downloads 208

Authors: Masahiro Miyaji

Abstract:

When a driver happens to be involved in some traffic congestion or after traffic incidents, the driver may fall in a state of anger. State of anger may encounter decisive risk resulting in severer traffic accidents. Preventive safety function using driver’s psychosomatic state with regard to anger may be one of solutions which would avoid that kind of risks. Identifying driver’s anger state is important to create countermeasures to prevent the risk of traffic accidents. As a first step, this research figured out root cause of traffic incidents by means of using Internet survey. From statistical analysis of the survey, dominant psychosomatic states immediately before traffic incidents were haste, distraction, drowsiness and anger. Then, we replicated anger state of a driver while driving, and then, replicated it by means of using driving simulator on bench test basis. Six types of facial expressions including anger were introduced as alternative characteristics. Kohonen neural network was adopted to classify anger state. Then, we created a methodology to detect anger state of a driver in high accuracy. We presented a driving support safety function. The function adapts driver’s anger state in cooperation with an autonomous driving unit to reduce the number of traffic accidents. Consequently, e evaluated reduction rate of driver’s anger in the traffic accident. To validate the estimation results, we referred the reduction rate of Advanced Safety Vehicle (ASV) as well as Intelligent Transportation Systems (ITS).

Keywords: Kohonen neural network, driver’s anger state, reduction of traffic accidents, driver’s state adaptive driving support safety

Procedia PDF Downloads 359

Authors: Rajvir Kaur, Jeewani Anupama Ginige

Abstract:

With recent trends in Big Data and advancements in Information and Communication Technologies, the healthcare industry is at the stage of its transition from clinician oriented to technology oriented. Many people around the world die of cancer because the diagnosis of disease was not done at an early stage. Nowadays, the computational methods in the form of Machine Learning (ML) are used to develop automated decision support systems that can diagnose cancer with high confidence in a timely manner. This paper aims to carry out the comparative evaluation of a selected set of ML classifiers on two existing datasets: breast cancer and cervical cancer. The ML classifiers compared in this study are Decision Tree (DT), Support Vector Machine (SVM), k-Nearest Neighbor (k-NN), Logistic Regression, Ensemble (Bagged Tree) and Artificial Neural Networks (ANN). The evaluation is carried out based on standard evaluation metrics Precision (P), Recall (R), F1-score and Accuracy. The experimental results based on the evaluation metrics show that ANN showed the highest-level accuracy (99.4%) when tested with breast cancer dataset. On the other hand, when these ML classifiers are tested with the cervical cancer dataset, Ensemble (Bagged Tree) technique gave better accuracy (93.1%) in comparison to other classifiers.

Keywords: artificial neural networks, breast cancer, classifiers, cervical cancer, f-score, machine learning, precision, recall

Procedia PDF Downloads 278

Authors: D. Pugazhenthi, B. Sree Vidya

Abstract:

Cloud computing is one of the emerging technologies that enables end users to use the services of cloud on ‘pay per usage’ strategy. This technology grows in a fast pace and so is its security threat. One among the various services provided by cloud is storage. In this service, security plays a vital factor for both authenticating legitimate users and protection of information. This paper brings in efficient ways of authenticating users as well as securing information on the cloud. Initial phase proposed in this paper deals with an authentication technique using multi-factor and multi-dimensional authentication system with multi-level security. Unique identification and slow intrusive formulates an advanced reliability on user-behaviour based biometrics than conventional means of password authentication. By biometric systems, the accounts are accessed only by a legitimate user and not by a nonentity. The biometric templates employed here do not include single trait but multiple, viz., iris and finger prints. The coordinating stage of the authentication system functions on Ensemble Support Vector Machine (SVM) and optimization by assembling weights of base SVMs for SVM ensemble after individual SVM of ensemble is trained by the Artificial Fish Swarm Algorithm (AFSA). Thus it helps in generating a user-specific secure cryptographic key of the multimodal biometric template by fusion process. Data security problem is averted and enhanced security architecture is proposed using encryption and decryption system with double key cryptography based on Fuzzy Neural Network (FNN) for data storing and retrieval in cloud computing . The proposing scheme aims to protect the records from hackers by arresting the breaking of cipher text to original text. This improves the authentication performance that the proposed double cryptographic key scheme is capable of providing better user authentication and better security which distinguish between the genuine and fake users. Thus, there are three important modules in this proposed work such as 1) Feature extraction, 2) Multimodal biometric template generation and 3) Cryptographic key generation. The extraction of the feature and texture properties from the respective fingerprint and iris images has been done initially. Finally, with the help of fuzzy neural network and symmetric cryptography algorithm, the technique of double key encryption technique has been developed. As the proposed approach is based on neural networks, it has the advantage of not being decrypted by the hacker even though the data were hacked already. The results prove that authentication process is optimal and stored information is secured.

Keywords: artificial fish swarm algorithm (AFSA), biometric authentication, decryption, encryption, fingerprint, fusion, fuzzy neural network (FNN), iris, multi-modal, support vector machine classification

Procedia PDF Downloads 260