Search results for: gamma neural oscillation
1524 Comparison of Feedforward Back Propagation and Self-Organizing Map for Prediction of Crop Water Stress Index of Rice
Authors: Aschalew Cherie Workneh, K. S. Hari Prasad, Chandra Shekhar Prasad Ojha
Abstract:
Due to the increase in water scarcity, the crop water stress index (CWSI) is receiving significant attention these days, especially in arid and semiarid regions, for quantifying water stress and effective irrigation scheduling. Nowadays, machine learning techniques such as neural networks are being widely used to determine CWSI. In the present study, the performance of two artificial neural networks, namely, Self-Organizing Maps (SOM) and Feed Forward-Back Propagation Artificial Neural Networks (FF-BP-ANN), are compared while determining the CWSI of rice crop. Irrigation field experiments with varying degrees of irrigation were conducted at the irrigation field laboratory of the Indian Institute of Technology, Roorkee, during the growing season of the rice crop. The CWSI of rice was computed empirically by measuring key meteorological variables (relative humidity, air temperature, wind speed, and canopy temperature) and crop parameters (crop height and root depth). The empirically computed CWSI was compared with SOM and FF-BP-ANN predicted CWSI. The upper and lower CWSI baselines are computed using multiple regression analysis. The regression analysis showed that the lower CWSI baseline for rice is a function of crop height (h), air vapor pressure deficit (AVPD), and wind speed (u), whereas the upper CWSI baseline is a function of crop height (h) and wind speed (u). The performance of SOM and FF-BP-ANN were compared by computing Nash-Sutcliffe efficiency (NSE), index of agreement (d), root mean squared error (RMSE), and coefficient of correlation (R²). It is found that FF-BP-ANN performs better than SOM while predicting the CWSI of rice crops.Keywords: artificial neural networks; crop water stress index; canopy temperature, prediction capability
Procedia PDF Downloads 1011523 Multiple Fault Detection and Classification in a Coupled Motor with Rotor Using Artificial Neural Network
Authors: Mehrdad Nouri Khajavi, Gollamhassan Payganeh, Mohsen Fallah Tafti
Abstract:
Fault diagnosis is an important aspect of maintaining rotating machinery health and increasing productivity. Many researches has been done in this regards. Many faults such as unbalance, misalignment, looseness, bearing faults, etc. have been considered and diagnosed with different techniques. Most of the researches in fault diagnosis of rotating machinery deal with single fault. Where as in reality faults usually occur simultaneously and it is, therefore, necessary to recognize them at the same time. In this research, two of the most common faults namely unbalance and misalignment have been considered simultaneously with different intensity and then identified and classified with the use of Multi-Layer Perception Neural Network (MLPNN). Processed Vibration signals are used as the input to the MLPNN, and the class of mixed unbalancy, and misalignment is the output of the NN.Keywords: unbalance, parallel misalignment, combined faults, vibration signals
Procedia PDF Downloads 3431522 The Numerical Model of the Onset of Acoustic Oscillation in Pulse Tube Engine
Authors: Alexander I. Dovgyallo, Evgeniy A. Zinoviev, Svetlana O. Nekrasova
Abstract:
The most of works applied for the pulse tube converters contain the workflow description implemented through the use of mathematical models on stationary modes. However, the study of the thermoacoustic systems unsteady behavior in the start, stop, and acoustic load changes modes is in the particular interest. The aim of the present study was to develop a mathematical thermal excitation model of acoustic oscillations in pulse tube engine (PTE) as a small-scale scheme of pulse tube engine operating at atmospheric air. Unlike some previous works this standing wave configuration is a fully closed system. The improvements over previous mathematical models are the following: the model allows specifying any values of porosity for regenerator, takes into account the piston weight and the friction in the cylinder and piston unit, and determines the operating frequency. The numerical method is based on the relation equations between the pressure and volume velocity variables at the ends of each element of PTE which is recorded through the appropriate transformation matrix. A solution demonstrates that the PTE operation frequency is the complex value, and it depends on the piston mass and the dynamic friction due to its movement in the cylinder. On the basis of the determined frequency thermoacoustically induced heat transport and generation of acoustic power equations were solved for channel with temperature gradient on its ends. The results of numerical simulation demonstrate the features of the initialization process of oscillation and show that that generated acoustic power more than power on the steady mode in a factor of 3…4. But doesn`t mean the possibility of its further continuous utilizing due to its existence only in transient mode which lasts only for a 30-40 sec. The experiments were carried out on small-scale PTE. The results shows that the value of acoustic power is in the range of 0.7..1.05 W for the defined frequency range f = 13..18 Hz and pressure amplitudes 11..12 kPa. These experimental data are satisfactorily correlated with the numerical modeling results. The mathematical model can be straightforwardly applied for the thermoacoustic devices with variable temperatures of thermal reservoirs and variable transduction loads which are expected to occur in practical implementations of portable thermoacoustic engines.Keywords: nonlinear processes, pulse tube engine, thermal excitation, standing wave
Procedia PDF Downloads 3661521 Heat and Mass Transfer of an Oscillating Flow in a Porous Channel with Chemical Reaction
Authors: Zahra Neffah, Henda Kahalerras
Abstract:
A numerical study is made in a parallel-plate porous channel subjected to an oscillating flow and an exothermic chemical reaction on its walls. The flow field in the porous region is modeled by the Darcy–Brinkman–Forchheimer model and the finite volume method is used to solve the governing equations. The effects of the modified Frank-Kamenetskii (FKm) and Damköhler (Dm) numbers, the amplitude of oscillation (A), and the Strouhal number (St) are examined. The main results show an increase of heat and mass transfer rates with A and St, and their decrease with FKm and Dm.Keywords: chemical reaction, heat and mass transfer, oscillating flow, porous channel
Procedia PDF Downloads 4051520 A Pattern Recognition Neural Network Model for Detection and Classification of SQL Injection Attacks
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 4551519 Evaluation of the Gamma-H2AX Expression as a Biomarker of DNA Damage after X-Ray Radiation in Angiography Patients
Authors: Reza Fardid, Aliyeh Alipour
Abstract:
Introduction: Coronary heart disease (CHD) is the most common and deadliest diseases. A coronary angiography is an important tool for the diagnosis and treatment of this disease. Because angiography is performed by exposure to ionizing radiation, it can lead to harmful effects. Ionizing radiation induces double-stranded breaks in DNA, which is a potentially life-threatening injury. The purpose of the present study is an investigation of the phosphorylation of histone H2AX in the location of the double-stranded break in Peripheral blood lymphocytes as an indication of Biological effects of radiation on angiography patients. Materials and Methods: This method is based on measurement of the phosphorylation of histone (gamma-H2AX, gH2AX) level on serine 139 after formation of DNA double-strand break. 5 cc of blood from 24 patients with angiography were sampled before and after irradiation. Blood lymphocytes were removed, fixed and were stained with specific ϒH2AX antibodies. Finally, ϒH2AX signal as an indicator of the double-strand break was measured with Flow Cytometry Technique. Results and discussion: In all patients, an increase was observed in the number of breaks in double-stranded DNA after irradiation (20.15 ± 14.18) compared to before exposure (1.52 ± 0.34). Also, the mean of DNA double-strand break was showed a linear correlation with DAP. However, although induction of DNA double-strand breaks associated with radiation dose in patients, the effect of individual factors such as radiosensitivity and regenerative capacity should not be ignored. If in future we can measure DNA damage response in every patient angiography and it will be used as a biomarker patient dose, will look very impressive on the public health level. Conclusion: Using flow cytometry readings which are done automatically, it is possible to detect ϒH2AX in the number of blood cells. Therefore, the use of this technique could play a significant role in monitoring patients.Keywords: coronary angiography, DSB of DNA, ϒH2AX, ionizing radiation
Procedia PDF Downloads 1711518 Evaluating the Capability of the Flux-Limiter Schemes in Capturing the Turbulence Structures in a Fully Developed Channel Flow
Authors: Mohamed Elghorab, Vendra C. Madhav Rao, Jennifer X. Wen
Abstract:
Turbulence modelling is still evolving, and efforts are on to improve and develop numerical methods to simulate the real turbulence structures by using the empirical and experimental information. The monotonically integrated large eddy simulation (MILES) is an attractive approach for modelling turbulence in high Re flows, which is based on the solving of the unfiltered flow equations with no explicit sub-grid scale (SGS) model. In the current work, this approach has been used, and the action of the SGS model has been included implicitly by intrinsic nonlinear high-frequency filters built into the convection discretization schemes. The MILES solver is developed using the opensource CFD OpenFOAM libraries. The role of flux limiters schemes namely, Gamma, superBee, van-Albada and van-Leer, is studied in predicting turbulent statistical quantities for a fully developed channel flow with a friction Reynolds number, ReT = 180, and compared the numerical predictions with the well-established Direct Numerical Simulation (DNS) results for studying the wall generated turbulence. It is inferred from the numerical predictions that Gamma, van-Leer and van-Albada limiters produced more diffusion and overpredicted the velocity profiles, while superBee scheme reproduced velocity profiles and turbulence statistical quantities in good agreement with the reference DNS data in the streamwise direction although it deviated slightly in the spanwise and normal to the wall directions. The simulation results are further discussed in terms of the turbulence intensities and Reynolds stresses averaged in time and space to draw conclusion on the flux limiter schemes performance in OpenFOAM context.Keywords: flux limiters, implicit SGS, MILES, OpenFOAM, turbulence statistics
Procedia PDF Downloads 1791517 Evaluating Generative Neural Attention Weights-Based Chatbot on Customer Support Twitter Dataset
Authors: Sinarwati Mohamad Suhaili, Naomie Salim, Mohamad Nazim Jambli
Abstract:
Sequence-to-sequence (seq2seq) models augmented with attention mechanisms are playing an increasingly important role in automated customer service. These models, which are able to recognize complex relationships between input and output sequences, are crucial for optimizing chatbot responses. Central to these mechanisms are neural attention weights that determine the focus of the model during sequence generation. Despite their widespread use, there remains a gap in the comparative analysis of different attention weighting functions within seq2seq models, particularly in the domain of chatbots using the Customer Support Twitter (CST) dataset. This study addresses this gap by evaluating four distinct attention-scoring functions—dot, multiplicative/general, additive, and an extended multiplicative function with a tanh activation parameter — in neural generative seq2seq models. Utilizing the CST dataset, these models were trained and evaluated over 10 epochs with the AdamW optimizer. Evaluation criteria included validation loss and BLEU scores implemented under both greedy and beam search strategies with a beam size of k=3. Results indicate that the model with the tanh-augmented multiplicative function significantly outperforms its counterparts, achieving the lowest validation loss (1.136484) and the highest BLEU scores (0.438926 under greedy search, 0.443000 under beam search, k=3). These results emphasize the crucial influence of selecting an appropriate attention-scoring function in improving the performance of seq2seq models for chatbots. Particularly, the model that integrates tanh activation proves to be a promising approach to improve the quality of chatbots in the customer support context.Keywords: attention weight, chatbot, encoder-decoder, neural generative attention, score function, sequence-to-sequence
Procedia PDF Downloads 711516 A Hybrid Model of Structural Equation Modelling-Artificial Neural Networks: Prediction of Influential Factors on Eating Behaviors
Authors: Maryam Kheirollahpour, Mahmoud Danaee, Amir Faisal Merican, Asma Ahmad Shariff
Abstract:
Background: The presence of nonlinearity among the risk factors of eating behavior causes a bias in the prediction models. The accuracy of estimation of eating behaviors risk factors in the primary prevention of obesity has been established. Objective: The aim of this study was to explore the potential of a hybrid model of structural equation modeling (SEM) and Artificial Neural Networks (ANN) to predict eating behaviors. Methods: The Partial Least Square-SEM (PLS-SEM) and a hybrid model (SEM-Artificial Neural Networks (SEM-ANN)) were applied to evaluate the factors affecting eating behavior patterns among university students. 340 university students participated in this study. The PLS-SEM analysis was used to check the effect of emotional eating scale (EES), body shape concern (BSC), and body appreciation scale (BAS) on different categories of eating behavior patterns (EBP). Then, the hybrid model was conducted using multilayer perceptron (MLP) with feedforward network topology. Moreover, Levenberg-Marquardt, which is a supervised learning model, was applied as a learning method for MLP training. The Tangent/sigmoid function was used for the input layer while the linear function applied for the output layer. The coefficient of determination (R²) and mean square error (MSE) was calculated. Results: It was proved that the hybrid model was superior to PLS-SEM methods. Using hybrid model, the optimal network happened at MPLP 3-17-8, while the R² of the model was increased by 27%, while, the MSE was decreased by 9.6%. Moreover, it was found that which one of these factors have significantly affected on healthy and unhealthy eating behavior patterns. The p-value was reported to be less than 0.01 for most of the paths. Conclusion/Importance: Thus, a hybrid approach could be suggested as a significant methodological contribution from a statistical standpoint, and it can be implemented as software to be able to predict models with the highest accuracy.Keywords: hybrid model, structural equation modeling, artificial neural networks, eating behavior patterns
Procedia PDF Downloads 1381515 On the Quantum Behavior of Nanoparticles: Quantum Theory and Nano-Pharmacology
Authors: Kurudzirayi Robson Musikavanhu
Abstract:
Nanophase particles exhibit quantum behavior by virtue of their small size, being particles of gamma to x-ray wavelength [atomic range]. Such particles exhibit high frequencies, high energy/photon, high penetration power, high ionization power [atomic behavior] and are stable at low energy levels as opposed to bulk phase matter [macro particles] which exhibit higher wavelength [radio wave end] properties, hence lower frequency, lower energy/photon, lower penetration power, lower ionizing power and are less stable at low temperatures. The ‘unique’ behavioral motion of Nano systems will remain a mystery as long as quantum theory remains a mystery, and for pharmacology, pharmacovigilance profiling of Nano systems becomes virtually impossible. Quantum theory is the 4 – 3 – 5 electromagnetic law of life and life motion systems on planet earth. Electromagnetic [wave-particle] properties of all particulate matter changes as mass [bulkiness] changes from one phase to the next [Nano-phase to micro-phase to milli-phase to meter-phase to kilometer phase etc.] and the subsequent electromagnetic effect of one phase particle on bulk matter [different phase] changes from one phase to another. All matter exhibit electromagnetic properties [wave-particle duality] in behavior and the lower the wavelength [and the lesser the bulkiness] the higher the gamma ray end properties exhibited and the higher the wavelength [and the greater the bulkiness], the more the radio-wave end properties are exhibited. Quantum theory is the 4 [moon] – 3[sun] – [earth] 5 law of the Electromagnetic spectrum [solar system]. 4 + 3 = 7; 4 + 3 + 5 = 12; 4 * 3 * 5 = 60; 42 + 32 = 52; 43 + 33 + 53 = 63. Quantum age is overdue.Keywords: electromagnetic solar system, nano-material, nano pharmacology, pharmacovigilance, quantum theory
Procedia PDF Downloads 4361514 Effective Supply Chain Coordination with Hybrid Demand Forecasting Techniques
Authors: Gurmail Singh
Abstract:
Effective supply chain is the main priority of every organization which is the outcome of strategic corporate investments with deliberate management action. Value-driven supply chain is defined through development, procurement and by configuring the appropriate resources, metrics and processes. However, responsiveness of the supply chain can be improved by proper coordination. So the Bullwhip effect (BWE) and Net stock amplification (NSAmp) values were anticipated and used for the control of inventory in organizations by both discrete wavelet transform-Artificial neural network (DWT-ANN) and Adaptive Network-based fuzzy inference system (ANFIS). This work presents a comparative methodology of forecasting for the customers demand which is non linear in nature for a multilevel supply chain structure using hybrid techniques such as Artificial intelligence techniques including Artificial neural networks (ANN) and Adaptive Network-based fuzzy inference system (ANFIS) and Discrete wavelet theory (DWT). The productiveness of these forecasting models are shown by computing the data from real world problems for Bullwhip effect and Net stock amplification. The results showed that these parameters were comparatively less in case of discrete wavelet transform-Artificial neural network (DWT-ANN) model and using Adaptive network-based fuzzy inference system (ANFIS).Keywords: bullwhip effect, hybrid techniques, net stock amplification, supply chain flexibility
Procedia PDF Downloads 1171513 Synthesis of the Robust Regulators on the Basis of the Criterion of the Maximum Stability Degree
Authors: S. A. Gayvoronsky, T. A. Ezangina
Abstract:
The robust control system objects with interval-undermined parameters is considers in this paper. Initial information about the system is its characteristic polynomial with interval coefficients. On the basis of coefficient estimations of quality indices and criterion of the maximum stability degree, the methods of synthesis of a robust regulator parametric is developed. The example of the robust stabilization system synthesis of the rope tension is given in this article.Keywords: interval polynomial, controller synthesis, analysis of quality factors, maximum degree of stability, robust degree of stability, robust oscillation, system accuracy
Procedia PDF Downloads 2921512 Using AI to Advance Factory Planning: A Case Study to Identify Success Factors of Implementing an AI-Based Demand Planning Solution
Authors: Ulrike Dowie, Ralph Grothmann
Abstract:
Rational planning decisions are based upon forecasts. Precise forecasting has, therefore, a central role in business. The prediction of customer demand is a prime example. This paper introduces recurrent neural networks to model customer demand and combines the forecast with uncertainty measures to derive decision support of the demand planning department. It identifies and describes the keys to the successful implementation of an AI-based solution: bringing together data with business knowledge, AI methods, and user experience, and applying agile software development practices.Keywords: agile software development, AI project success factors, deep learning, demand forecasting, forecast uncertainty, neural networks, supply chain management
Procedia PDF Downloads 1731511 Facebook Spam and Spam Filter Using Artificial Neural Networks
Authors: A. Fahim, Mutahira N. Naseem
Abstract:
SPAM is any unwanted electronic message or material in any form posted to many people. As the world is growing as global world, social networking sites play an important role in making world global providing people from different parts of the world a platform to meet and express their views. Among different social networking sites facebook become the leading one. With increase in usage different users start abusive use of facebook by posting or creating ways to post spam. This paper highlights the potential spam types nowadays facebook users faces. This paper also provide the reason how user become victim to spam attack. A methodology is proposed in the end discusses how to handle different types of spam.Keywords: artificial neural networks, facebook spam, social networking sites, spam filter
Procedia PDF Downloads 3671510 A Convolution Neural Network Approach to Predict Pes-Planus Using Plantar Pressure Mapping Images
Authors: Adel Khorramrouz, Monireh Ahmadi Bani, Ehsan Norouzi, Morvarid Lalenoor
Abstract:
Background: Plantar pressure distribution measurement has been used for a long time to assess foot disorders. Plantar pressure is an important component affecting the foot and ankle function and Changes in plantar pressure distribution could indicate various foot and ankle disorders. Morphologic and mechanical properties of the foot may be important factors affecting the plantar pressure distribution. Accurate and early measurement may help to reduce the prevalence of pes planus. With recent developments in technology, new techniques such as machine learning have been used to assist clinicians in predicting patients with foot disorders. Significance of the study: This study proposes a neural network learning-based flat foot classification methodology using static foot pressure distribution. Methodologies: Data were collected from 895 patients who were referred to a foot clinic due to foot disorders. Patients with pes planus were labeled by an experienced physician based on clinical examination. Then all subjects (with and without pes planus) were evaluated for static plantar pressures distribution. Patients who were diagnosed with the flat foot in both feet were included in the study. In the next step, the leg length was normalized and the network was trained for plantar pressure mapping images. Findings: From a total of 895 image data, 581 were labeled as pes planus. A computational neural network (CNN) ran to evaluate the performance of the proposed model. The prediction accuracy of the basic CNN-based model was performed and the prediction model was derived through the proposed methodology. In the basic CNN model, the training accuracy was 79.14%, and the test accuracy was 72.09%. Conclusion: This model can be easily and simply used by patients with pes planus and doctors to predict the classification of pes planus and prescreen for possible musculoskeletal disorders related to this condition. However, more models need to be considered and compared for higher accuracy.Keywords: foot disorder, machine learning, neural network, pes planus
Procedia PDF Downloads 3481509 Personal Information Classification Based on Deep Learning in Automatic Form Filling System
Authors: Shunzuo Wu, Xudong Luo, Yuanxiu Liao
Abstract:
Recently, the rapid development of deep learning makes artificial intelligence (AI) penetrate into many fields, replacing manual work there. In particular, AI systems also become a research focus in the field of automatic office. To meet real needs in automatic officiating, in this paper we develop an automatic form filling system. Specifically, it uses two classical neural network models and several word embedding models to classify various relevant information elicited from the Internet. When training the neural network models, we use less noisy and balanced data for training. We conduct a series of experiments to test my systems and the results show that our system can achieve better classification results.Keywords: artificial intelligence and office, NLP, deep learning, text classification
Procedia PDF Downloads 1861508 A Nonlinear Approach for System Identification of a Li-Ion Battery Based on a Non-Linear Autoregressive Exogenous Model
Authors: Meriem Mossaddek, El Mehdi Laadissi, El Mehdi Loualid, Chouaib Ennawaoui, Sohaib Bouzaid, Abdelowahed Hajjaji
Abstract:
An electrochemical system is a subset of mechatronic systems that includes a wide variety of batteries and nickel-cadmium, lead-acid batteries, and lithium-ion. Those structures have several non-linear behaviors and uncertainties in their running range. This paper studies an effective technique for modeling Lithium-Ion (Li-Ion) batteries using a Nonlinear Auto-Regressive model with exogenous input (NARX). The Artificial Neural Network (ANN) is trained to employ the data collected from the battery testing process. The proposed model is implemented on a Li-Ion battery cell. Simulation of this model in MATLAB shows good accuracy of the proposed model.Keywords: lithium-ion battery, neural network, energy storage, battery model, nonlinear models
Procedia PDF Downloads 991507 From Electroencephalogram to Epileptic Seizures Detection by Using Artificial Neural Networks
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 1761506 Film Dosimetry – An Asset for Collaboration Between Cancer Radiotherapy Centers at Established Institutions and Those Located in Low- and Middle-Income Countries
Authors: A. Fomujong, P. Mobit, A. Ndlovu, R. Teboh
Abstract:
Purpose: Film’s unique qualities, such as tissue equivalence, high spatial resolution, near energy independence and comparatively less expensive dosimeter, ought to make it the preferred and widely used in radiotherapy centers in low and middle income countries (LMICs). This, however, is not always the case, as other factors that are often maybe taken for granted in advanced radiotherapy centers remain a challenge in LMICs. We explored the unique qualities of film dosimetry that can make it possible for one Institution to benefit from another’s protocols via collaboration. Methods: For simplicity, two Institutions were considered in this work. We used a single batch of films (EBT-XD) and established a calibration protocol, including scan protocols and calibration curves, using the radiotherapy delivery system at Institution A. We then proceeded and performed patient-specific QA for patients treated on system A (PSQA-A-A). Films from the same batch were then sent to a remote center for PSQA on radiotherapy delivery system B. Irradiations were done at Institution B and then returned to Institution A for processing and analysis (PSQA-B-A). The following points were taken into consideration throughout the process (a) A reference film was irradiated to a known dose on the same system irradiating the PSQA film. (b) For calibration, we utilized the one-scan protocol and maintained the same scan orientation of the calibration, PSQA and reference films. Results: Gamma index analysis using a dose threshold of 10% and 3%/2mm criteria showed a gamma passing rate of 99.8% and 100% for the PSQA-A-A and PSQA-B-A, respectively. Conclusion: This work demonstrates that one could use established film dosimetry protocols in one Institution, e.g., an advanced radiotherapy center and apply similar accuracies to irradiations performed at another institution, e.g., a center located in LMIC, which thus encourages collaboration between the two for worldwide patient benefits.Keywords: collaboration, film dosimetry, LMIC, radiotherapy, calibration
Procedia PDF Downloads 651505 Musical Instrument Recognition in Polyphonic Audio Through Convolutional Neural Networks and Spectrograms
Authors: Rujia Chen, Akbar Ghobakhlou, Ajit Narayanan
Abstract:
This study investigates the task of identifying musical instruments in polyphonic compositions using Convolutional Neural Networks (CNNs) from spectrogram inputs, focusing on binary classification. The model showed promising results, with an accuracy of 97% on solo instrument recognition. When applied to polyphonic combinations of 1 to 10 instruments, the overall accuracy was 64%, reflecting the increasing challenge with larger ensembles. These findings contribute to the field of Music Information Retrieval (MIR) by highlighting the potential and limitations of current approaches in handling complex musical arrangements. Future work aims to include a broader range of musical sounds, including electronic and synthetic sounds, to improve the model's robustness and applicability in real-time MIR systems.Keywords: binary classifier, CNN, spectrogram, instrument
Procedia PDF Downloads 531504 Crushing Analysis of Foam-Filled Thin-Walled Aluminum Profiles Subjected to Axial Loading
Authors: Michał Rogala, Jakub Gajewski
Abstract:
As the automotive industry develops, passive safety is becoming an increasingly important aspect when designing motor vehicles. A commonly used solution is energy absorption by thin-walled construction. One such structure is a closed thin-walled profile fixed to the vehicle stringers. The article presents numerical tests of conical thin-walled profiles filled with aluminum foam. The columns were loaded axially with constant energy. On the basis of the results obtained, efficiency indicators were calculated. The efficiency of the foam filling was evaluated. Artificial neural networks were used for data analysis. The application of regression analysis was used as a tool to study the relationship between the quantities characteristic of the dynamic crush.Keywords: aluminium foam, crashworthiness, neural networks, thin-walled structure
Procedia PDF Downloads 1351503 Basics of Gamma Ray Burst and Its Afterglow
Authors: Swapnil Kumar Singh
Abstract:
Gamma-ray bursts (GRB's), short and intense pulses of low-energy γ rays, have fascinated astronomers and astrophysicists since their unexpected discovery in the late sixties. GRB'sare accompanied by long-lasting afterglows, and they are associated with core-collapse supernovae. The detection of delayed emission in X-ray, optical, and radio wavelength, or "afterglow," following a γ-ray burst can be described as the emission of a relativistic shell decelerating upon collision with the interstellar medium. While it is fair to say that there is strong diversity amongst the afterglow population, probably reflecting diversity in the energy, luminosity, shock efficiency, baryon loading, progenitor properties, circumstellar medium, and more, the afterglows of GRBs do appear more similar than the bursts themselves, and it is possible to identify common features within afterglows that lead to some canonical expectations. After an initial flash of gamma rays, a longer-lived "afterglow" is usually emitted at longer wavelengths (X-ray, ultraviolet, optical, infrared, microwave, and radio). It is a slowly fading emission at longer wavelengths created by collisions between the burst ejecta and interstellar gas. In X-ray wavelengths, the GRB afterglow fades quickly at first, then transitions to a less-steep drop-off (it does other stuff after that, but we'll ignore that for now). During these early phases, the X-ray afterglow has a spectrum that looks like a power law: flux F∝ E^β, where E is energy and beta is some number called the spectral index. This kind of spectrum is characteristic of synchrotron emission, which is produced when charged particles spiral around magnetic field lines at close to the speed of light. In addition to the outgoing forward shock that ploughs into the interstellar medium, there is also a so-called reverse shock, which propagates backward through the ejecta. In many ways," reverse" shock can be misleading; this shock is still moving outward from the restframe of the star at relativistic velocity but is ploughing backward through the ejecta in their frame and is slowing the expansion. This reverse shock can be dynamically important, as it can carry comparable energy to the forward shock. The early phases of the GRB afterglow still provide a good description even if the GRB is highly collimated since the individual emitting regions of the outflow are not in causal contact at large angles and so behave as though they are expanding isotropically. The majority of afterglows, at times typically observed, fall in the slow cooling regime, and the cooling break lies between the optical and the X-ray. Numerous observations support this broad picture for afterglows in the spectral energy distribution of the afterglow of the very bright GRB. The bluer light (optical and X-ray) appears to follow a typical synchrotron forward shock expectation (note that the apparent features in the X-ray and optical spectrum are due to the presence of dust within the host galaxy). We need more research in GRB and Particle Physics in order to unfold the mysteries of afterglow.Keywords: GRB, synchrotron, X-ray, isotropic energy
Procedia PDF Downloads 851502 Radioactivity Assessment of Sediments in Negombo Lagoon Sri Lanka
Authors: H. M. N. L. Handagiripathira
Abstract:
The distributions of naturally occurring and anthropogenic radioactive materials were determined in surface sediments taken at 27 different locations along the bank of Negombo Lagoon in Sri Lanka. Hydrographic parameters of lagoon water and the grain size analyses of the sediment samples were also carried out for this study. The conductivity of the adjacent water was varied from 13.6 mS/cm to 55.4 mS/cm near to the southern end and the northern end of the lagoon, respectively, and equally salinity levels varied from 7.2 psu to 32.1 psu. The average pH in the water was 7.6 and average water temperature was 28.7 °C. The grain size analysis emphasized the mass fractions of the samples as sand (60.9%), fine sand (30.6%) and fine silt+clay (1.3%) in the sampling locations. The surface sediment samples of wet weight, 1 kg each from upper 5-10 cm layer, were oven dried at 105 °C for 24 hours to get a constant weight, homogenized and sieved through a 2 mm sieve (IAEA technical series no. 295). The radioactivity concentrations were determined using gamma spectrometry technique. Ultra Low Background Broad Energy High Purity Ge Detector, BEGe (Model BE5030, Canberra) was used for radioactivity measurement with Canberra Industries' Laboratory Source-less Calibration Software (LabSOCS) mathematical efficiency calibration approach and Geometry composer software. The mean activity concentration was found to be 24 ± 4, 67 ± 9, 181 ± 10, 59 ± 8, 3.5 ± 0.4 and 0.47 ± 0.08 Bq/kg for 238U, 232Th, 40K, 210Pb, 235U and 137Cs respectively. The mean absorbed dose rate in air, radium equivalent activity, external hazard index, annual gonadal dose equivalent and annual effective dose equivalent were 60.8 nGy/h, 137.3 Bq/kg, 0.4, 425.3 mSv/year and 74.6 mSv/year, respectively. The results of this study will provide baseline information on the natural and artificial radioactive isotopes and environmental pollution associated with information on radiological risk.Keywords: gamma spectrometry, lagoon, radioactivity, sediments
Procedia PDF Downloads 1301501 Measurement of Radon Exhalation Rate, Natural Radioactivity, and Radiation Hazard Assessment in Soil Samples from the Surrounding Area of Kasimpur Thermal Power Plant Kasimpur (U. P.), India
Authors: Anil Sharma, Ajay Kumar Mahur, R. G. Sonkawade, A. C. Sharma, R. Prasad
Abstract:
In coal fired thermal power stations, large amount of fly ash is produced after burning of coal. Fly ash is spread and distributed in the surrounding area by air and may be deposited on the soil of the region surrounding the power plant. Coal contains increased levels of these radionuclides and fly ash may increase the radioactivity in the soil around the power plant. Radon atoms entering into the pore space from the mineral grain are transported by diffusion and advection through this space until they in turn decay or are released into the atmosphere. In the present study, Soil samples were collected from the region around a Kasimpur Thermal Power Plant, Kasimpur, Aligarh (U.P.). Radon activity, radon surface exhalation and mass exhalation rates were measured using “sealed can technique” using LR 115-type II nuclear track detectors. Radon activities vary from 92.9 to 556.8 Bq m-3 with mean value of 279.8 Bq m-3. Surface exhalation rates (EX) in these samples are found to vary from 33.4 to 200.2 mBq m-2 h-1 with an average value of 100.5 mBq m-2 h-1 whereas, Mass exhalation rates (EM) vary from 1.2 to 7.7 mBq kg-1 h-1 with an average value of 3.8 mBq kg-1 h-1. Activity concentrations of radionuclides were measured in these samples by using a low level NaI (Tl) based gamma ray spectrometer. Activity concentrations of 226Ra 232Th and 40K vary from 12 to 49 Bq kg-1, 24 to 49 Bq kg-1 and 135 to 546 Bq kg-1 with overall mean values of 30.3 Bq kg-1, 38.5 Bq kg-1 and 317.8 Bq kg-1, respectively. Radium equivalent activity has been found to vary from 80.0 to 143.7 Bq kg-1 with an average value of 109.7 Bq kg-1. Absorbed dose rate varies from 36.1 to 66.4 nGy h-1 with an average value of 50.4 nGy h-1 and corresponding outdoor annual effective dose varies from 0.044 to 0.081 mSv with an average value of 0.061 mSv. Values of external and internal hazard index Hex, Hin in this study vary from 0.21 to 0.38 and 0.27 to 0.50 with an average value of 0.29 and 0.37, Respectively. The results will be discussed in light of various factors.Keywords: natural radioactivity, radium equivalent activity, absorbed dose rate, gamma ray spectroscopy
Procedia PDF Downloads 3531500 Enhanced Retrieval-Augmented Generation (RAG) Method with Knowledge Graph and Graph Neural Network (GNN) for Automated QA Systems
Authors: Zhihao Zheng, Zhilin Wang, Linxin Liu
Abstract:
In the research of automated knowledge question-answering systems, accuracy and efficiency are critical challenges. This paper proposes a knowledge graph-enhanced Retrieval-Augmented Generation (RAG) method, combined with a Graph Neural Network (GNN) structure, to automatically determine the correctness of knowledge competition questions. First, a domain-specific knowledge graph was constructed from a large corpus of academic journal literature, with key entities and relationships extracted using Natural Language Processing (NLP) techniques. Then, the RAG method's retrieval module was expanded to simultaneously query both text databases and the knowledge graph, leveraging the GNN to further extract structured information from the knowledge graph. During answer generation, contextual information provided by the knowledge graph and GNN is incorporated to improve the accuracy and consistency of the answers. Experimental results demonstrate that the knowledge graph and GNN-enhanced RAG method perform excellently in determining the correctness of questions, achieving an accuracy rate of 95%. Particularly in cases involving ambiguity or requiring contextual information, the structured knowledge provided by the knowledge graph and GNN significantly enhances the RAG method's performance. This approach not only demonstrates significant advantages in improving the accuracy and efficiency of automated knowledge question-answering systems but also offers new directions and ideas for future research and practical applications.Keywords: knowledge graph, graph neural network, retrieval-augmented generation, NLP
Procedia PDF Downloads 191499 Optimizing Perennial Plants Image Classification by Fine-Tuning Deep Neural Networks
Authors: Khairani Binti Supyan, Fatimah Khalid, Mas Rina Mustaffa, Azreen Bin Azman, Amirul Azuani Romle
Abstract:
Perennial plant classification plays a significant role in various agricultural and environmental applications, assisting in plant identification, disease detection, and biodiversity monitoring. Nevertheless, attaining high accuracy in perennial plant image classification remains challenging due to the complex variations in plant appearance, the diverse range of environmental conditions under which images are captured, and the inherent variability in image quality stemming from various factors such as lighting conditions, camera settings, and focus. This paper proposes an adaptation approach to optimize perennial plant image classification by fine-tuning the pre-trained DNNs model. This paper explores the efficacy of fine-tuning prevalent architectures, namely VGG16, ResNet50, and InceptionV3, leveraging transfer learning to tailor the models to the specific characteristics of perennial plant datasets. A subset of the MYLPHerbs dataset consisted of 6 perennial plant species of 13481 images under various environmental conditions that were used in the experiments. Different strategies for fine-tuning, including adjusting learning rates, training set sizes, data augmentation, and architectural modifications, were investigated. The experimental outcomes underscore the effectiveness of fine-tuning deep neural networks for perennial plant image classification, with ResNet50 showcasing the highest accuracy of 99.78%. Despite ResNet50's superior performance, both VGG16 and InceptionV3 achieved commendable accuracy of 99.67% and 99.37%, respectively. The overall outcomes reaffirm the robustness of the fine-tuning approach across different deep neural network architectures, offering insights into strategies for optimizing model performance in the domain of perennial plant image classification.Keywords: perennial plants, image classification, deep neural networks, fine-tuning, transfer learning, VGG16, ResNet50, InceptionV3
Procedia PDF Downloads 491498 Using Historical Data for Stock Prediction
Authors: Sofia Stoica
Abstract:
In this paper, we use historical data to predict the stock price of a tech company. To this end, we use a dataset consisting of the stock prices in the past five years of ten major tech companies – Adobe, Amazon, Apple, Facebook, Google, Microsoft, Netflix, Oracle, Salesforce, and Tesla. We experimented with a variety of models– a linear regressor model, K nearest Neighbors (KNN), a sequential neural network – and algorithms - Multiplicative Weight Update, and AdaBoost. We found that the sequential neural network performed the best, with a testing error of 0.18%. Interestingly, the linear model performed the second best with a testing error of 0.73%. These results show that using historical data is enough to obtain high accuracies, and a simple algorithm like linear regression has a performance similar to more sophisticated models while taking less time and resources to implement.Keywords: finance, machine learning, opening price, stock market
Procedia PDF Downloads 1741497 Study of Radiation Response in Lactobacillus Species
Authors: Kanika Arora, Madhu Bala
Abstract:
The small intestine epithelium is highly sensitive and major targets of ionizing radiation. Radiation causes gastrointestinal toxicity either by direct deposition of energy or indirectly (inflammation or bystander effects) generating free radicals and reactive oxygen species. Oxidative stress generated as a result of radiation causes active inflammation within the intestinal mucosa leading to structural and functional impairment of gut epithelial barrier. As a result, there is a loss of tolerance to normal dietary antigens and commensal flora together with exaggerated response to pathogens. Dysbiosis may therefore thought to play a role in radiation enteropathy and can contribute towards radiation induced bowel toxicity. Lactobacilli residing in the gut shares a long conjoined evolutionary history with their hosts and by doing so these organisms have developed an intimate and complex symbiotic relationships. The objective behind this study was to look for the strains with varying resistance to ionizing radiation and to see whether the niche of the bacteria is playing any role in radiation resistance property of bacteria. In this study, we have isolated the Lactobacillus spp. from probiotic preparation and murine gastrointestinal tract, both of which were supposed to be the important source for its isolation. Biochemical characterization did not show a significant difference in the properties, while a significant preference was observed in carbohydrate utilization capacity by the isolates. Effect of ionizing radiations induced by Co60 gamma radiation (10 Gy) on lactobacilli cells was investigated. A cellular survival curve versus absorbed doses was determined. Radiation resistance studies showed that the response of isolates towards cobalt-60 gamma radiation differs from each other and significant decrease in survival was observed in a dose-dependent manner. Thus the present study revealed that the property of radioresistance in Lactobacillus depends upon the source from where they have been isolated.Keywords: dysbiosis, lactobacillus, mitigation, radiation
Procedia PDF Downloads 1231496 A Palmprint Identification System Based Multi-Layer Perceptron
Authors: David P. Tantua, Abdulkader Helwan
Abstract:
Biometrics has been recently used for the human identification systems using the biological traits such as the fingerprints and iris scanning. Identification systems based biometrics show great efficiency and accuracy in such human identification applications. However, these types of systems are so far based on some image processing techniques only, which may decrease the efficiency of such applications. Thus, this paper aims to develop a human palmprint identification system using multi-layer perceptron neural network which has the capability to learn using a backpropagation learning algorithms. The developed system uses images obtained from a public database available on the internet (CASIA). The processing system is as follows: image filtering using median filter, image adjustment, image skeletonizing, edge detection using canny operator to extract features, clear unwanted components of the image. The second phase is to feed those processed images into a neural network classifier which will adaptively learn and create a class for each different image. 100 different images are used for training the system. Since this is an identification system, it should be tested with the same images. Therefore, the same 100 images are used for testing it, and any image out of the training set should be unrecognized. The experimental results shows that this developed system has a great accuracy 100% and it can be implemented in real life applications.Keywords: biometrics, biological traits, multi-layer perceptron neural network, image skeletonizing, edge detection using canny operator
Procedia PDF Downloads 3641495 Mechanical Properties and Microstructure of Ultra-High Performance Concrete Containing Fly Ash and Silica Fume
Authors: Jisong Zhang, Yinghua Zhao
Abstract:
The present study investigated the mechanical properties and microstructure of Ultra-High Performance Concrete (UHPC) containing supplementary cementitious materials (SCMs), such as fly ash (FA) and silica fume (SF), and to verify the synergistic effect in the ternary system. On the basis of 30% fly ash replacement, the incorporation of either 10% SF or 20% SF show a better performance compared to the reference sample. The efficiency factor (k-value) was calculated as a synergistic effect to predict the compressive strength of UHPC with these SCMs. The SEM of micrographs and pore volume from BJH method indicate a high correlation with compressive strength. Further, an artificial neural networks model was constructed for prediction of the compressive strength of UHPC containing these SCMs.Keywords: artificial neural network, fly ash, mechanical properties, ultra-high performance concrete
Procedia PDF Downloads 402