Search results for: physics-informed neural network

Authors: Piotr A. Kowalski, Kasper Sapala, Wiktor Warchalowski

Abstract:

PM10 is a suspended dust that primarily has a negative effect on the respiratory system. PM10 is responsible for attacks of coughing and wheezing, asthma or acute, violent bronchitis. Indirectly, PM10 also negatively affects the rest of the body, including increasing the risk of heart attack and stroke. Unfortunately, Poland is a country that cannot boast of good air quality, in particular, due to large PM concentration levels. Therefore, based on the dense network of Airly sensors, it was decided to deal with the problem of prediction of suspended particulate matter concentration. Due to the very complicated nature of this issue, the Machine Learning approach was used. For this purpose, Convolution Neural Network (CNN) neural networks have been adopted, these currently being the leading information processing methods in the field of computational intelligence. The aim of this research is to show the influence of particular CNN network parameters on the quality of the obtained forecast. The forecast itself is made on the basis of parameters measured by Airly sensors and is carried out for the subsequent day, hour after hour. The evaluation of learning process for the investigated models was mostly based upon the mean square error criterion; however, during the model validation, a number of other methods of quantitative evaluation were taken into account. The presented model of pollution prediction has been verified by way of real weather and air pollution data taken from the Airly sensor network. The dense and distributed network of Airly measurement devices enables access to current and archival data on air pollution, temperature, suspended particulate matter PM1.0, PM2.5, and PM10, CAQI levels, as well as atmospheric pressure and air humidity. In this investigation, PM2.5, and PM10, temperature and wind information, as well as external forecasts of temperature and wind for next 24h served as inputted data. Due to the specificity of the CNN type network, this data is transformed into tensors and then processed. This network consists of an input layer, an output layer, and many hidden layers. In the hidden layers, convolutional and pooling operations are performed. The output of this system is a vector containing 24 elements that contain prediction of PM10 concentration for the upcoming 24 hour period. Over 1000 models based on CNN methodology were tested during the study. During the research, several were selected out that give the best results, and then a comparison was made with the other models based on linear regression. The numerical tests carried out fully confirmed the positive properties of the presented method. These were carried out using real ‘big’ data. Models based on the CNN technique allow prediction of PM10 dust concentration with a much smaller mean square error than currently used methods based on linear regression. What's more, the use of neural networks increased Pearson's correlation coefficient (R²) by about 5 percent compared to the linear model. During the simulation, the R² coefficient was 0.92, 0.76, 0.75, 0.73, and 0.73 for 1st, 6th, 12th, 18th, and 24th hour of prediction respectively.

Keywords: air pollution prediction (forecasting), machine learning, regression task, convolution neural networks

Procedia PDF Downloads 149

Authors: Smail Boussaadi, Hassina Aliane

Abstract:

With the rapid growth of scientific literature, it is becoming increasingly challenging for researchers to keep up with the latest findings in their fields. Academic, professional networks play an essential role in connecting researchers and disseminating knowledge. To improve the user experience within these networks, we need effective article recommendation systems that provide personalized content.Current recommendation systems often rely on collaborative filtering or content-based techniques. However, these methods have limitations, such as the cold start problem and difficulty in capturing semantic relationships between articles. To overcome these challenges, we propose a new approach that combines BERTopic (Bidirectional Encoder Representations from Transformers), a state-of-the-art topic modeling technique, with community detection algorithms in a academic, professional network. Experiences confirm our performance expectations by showing good relevance and objectivity in the results.

Keywords: scientific articles, community detection, academic social network, recommender systems, neural topic model

Procedia PDF Downloads 97

Authors: Vaishnavi Shivde, Shrishti Sinha, Trapti Mishra

Abstract:

Traffic light detection from a moving vehicle is an important technology both for driver safety assistance functions as well as for autonomous driving in the city. This paper proposed a deep-learning-based traffic light recognition method that consists of a pixel-wise image segmentation technique and a fully convolutional network i.e., UNET architecture. This paper has used a method for detecting the position and recognizing the state of the traffic lights in video sequences is presented and evaluated using Traffic Light Dataset which contains masked traffic light image data. The first stage is the detection, which is accomplished through image processing (image segmentation) techniques such as image cropping, color transformation, segmentation of possible traffic lights. The second stage is the recognition, which means identifying the color of the traffic light or knowing the state of traffic light which is achieved by using a Convolutional Neural Network (UNET architecture).

Keywords: traffic light detection, image segmentation, machine learning, classification, convolutional neural networks

Procedia PDF Downloads 173

Authors: Justin Reverdi, Sixin Zhang, Serge Gratton, Said Aoues, Thomas Pellegrini

Abstract:

In Vapor Cycle Systems, the flow sensor plays a key role in different monitoring and control purposes. However, physical sensors can be expensive, inaccurate, heavy, cumbersome, or highly sensitive to vibrations, which is especially problematic when embedded into an aircraft. The conception of a virtual sensor based on other standard sensors is a good alternative. In this paper, a data-driven model using a Convolutional Neural Network is proposed to estimate the flow of the compressor. To fit the model to our dataset, we tested different loss functions. We show in our application that a Dynamic Time Warping based loss function called DILATE leads to better dynamical performance than the vanilla mean squared error (MSE) loss function. DILATE allows choosing a trade-off between static and dynamic performance.

Keywords: deep learning, dynamic time warping, vapor cycle system, virtual sensor

Procedia PDF Downloads 146

Authors: Nan Deng, Zhenqiu Liu

Abstract:

Thousands of patients with metastatic tumors were diagnosed with cancers of unknown primary sites each year. The inability to identify the primary cancer site may lead to inappropriate treatment and unexpected prognosis. Nowadays, a large amount of genomics and transcriptomics cancer data has been generated by next-generation sequencing (NGS) technologies, and The Cancer Genome Atlas (TCGA) database has accrued thousands of human cancer tumors and healthy controls, which provides an abundance of resource to differentiate cancer types. Meanwhile, deep convolutional neural networks (CNNs) have shown high accuracy on classification among a large number of image object categories. Here, we utilize 25 cancer primary tumors and 3 normal tissues from TCGA and convert their RNA-Seq gene expression profiling to color images; train, validate and test a CNN classifier directly from these images. The performance result shows that our CNN classifier can archive >80% test accuracy on most of the tumors and normal tissues. Since the gene expression pattern of distant metastases is similar to their primary tumors, the CNN classifier may provide a potential computational strategy on identifying the unknown primary origin of metastatic cancer in order to plan appropriate treatment for patients.

Keywords: bioinformatics, cancer, convolutional neural network, deep leaning, gene expression pattern

Procedia PDF Downloads 299

Authors: Biruhi Tesfaye, Avinash M. Potdar

Abstract:

The laboratory test process to determine the California bearing ratio (CBR) of black cotton soils is not only overpriced but also time-consuming as well. Hence advanced prediction of CBR plays a significant role as it is applicable In pavement design. The prediction of CBR of treated soil was executed by Artificial Neural Networks (ANNs) which is a Computational tool based on the properties of the biological neural system. To observe CBR values, combined eggshell and waste glass was added to soil as 4, 8, 12, and 16 % of the weights of the soil samples. Accordingly, the laboratory related tests were conducted to get the required best model. The maximum CBR value found at 5.8 at 8 % of eggshell waste glass powder addition. The model was developed using CBR as an output layer variable. CBR was considered as a function of the joint effect of liquid limit, plastic limit, and plastic index, optimum moisture content and maximum dry density. The best model that has been found was ANN with 5, 6 and 1 neurons in the input, hidden and output layer correspondingly. The performance of selected ANN has been 0.99996, 4.44E-05, 0.00353 and 0.0067 which are correlation coefficient (R), mean square error (MSE), mean absolute error (MAE) and root mean square error (RMSE) respectively. The research presented or summarized above throws light on future scope on stabilization with waste glass combined with different percentages of eggshell that leads to the economical design of CBR acceptable to pavement sub-base or base, as desired.

Keywords: CBR, artificial neural network, liquid limit, plastic limit, maximum dry density, OMC

Procedia PDF Downloads 191

Authors: T. Praveenkumar, Kulpreet Singh, Divy Bhanpuriya, M. Saimurugan

Abstract:

This study analysed the classification accuracy for gearbox faults using Machine Learning Techniques. Gearboxes are widely used for mechanical power transmission in rotating machines. Its rotating components such as bearings, gears, and shafts tend to wear due to prolonged usage, causing fluctuating vibrations. Increasing the dependability of mechanical components like a gearbox is hampered by their sealed design, which makes visual inspection difficult. One way of detecting impending failure is to detect a change in the vibration signature. The current study proposes various machine learning algorithms, with aid of these vibration signals for obtaining the fault classification accuracy of an automotive 4-Speed synchromesh gearbox. Experimental data in the form of vibration signals were acquired from a 4-Speed synchromesh gearbox using Data Acquisition System (DAQs). Statistical features were extracted from the acquired vibration signal under various operating conditions. Then the extracted features were given as input to the algorithms for fault classification. Supervised Machine Learning algorithms such as Support Vector Machines (SVM) and unsupervised algorithms such as Deep Feed Forward Neural Network (DFFNN), Deep Belief Networks (DBN) algorithms are used for fault classification. The fusion of DBN & DFFNN classifiers were architected to further enhance the classification accuracy and to reduce the computational complexity. The fault classification accuracy for each algorithm was thoroughly studied, tabulated, and graphically analysed for fused and individual algorithms. In conclusion, the fusion of DBN and DFFNN algorithm yielded the better classification accuracy and was selected for fault detection due to its faster computational processing and greater efficiency.

Keywords: deep belief networks, DBN, deep feed forward neural network, DFFNN, fault diagnosis, fusion of algorithm, vibration signal

Procedia PDF Downloads 113

Authors: A. Basu, A. A. Purohit, M. M. Vaidya, M. D. Kudale

Abstract:

Mumbai, being traditionally the epicenter of India's trade and commerce, the existing major ports such as Mumbai and Jawaharlal Nehru Ports (JN) situated in Thane estuary are also developing its waterfront facilities. Various developments over the passage of decades in this region have changed the tidal flux entering/leaving the estuary. The intake at Pir-Pau is facing the problem of shortage of water in view of advancement of shoreline, while jetty near Ulwe faces the problem of ship scheduling due to existence of shallower depths between JN Port and Ulwe Bunder. In order to solve these problems, it is inevitable to have information about tide levels over a long duration by field measurements. However, field measurement is a tedious and costly affair; application of artificial intelligence was used to predict water levels by training the network for the measured tide data for one lunar tidal cycle. The application of two layered feed forward Artificial Neural Network (ANN) with back-propagation training algorithms such as Gradient Descent (GD) and Levenberg-Marquardt (LM) was used to predict the yearly tide levels at waterfront structures namely at Ulwe Bunder and Pir-Pau. The tide data collected at Apollo Bunder, Ulwe, and Vashi for a period of lunar tidal cycle (2013) was used to train, validate and test the neural networks. These trained networks having high co-relation coefficients (R= 0.998) were used to predict the tide at Ulwe, and Vashi for its verification with the measured tide for the year 2000 & 2013. The results indicate that the predicted tide levels by ANN give reasonably accurate estimation of tide. Hence, the trained network is used to predict the yearly tide data (2015) for Ulwe. Subsequently, the yearly tide data (2015) at Pir-Pau was predicted by using the neural network which was trained with the help of measured tide data (2000) of Apollo and Pir-Pau. The analysis of measured data and study reveals that: The measured tidal data at Pir-Pau, Vashi and Ulwe indicate that there is maximum amplification of tide by about 10-20 cm with a phase lag of 10-20 minutes with reference to the tide at Apollo Bunder (Mumbai). LM training algorithm is faster than GD and with increase in number of neurons in hidden layer and the performance of the network increases. The predicted tide levels by ANN at Pir-Pau and Ulwe provides valuable information about the occurrence of high and low water levels to plan the operation of pumping at Pir-Pau and improve ship schedule at Ulwe.

Keywords: artificial neural network, back-propagation, tide data, training algorithm

Procedia PDF Downloads 483

Authors: Mohamed Mokhtar, Mostafa F. Shaaban

Abstract:

Among the challenges facing solar photovoltaic (PV) systems in the United Arab Emirates (UAE), dust accumulation on solar panels is considered the most severe problem that faces the growth of solar power plants. The accumulation of dust on the solar panels significantly degrades output from these panels. Hence, solar PV panels have to be cleaned manually or using costly automated cleaning methods. This paper focuses on initiating cleaning actions when required to reduce maintenance costs. The cleaning actions are triggered only when the dust level exceeds a threshold value. The amount of dust accumulated on the PV panels is estimated using an artificial neural network (ANN). Experiments are conducted to collect the required data, which are used in the training of the ANN model. Then, this ANN model will be fed by the output power from solar panels, ambient temperature, and solar irradiance, and thus, it will be able to estimate the amount of dust accumulated on solar panels at these conditions. The model was tested on different case studies to confirm the accuracy of the developed model.

Keywords: machine learning, dust, PV panels, renewable energy

Procedia PDF Downloads 144

Authors: Ci Lin, Tet Yeap, Iluju Kiringa

Abstract:

This paper introduces the subspace rotation algorithm (SRA) to train the Restricted Hopfield Network (RHN) as an auto-associative memory. Subspace rotation algorithm is a gradient-free subspace tracking approach based on the singular value decomposition (SVD). In comparison with Backpropagation Through Time (BPTT) on training RHN, it is observed that SRA could always converge to the optimal solution and BPTT could not achieve the same performance when the model becomes complex, and the number of patterns is large. The AUTS case study showed that the RHN model trained by SRA could achieve a better structure of attraction basin with larger radius(in general) than the Hopfield Network(HNN) model trained by Hebbian learning rule. Through learning 10000 patterns from MNIST dataset with RHN models with different number of hidden nodes, it is observed that an several components could be adjusted to achieve a balance between recovery accuracy and noise resistance.

Keywords: hopfield neural network, restricted hopfield network, subspace rotation algorithm, hebbian learning rule

Procedia PDF Downloads 117

Authors: Mustafa Alhamdi

Abstract:

Industrial application to classify gamma rays and neutron events is investigated in this study using deep machine learning. The identification using a convolutional neural network and recursive neural network showed a significant improvement in predication accuracy in a variety of applications. The ability to identify the isotope type and activity from spectral information depends on feature extraction methods, followed by classification. The features extracted from the spectrum profiles try to find patterns and relationships to present the actual spectrum energy in low dimensional space. Increasing the level of separation between classes in feature space improves the possibility to enhance classification accuracy. The nonlinear nature to extract features by neural network contains a variety of transformation and mathematical optimization, while principal component analysis depends on linear transformations to extract features and subsequently improve the classification accuracy. In this paper, the isotope spectrum information has been preprocessed by finding the frequencies components relative to time and using them as a training dataset. Fourier transform implementation to extract frequencies component has been optimized by a suitable windowing function. Training and validation samples of different isotope profiles interacted with CdTe crystal have been simulated using Geant4. The readout electronic noise has been simulated by optimizing the mean and variance of normal distribution. Ensemble learning by combing voting of many models managed to improve the classification accuracy of neural networks. The ability to discriminate gamma and neutron events in a single predication approach using deep machine learning has shown high accuracy using deep learning. The paper findings show the ability to improve the classification accuracy by applying the spectrogram preprocessing stage to the gamma and neutron spectrums of different isotopes. Tuning deep machine learning models by hyperparameter optimization of neural network models enhanced the separation in the latent space and provided the ability to extend the number of detected isotopes in the training database. Ensemble learning contributed significantly to improve the final prediction.

Keywords: machine learning, nuclear physics, Monte Carlo simulation, noise estimation, feature extraction, classification

Procedia PDF Downloads 150

Authors: Amin Ranjbar, Amir Arsalan Jalili Zolfaghari, Amir Abolfazl Suratgar, Mehrdad Khajavi

Abstract:

This paper describes two stages of learning-based fault detection procedure in alternators. The procedure consists of three states of machine condition namely shortened brush, high impedance relay and maintaining a healthy condition in the alternator. The fault detection algorithm uses Wigner-Ville distribution as a feature extractor and also appropriate feature classifier. In this work, ANN (Artificial Neural Network) and also SVM (support vector machine) were compared to determine more suitable performance evaluated by the mean squared of errors criteria. Modules work together to detect possible faulty conditions of machines working. To test the method performance, a signal database is prepared by making different conditions on a laboratory setup. Therefore, it seems by implementing this method, satisfactory results are achieved.

Keywords: alternator, artificial neural network, support vector machine, time-frequency analysis, Wigner-Ville distribution

Procedia PDF Downloads 374

Authors: Chaitanya Chawla, Divya Panwar, Gurneesh Singh Anand, M. P. S Bhatia

Abstract:

This paper presents a deep-learning mechanism for classifying computer generated images and photographic images. The proposed method accounts for a convolutional layer capable of automatically learning correlation between neighbouring pixels. In the current form, Convolutional Neural Network (CNN) will learn features based on an image's content instead of the structural features of the image. The layer is particularly designed to subdue an image's content and robustly learn the sensor pattern noise features (usually inherited from image processing in a camera) as well as the statistical properties of images. The paper was assessed on latest natural and computer generated images, and it was concluded that it performs better than the current state of the art methods.

Keywords: image forensics, computer graphics, classification, deep learning, convolutional neural networks

Procedia PDF Downloads 336

Authors: Ying Li, Yan Li

Abstract:

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

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

Procedia PDF Downloads 534

Authors: Ulas Vural, M. Ergun Okay, E. Mesut Yildiz

Abstract:

Telecommunication service providers demand accurate and precise prediction of customer churn probabilities to increase the effectiveness of their customer relation services. The large amount of customer data owned by the service providers is suitable for analysis by machine learning methods. In this study, expenditure data of customers are analyzed by using an artificial neural network (ANN). The ANN model is applied to the data of customers with different billing duration. The proposed model successfully predicts the churn probabilities at 83% accuracy for only three months expenditure data and the prediction accuracy increases up to 89% when the nine month data is used. The experiments also show that the accuracy of ANN model increases on an extended feature set with information of the changes on the bill amounts.

Keywords: customer relationship management, churn prediction, telecom industry, deep learning, artificial neural networks

Procedia PDF Downloads 146

Authors: Wang Yichen, Haruka Yamashita

Abstract:

In recent years, in the field of sports, decision making such as member in the game and strategy of the game based on then analysis of the accumulated sports data are widely attempted. In fact, in the NBA basketball league where the world's highest level players gather, to win the games, teams analyze the data using various statistical techniques. However, it is difficult to analyze the game data for each play such as the ball tracking or motion of the players in the game, because the situation of the game changes rapidly, and the structure of the data should be complicated. Therefore, it is considered that the analysis method for real time game play data is proposed. In this research, we propose an analytical model for "determining the optimal lineup composition" using the real time play data, which is considered to be difficult for all coaches. In this study, because replacing the entire lineup is too complicated, and the actual question for the replacement of players is "whether or not the lineup should be changed", and “whether or not Small Ball lineup is adopted”. Therefore, we propose an analytical model for the optimal player selection problem based on Small Ball lineups. In basketball, we can accumulate scoring data for each play, which indicates a player's contribution to the game, and the scoring data can be considered as a time series data. In order to compare the importance of players in different situations and lineups, we combine RNN (Recurrent Neural Network) model, which can analyze time series data, and NN (Neural Network) model, which can analyze the situation on the field, to build the prediction model of score. This model is capable to identify the current optimal lineup for different situations. In this research, we collected all the data of accumulated data of NBA from 2019-2020. Then we apply the method to the actual basketball play data to verify the reliability of the proposed model.

Keywords: recurrent neural network, players lineup, basketball data, decision making model

Procedia PDF Downloads 133

Authors: Naghmeh Moradpoor Sheykhkanloo

Abstract:

Structured Query Language Injection (SQLI) attack is a code injection technique in which malicious SQL statements are inserted into a given SQL database by simply using a web browser. Losing data, disclosing confidential information or even changing the value of data are the severe damages that SQLI attack can cause on a given database. SQLI attack has also been rated as the number-one attack among top ten web application threats on Open Web Application Security Project (OWASP). OWASP is an open community dedicated to enabling organisations to consider, develop, obtain, function, and preserve applications that can be trusted. In this paper, we propose an effective pattern recognition neural network model for detection and classification of SQLI attacks. The proposed model is built from three main elements of: a Uniform Resource Locator (URL) generator in order to generate thousands of malicious and benign URLs, a URL classifier in order to: 1) classify each generated URL to either a benign URL or a malicious URL and 2) classify the malicious URLs into different SQLI attack categories, and an NN model in order to: 1) detect either a given URL is a malicious URL or a benign URL and 2) identify the type of SQLI attack for each malicious URL. The model is first trained and then evaluated by employing thousands of benign and malicious URLs. The results of the experiments are presented in order to demonstrate the effectiveness of the proposed approach.

Keywords: neural networks, pattern recognition, SQL injection attacks, SQL injection attack classification, SQL injection attack detection

Procedia PDF Downloads 469

Authors: Aydin Teymourifar, Gurkan Ozturk

Abstract:

In this paper, a distributed hybrid algorithm is proposed for solving the job shop scheduling problem. The suggested method executes different artificial neural networks, heuristics and meta-heuristics simultaneously on more than one machine. The neural networks are used to control the constraints of the problem while the meta-heuristics search the global space and the heuristics are used to prevent the premature convergence. To attain an efficient distributed intelligent method for solving big and distributed job shop scheduling problems, Apache Spark and Hadoop frameworks are used. In the algorithm implementation and design steps, new approaches are applied. Comparison between the proposed algorithm and other efficient algorithms from the literature shows its efficiency, which is able to solve large size problems in short time.

Keywords: distributed algorithms, Apache Spark, Hadoop, job shop scheduling, neural network

Procedia PDF Downloads 387

Authors: Chithra A. V., Somoshree Datta, Sandeep Nithyanandan

Abstract:

Sign Language Recognition (SLR) is the process of interpreting and translating sign language into spoken or written language using technological systems. It involves recognizing hand gestures, facial expressions, and body movements that makeup sign language communication. The primary goal of SLR is to facilitate communication between hearing- and speech-impaired communities and those who do not understand sign language. Due to the increased awareness and greater recognition of the rights and needs of the hearing- and speech-impaired community, sign language recognition has gained significant importance over the past 10 years. Technological advancements in the fields of Artificial Intelligence and Machine Learning have made it more practical and feasible to create accurate SLR systems. This paper presents a distinct approach to SLR by framing it as a video classification problem using Deep Learning (DL), whereby a combination of Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) has been used. This research targets the integration of sign language recognition into healthcare settings, aiming to improve communication between medical professionals and patients with hearing impairments. The spatial features from each video frame are extracted using a CNN, which captures essential elements such as hand shapes, movements, and facial expressions. These features are then fed into an RNN network that learns the temporal dependencies and patterns inherent in sign language sequences. The INCLUDE dataset has been enhanced with more videos from the healthcare domain and the model is evaluated on the same. Our model achieves 91% accuracy, representing state-of-the-art performance in this domain. The results highlight the effectiveness of treating SLR as a video classification task with the CNN-RNN architecture. This approach not only improves recognition accuracy but also offers a scalable solution for real-time SLR applications, significantly advancing the field of accessible communication technologies.

Keywords: sign language recognition, deep learning, convolution neural network, recurrent neural network

Procedia PDF Downloads 27

Authors: Nataša Kalajdžija, Strahinja Kovačević, Davor Lončar, Sanja Podunavac Kuzmanović, Lidija Jevrić

Abstract:

In order to investigate the relationship between retention and structure, a quantitative Structure Retention Relationships (QSRRs) study was applied for the prediction of retention times of a set of 23 secoestrane derivatives in a reversed-phase thin-layer chromatography. After the calculation of molecular descriptors, a suitable set of molecular descriptors was selected by using step-wise multiple linear regressions. Artificial Neural Network (ANN) method was employed to model the nonlinear structure-activity relationships. The ANN technique resulted in 5-6-1 ANN model with the correlation coefficient of 0.98. We found that the following descriptors: Critical pressure, total energy, protease inhibition, distribution coefficient (LogD) and parameter of lipophilicity (miLogP) have a significant effect on the retention times. The prediction results are in very good agreement with the experimental ones. This approach provided a new and effective method for predicting the chromatographic retention index for the secoestrane derivatives investigated.

Keywords: lipophilicity, QSRR, RP TLC retention, secoestranes

Procedia PDF Downloads 456

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

Abstract:

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

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

Procedia PDF Downloads 188

Authors: Lu Yang, Meiyang Song, Xiang Yu, Wenhao Zhou, Chuntao Feng

Abstract:

To address the problem that the FM continuous-wave radar (FMCW) extracts human vital sign signals which are susceptible to noise interference and low reconstruction accuracy, a new detection scheme for the sign signals is proposed. Firstly, an improved complete ensemble empirical modal decomposition with adaptive noise (ICEEMDAN) algorithm is applied to decompose the radar-extracted thoracic signals to obtain several intrinsic modal functions (IMF) with different spatial scales, and then the IMF components are optimized by a BP neural network improved by immune genetic algorithm (IGA). The simulation results show that this scheme can effectively separate the noise and accurately extract the respiratory and heartbeat signals and improve the reconstruction accuracy and signal-to-noise ratio of the sign signals.

Keywords: frequency modulated continuous wave radar, ICEEMDAN, BP neural network, vital signs signal

Procedia PDF Downloads 165

Authors: Humeyra Bolakar Tosun

Abstract:

The transport sector has an undisputed place in human life. People need transport access to continuous increase day by day with growing population. The number of rail network, urban transport planning, infrastructure improvements, transportation management and other related areas is a key factor affecting our country made it quite necessary to improve the work of transportation. In this context, it plays an important role in domestic rail freight demand planning. Alternatives that the increase in the transportation field and has made it mandatory requirements such as the demand for improving transport quality. In this study generally is known and used in studies by the definition, rail freight transport, railway line length, population, energy consumption. In this study, Iron Road Load Net Demand was modeled by multiple regression and ANN methods. In this study, model dependent variable (Output) is Iron Road Load Net demand and 6 entries variable was determined. These outcome values extracted from the model using ANN and regression model results. In the regression model, some parameters are considered as determinative parameters, and the coefficients of the determinants give meaningful results. As a result, ANN model has been shown to be more successful than traditional regression model.

Keywords: railway load carrying, neural network, modelling transport, transportation

Procedia PDF Downloads 143

Authors: Gurukiran Veerapur, Nytik Birudavolu, Seetharam U. N., Chandravva Hebbi, R. Praneeth Reddy

Abstract:

This work presents a robust approach for the recognition of characters in Telugu and Kannada, two South Indian scripts with structural similarities in characters. To recognize the characters exhaustive datasets are required, but there are only a few publicly available datasets. As a result, we decided to create a dataset for one language (source language),train the model with it, and then test it with the target language.Telugu is the target language in this work, whereas Kannada is the source language. The suggested method makes use of Canny edge features to increase character identification accuracy on pictures with noise and different lighting. A dataset of 45,150 images containing printed Kannada characters was created. The Nudi software was used to automatically generate printed Kannada characters with different writing styles and variations. Manual labelling was employed to ensure the accuracy of the character labels. The deep learning models like CNN (Convolutional Neural Network) and Visual Attention neural network (VAN) are used to experiment with the dataset. A Visual Attention neural network (VAN) architecture was adopted, incorporating additional channels for Canny edge features as the results obtained were good with this approach. The model's accuracy on the combined Telugu and Kannada test dataset was an outstanding 97.3%. Performance was better with Canny edge characteristics applied than with a model that solely used the original grayscale images. The accuracy of the model was found to be 80.11% for Telugu characters and 98.01% for Kannada words when it was tested with these languages. This model, which makes use of cutting-edge machine learning techniques, shows excellent accuracy when identifying and categorizing characters from these scripts.

Keywords: base characters, modifiers, guninthalu, aksharas, vattakshara, VAN

Procedia PDF Downloads 53

Authors: Kamal KC, Zhendong Yin, Dasen Li, Zhilu Wu

Abstract:

Intra-plant disease classification based on leaf images is a challenging computer vision task due to similarities in texture, color, and shape of leaves with a slight variation of leaf spot; and external environmental changes such as lighting and background noises. Deep convolutional neural network (DCNN) has proven to be an effective tool for binary classification. In this paper, two methods for binary classification of diseased plant leaves using DCNN are presented; model created from scratch and transfer learning. Our main contribution is a thorough evaluation of 4 networks created from scratch and transfer learning of 5 pre-trained models. Training and testing of these models were performed on a plant leaf images dataset belonging to 16 distinct classes, containing a total of 22,265 images from 8 different plants, consisting of a pair of healthy and diseased leaves. We introduce a deep CNN model, Optimized MobileNet. This model with depthwise separable CNN as a building block attained an average test accuracy of 99.77%. We also present a fine-tuning method by introducing the concept of a convolutional block, which is a collection of different deep neural layers. Fine-tuned models proved to be efficient in terms of accuracy and computational cost. Fine-tuned MobileNet achieved an average test accuracy of 99.89% on 8 pairs of [healthy, diseased] leaf ImageSet.

Keywords: deep convolution neural network, depthwise separable convolution, fine-grained classification, MobileNet, plant disease, transfer learning

Procedia PDF Downloads 186

Authors: David Oluigbo, Erik Hemberg, Nathan Shwatal, Wenqi Ding, Yin Yuan, Susanna Mierau

Abstract:

Introduction: Calcium imaging is an established technique in neuroscience research for detecting activity in neural networks. Bursts of action potentials in neurons lead to transient increases in intracellular calcium visualized with fluorescent indicators. Manual identification of cell bodies and their contours by experts typically takes 10-20 minutes per calcium imaging recording. Our aim, therefore, was to design an automated pipeline to facilitate and optimize calcium imaging data analysis. Our pipeline aims to accelerate cell body and contour identification and production of graphical representations reflecting changes in neuronal calcium-based fluorescence. Methods: We created a Python-based pipeline that uses OpenCV (a computer vision Python package) to accurately (1) detect neuron contours, (2) extract the mean fluorescence within the contour, and (3) identify transient changes in the fluorescence due to neuronal activity. The pipeline consisted of 3 Python scripts that could both be easily accessed through a Python Jupyter notebook. In total, we tested this pipeline on ten separate calcium imaging datasets from murine dissociate cortical cultures. We next compared our automated pipeline outputs with the outputs of manually labeled data for neuronal cell location and corresponding fluorescent times series generated by an expert neuroscientist. Results: Our results show that our automated pipeline efficiently pinpoints neuronal cell body location and neuronal contours and provides a graphical representation of neural network metrics accurately reflecting changes in neuronal calcium-based fluorescence. The pipeline detected the shape, area, and location of most neuronal cell body contours by using binary thresholding and grayscale image conversion to allow computer vision to better distinguish between cells and non-cells. Its results were also comparable to manually analyzed results but with significantly reduced result acquisition times of 2-5 minutes per recording versus 10-20 minutes per recording. Based on these findings, our next step is to precisely measure the specificity and sensitivity of the automated pipeline’s cell body and contour detection to extract more robust neural network metrics and dynamics. Conclusion: Our Python-based pipeline performed automated computer vision-based analysis of calcium image recordings from neuronal cell bodies in neuronal cell cultures. Our new goal is to improve cell body and contour detection to produce more robust, accurate neural network metrics and dynamic graphs.

Keywords: calcium imaging, computer vision, neural activity, neural networks

Procedia PDF Downloads 82

Authors: Merouane Boudjerda, Bénina Touaibia, Mustapha K Mihoubi

Abstract:

In Algeria, water resources play a crucial role in economic development. But over the last decades, they are relatively limited and gradually decreasing to the detriment of agriculture. The agricultural irrigation is the primary water consuming sector followed by the domestic and industrial sectors. The research presented in this paper focuses on the optimization of irrigation water demand. Dynamic Programming-Neural Network (DPNN) method is applied to investigate reservoir optimization. The optimal operation rule is formulated to minimize the gap between water release and water irrigation demand. As a case study, Boukerdane dam’s reservoir system in North of Algeria has been selected to examine our proposed optimization model. The application of DPNN method allowed increasing the satisfaction rate (SR) from 34% to 60%. In addition, the operation rule generated showed more reliable and resilience operation for the examined case study.

Keywords: water management, agricultural demand, Boukerdane dam, dynamic programming, artificial neural network

Procedia PDF Downloads 131

Authors: Dimitrios Triantakonstantis, Demetris Stathakis

Abstract:

Urban areas have been expanded throughout the globe. Monitoring and modeling urban growth have become a necessity for a sustainable urban planning and decision making. Urban prediction models are important tools for analyzing the causes and consequences of urban land use dynamics. The objective of this research paper is to analyze and model the urban change, which has been occurred from 1990 to 2000 using CORINE land cover maps. The model was developed using drivers of urban changes (such as road distance, slope, etc.) under an Artificial Neural Network modeling approach. Validation was achieved using a prediction map for 2006 which was compared with a real map of Urban Atlas of 2006. The accuracy produced a Kappa index of agreement of 0,639 and a value of Cramer's V of 0,648. These encouraging results indicate the importance of the developed urban growth prediction model which using a set of available common biophysical drivers could serve as a management tool for the assessment of urban change.

Keywords: artificial neural networks, CORINE, urban atlas, urban growth prediction

Procedia PDF Downloads 529

Authors: Vijay Pal Singh, Yogesh Chandra Kotiyal

Abstract:

Structures are a combination of various load carrying members which transfer the loads to the foundation from the superstructure safely. At the design stage, the loading of the structure is defined and appropriate material choices are made based upon their properties, mainly related to strength. The strength of materials kept on reducing with time because of many factors like environmental exposure and deformation caused by unpredictable external loads. Hence, to predict the strength of materials used in structures, various techniques are used. Among these techniques, Non-Destructive Techniques (NDT) are the one that can be used to predict the strength without damaging the structure. In the present study, the compressive strength of concrete has been predicted using Artificial Neural Network (ANN). The predicted strength was compared with the experimentally obtained actual compressive strength of concrete and equations were developed for different models. A good co-relation has been obtained between the predicted strength by these models and experimental values. Further, the co-relation has been developed using two NDT techniques for prediction of strength by regression analysis. It was found that the percentage error has been reduced between the predicted strength by using combined techniques in place of single techniques.

Keywords: rebound, ultra-sonic pulse, penetration, ANN, NDT, regression

Procedia PDF Downloads 428

Authors: Jiajun Wang, Xiaoge Li

Abstract:

The purpose of the aspect-level sentiment analysis task is to identify the sentiment polarity of aspects in a sentence. Currently, most methods mainly focus on using neural networks and attention mechanisms to model the relationship between aspects and context, but they ignore the dependence of words in different ranges in the sentence, resulting in deviation when assigning relationship weight to other words other than aspect words. To solve these problems, we propose a new aspect-level sentiment analysis model that combines a multi-channel convolutional network and graph convolutional network (GCN). Firstly, the context and the degree of association between words are characterized by Long Short-Term Memory (LSTM) and self-attention mechanism. Besides, a multi-channel convolutional network is used to extract the features of words in different ranges. Finally, a convolutional graph network is used to associate the node information of the dependency tree structure. We conduct experiments on four benchmark datasets. The experimental results are compared with those of other models, which shows that our model is better and more effective.

Keywords: aspect-level sentiment analysis, attention, multi-channel convolution network, graph convolution network, dependency tree

Procedia PDF Downloads 219