Search results for: discrete feature vector

Authors: L. S. Chathurika

Abstract:

Early prediction of student performance is an important factor to be gained academic excellence. Whatever the study stream in secondary education, students lay the foundation for higher studies during the first year of their degree or diploma program in Sri Lanka. The information technology (IT) field has certain improvements in the education domain by selecting specialization areas to show the talents and skills of students. These specializations can be software engineering, network administration, database administration, multimedia design, etc. After completing the first-year, students attempt to select the best path by considering numerous factors. The purpose of this experiment is to predict the best study path using machine learning algorithms. Five classification algorithms: decision tree, support vector machine, artificial neural network, Naïve Bayes, and logistic regression are selected and tested. The support vector machine obtained the highest accuracy, 82.4%. Then affecting features are recognized to select the best study path.

Keywords: algorithm, classification, evaluation, features, testing, training

Procedia PDF Downloads 119

Authors: Mohammad R. Aghakashkooli, Milutin G. Jovanovic

Abstract:

The brushless doubly-fed reluctance generator (BDFRG) is an emerging, medium-speed alternative to a conventional wound rotor slip-ring doubly-fed induction generator (DFIG) in wind energy conversion systems (WECS). It can provide competitive overall performance and similar low failure rates of a typically 30% rated back-to-back power electronics converter in 2:1 speed ranges but with the following important reliability and cost advantages over DFIG: the maintenance-free operation afforded by its brushless structure, 50% synchronous speed with the same number of rotor poles (allowing the use of a more compact, and more efficient two-stage gearbox instead of a vulnerable three-stage one), and superior grid integration properties including simpler protection for the low voltage ride through compliance of the fractional converter due to the comparatively higher leakage inductances and lower fault currents. Vector controlled pulse-width-modulated converters generally feature a much lower total harmonic distortion relative to hysteresis counterparts with variable switching rates and as such have been a predominant choice for BDFRG (and DFIG) wind turbines. Eliminating a shaft position sensor, which is often required for control implementation in this case, would be desirable to address the associated reliability issues. This fact has largely motivated the recent growing research of sensorless methods and developments of various rotor position and/or speed estimation techniques for this purpose. The main limitation of all the observer-based control approaches for grid-connected wind power applications of the BDFRG reported in the open literature is the requirement for pre-commissioning procedures and prior knowledge of the machine inductances, which are usually difficult to accurately identify by off-line testing. A model reference adaptive system (MRAS) based sensor-less vector control scheme to be presented will overcome this shortcoming. The true machine parameter independence of the proposed field-oriented algorithm, offering robust, inherently decoupled real and reactive power control of the grid-connected winding, is achieved by on-line estimation of the inductance ratio, the underlying rotor angular velocity and position MRAS observer being reliant upon. Such an observer configuration will be more practical to implement and clearly preferable to the existing machine parameter dependent solutions, and especially bearing in mind that with very little modifications it can be adapted for commercial DFIGs with immediately obvious further industrial benefits and prospects of this work. The excellent encoder-less controller performance with maximum power point tracking in the base speed region will be demonstrated by realistic simulation studies using large-scale BDFRG design data and verified by experimental results on a small laboratory prototype of the WECS emulation facility.

Keywords: brushless doubly fed reluctance generator, model reference adaptive system, sensorless vector control, wind energy conversion

Procedia PDF Downloads 62

Authors: S. Saju, G. Thirugnanam

Abstract:

In this paper, a medical image watermarking algorithm based on contourlet is proposed. Medical image watermarking is a special subcategory of image watermarking in the sense that images have special requirements. Watermarked medical images should not differ perceptually from their original counterparts because clinical reading of images must not be affected. Watermarking techniques based on wavelet transform are reported in many literatures but robustness and security using contourlet are better when compared to wavelet transform. The main challenge in exploring geometry in images comes from the discrete nature of the data. In this paper, original image is decomposed to two level using contourlet and the watermark is embedded in the resultant sub-bands. Sub-band selection is based on the value of Peak Signal to Noise Ratio (PSNR) that is calculated between watermarked and original image. To extract the watermark, Kernel ICA is used and it has a novel characteristic is that it does not require the transformation process to extract the watermark. Simulation results show that proposed scheme is robust against attacks such as Salt and Pepper noise, Median filtering and rotation. The performance measures like PSNR and Similarity measure are evaluated and compared with Discrete Wavelet Transform (DWT) to prove the robustness of the scheme. Simulations are carried out using Matlab Software.

Keywords: digital watermarking, independent component analysis, wavelet transform, contourlet

Procedia PDF Downloads 529

Authors: Jaehyug Lee, Tae-Ho Song

Abstract:

Vacuum insulation panel (VIP) can achieve very low thermal conductivity by evacuating its inner space. Heat transfer in the core materials of highly-evacuated VIP occurs by conduction through the solid structure and radiation through the pore. The effect of various scattering modes in combined conduction-radiation in VIP is investigated through numerical analysis. The discrete ordinates interpolation method (DOIM) incorporated with the commercial code FLUENT® is employed. It is found that backward scattering is more effective in reducing the total heat transfer while isotropic scattering is almost identical with pure absorbing/emitting case of the same optical thickness. For a purely scattering medium, the results agree well with additive solution with diffusion approximation, while a modified term is added in the effect of optical thickness to backward scattering is employed. For other scattering phase functions, it is also confirmed that backwardly scattering phase function gives a lower effective thermal conductivity. Thus, the materials with backward scattering properties, with radiation shields are desirable to lower the thermal conductivity of VIPs.

Keywords: combined conduction and radiation, discrete ordinates interpolation method, scattering phase function, vacuum insulation panel

Procedia PDF Downloads 366

Authors: Belaynesh Chekol, Numan Çelebi

Abstract:

The main purpose of this work is to recognize individual characters extracted from natural scene images using scale invariant feature transform (SIFT) features as an input to K-nearest neighbor (KNN); a classification learner algorithm. For this task, 1,068 and 78 images of English alphabet characters taken from Chars74k data set is used to train and test the classifier respectively. For each character image, We have generated describing features by using SIFT algorithm. This set of features is fed to the learner so that it can recognize and label new images of English characters. Two types of KNN (fine KNN and weighted KNN) were trained and the resulted classification accuracy is 56.9% and 56.5% respectively. The training time taken was the same for both fine and weighted KNN.

Keywords: character recognition, KNN, natural scene image, SIFT

Procedia PDF Downloads 281

Authors: Arth Bohra, Marwa Mahmoud

Abstract:

In this paper, we utilize computer vision to develop a tool for youth coaches to formulate set-piece tactics for their players. We used the Soccernet database to extract the ResNet features and camera calibration data for over 3000 corner kick across 500 professional matches in the top 6 European leagues (English Premier League, UEFA Champions League, Ligue 1, La Liga, Serie A, Bundesliga). Leveraging the provided homography matrix, we construct a feature vector representing the formation of players on these corner kicks. Additionally, labeling the videos manually, we obtained the pass-trajectory of each of the 3000+ corner kicks by segmenting the field into four zones. Next, after determining the localization of the players and ball, we used event data to give the corner kicks a rating on a 1-4 scale. By employing a Convolutional Neural Network, our model managed to predict the success of a corner kick given the formations of players. This suggests that with the right formations, teams can optimize the way they approach corner kicks. By understanding this, we can help coaches formulate set-piece tactics for their own teams in order to maximize the success of their play. The proposed model can be easily extended; our method could be applied to even more game situations, from free kicks to counterattacks. This research project also gives insight into the myriad of possibilities that artificial intelligence possesses in transforming the domain of sports.

Keywords: soccer, corner kicks, AI, computer vision

Procedia PDF Downloads 176

Authors: Godfrey Nsereko, Daniel Kadobera, Denis Okethwangu, Joyce Nguna, Alex Riolexus Ario

Abstract:

Background: Malaria is a leading cause of morbidity and mortality in Uganda. In April 2018, malaria cases surged in Nwoya District, northern Uganda, exceeding the action thresholds. We investigated to assess the outbreak’s magnitude, identify transmission risk factors, and recommend evidence-based control measures. Methods: We defined a malaria case as onset of fever in a resident of Nwoya District with a positive Rapid Diagnostic Test or microscopy for malaria P. falciparum from 1 February to 22 May 2018. We reviewed medical records in all health facilities of affected sub-counties to find cases. In a case-control study, we compared exposure risk factors between 107 case-persons and 107 asymptomatic controls matched by age and village. We conducted entomological assessment on vector-density and behavior. Results: We identified 3,879 case-persons (attack rate [AR]=6.5%) and 2 deaths (case-fatality rate=5.2/10,000). Females (AR=8.1%) were more affected than males (AR=4.7%). Of all age groups, the 5-18 year age group (AR=8.4%) was most affected. Heavy rain started on 4 March; a propagated outbreak began during the week of 2 April. In the case-control study, 55% (59/107) of case-patients and 18% (19/107) of controls had stagnant water around households for several days following rainfall (ORM-H=5.6, 95%CI=3.0-11); 25% (27/107) of case-patients and 51% (55/107) of controls wore long-sleeve cloths during evening hours (ORM-H=0.30, 95%CI=0.20-0.60); 29% (31/107) of case-patients and 15% (16/107) of controls did not sleep under a long-lasting insecticide-treated net (LLIN) (ORM-H=2.3, 95%CI=1.1-4.9); 37% (40/107) of case-patients and 52% (56/107) of controls had ≥1 LLIN per 2 household members (ORM-H=0.54, 95%CI=0.30-0.97). Entomological assessment indicated active breeding sites; Anopheles gambiae sensu lato species were the predominant vector. Conclusion: Increased vector breeding sites after heavy rainfall, together with inadequate malaria preventive measures caused this outbreak. We recommended increasing coverage for LLINs and larviciding breeding sites.

Keywords: malaria outbreak, Plasmodium falciparum, global health security, Uganda

Procedia PDF Downloads 226

Authors: A. Degale Desta, Cheng Jian

Abstract:

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

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

Procedia PDF Downloads 165

Authors: Nitin Shravan, Sudarsun Santhiappan, B. Sivaselvan

Abstract:

Subsection identification, in the context of Electronic Health Records (EHRs), is identifying the important sections for down-stream tasks like auto-coding. In this work, we classify the text present in EHRs according to their information, using machine learning and deep learning techniques. We initially describe briefly about the problem and formulate it as a text classification problem. Then, we discuss upon the methods from the literature. We try two approaches - traditional feature extraction based machine learning methods and deep learning methods. Through experiments on a private dataset, we establish that the deep learning methods perform better than the feature extraction based Machine Learning Models.

Keywords: deep learning, machine learning, semantic clinical classification, subsection identification, text classification

Procedia PDF Downloads 220

Authors: Amber Jamal, Imran Siddiqui, Syed Tanveer Iqbal

Abstract:

This review is aimed to shed some light on problems constructing a theory of spacetime and geometry in terms of all quantum degrees of freedom called ‘Quantum Gravity’. Such a theory, which is effective at all scales of distances and energies, describes the enigma of the beginning of the Universe, its possible end, and reducing to general relativity at large distances but in a semi-classical approximation. Furthermore, the theory of quantum gravity also describes the Universe as a whole and provides a description of most fundamental questions that have puzzled scientists for decades, such as: what is space, what is time, and what is the fundamental structure of the Universe, is the spacetime discrete, if it is, where does the continuum of spacetime come from at low energies and macroscopic scales and where does it emerge from its fundamentally discrete building blocks? Quantum Field Theory (QFT) is a framework which describes the microscopic properties and dynamics of the basic building blocks of any condensed matter system. In QFT, atoms are quanta of continuous fields. At smaller scales or higher energies, the continuum description of spacetime fails. Therefore, a new description is required in terms of microscopic constituents (atoms or molecules). The objective of this scientific endeavor is to discuss the above-mentioned problems rigorously and to discuss possible way-out of the problems.

Keywords: QFT, quantum degrees of freedom, quantum gravity, semi-classical approximation

Procedia PDF Downloads 122

Authors: Emmanuel Osaze Oshoiribhor, Adetokunbo MacGregor John-Otumu

Abstract:

In recent years, there has been a desire to forecast student academic achievement prior to graduation. This is to help them improve their grades, particularly for individuals with poor performance. The goal of this study is to employ supervised learning techniques to construct a predictive model for student academic achievement. Many academics have already constructed models that predict student academic achievement based on factors such as smoking, demography, culture, social media, parent educational background, parent finances, and family background, to name a few. This feature and the model employed may not have correctly classified the students in terms of their academic performance. This model is built using a logistic regression classifier with basic features such as the previous semester's course score, attendance to class, class participation, and the total number of course materials or resources the student is able to cover per semester as a prerequisite to predict if the student will perform well in future on related courses. The model outperformed other classifiers such as Naive bayes, Support vector machine (SVM), Decision Tree, Random forest, and Adaboost, returning a 96.7% accuracy. This model is available as a desktop application, allowing both instructors and students to benefit from user-friendly interfaces for predicting student academic achievement. As a result, it is recommended that both students and professors use this tool to better forecast outcomes.

Keywords: artificial intelligence, ML, logistic regression, performance, prediction

Procedia PDF Downloads 98

Authors: Syeda Mainaaz Unnisa, Deepa Suresh

Abstract:

Due to the increase in usage of public domain channels, such as the internet, and communication technology, there is a concern about the protection of intellectual property and security threats. This interest has led to growth in researching and implementing techniques for information hiding. Steganography is the art and science of hiding information in a private manner such that its existence cannot be recognized. Communication using steganographic techniques makes not only the secret message but also the presence of hidden communication, invisible. Steganalysis is the art of detecting the presence of this hidden communication. Parallel to steganography, steganalysis is also gaining prominence, since the detection of hidden messages can prevent catastrophic security incidents from occurring. Steganalysis can also be incredibly helpful in identifying and revealing holes with the current steganographic techniques, which makes them vulnerable to attacks. Through the formulation of new effective steganalysis methods, further research to improve the resistance of tested steganography techniques can be developed. Feature-based steganalysis method for JPEG images calculates the features of an image using the L1 norm of the difference between a stego image and the calibrated version of the image. This calibration can help retrieve some of the parameters of the cover image, revealing the variations between the cover and stego image and enabling a more accurate detection. Applying this method to various steganographic schemes, experimental results were compared and evaluated to derive conclusions and principles for more protected JPEG steganography.

Keywords: cover image, feature-based steganalysis, information hiding, steganalysis, steganography

Procedia PDF Downloads 217

Authors: Alexandra Tucaliuc, Alexandra C. Blaga, Anca I. Galaction, Lenuta Kloetzer, Dan Cascaval

Abstract:

Ergosterol (ergosta-5,7,22-trien-3β-ol), also known as provitamin D2, is the precursor of vitamin D2 (ergocalciferol), because it is converted under UV radiation to this vitamin. The natural sources of ergosterol are mainly the yeasts (Saccharomyces sp., Candida sp.), but it can be also found in fungus (Claviceps sp.) or plants (orchids). In the yeasts cells, ergosterol is accumulated in membranes, especially in free form in the plasma membrane, but also as esters with fatty acids in membrane lipids. The chemical synthesis of ergosterol does not represent an efficient method for its production, in these circumstances, the most attractive alternative for producing ergosterol at larger-scale remains the aerobic fermentation using S. cerevisiae on glucose or by-products from agriculture of food industry as substrates, in batch or fed-batch operating systems. The aim of this work is to analyze comparatively the influence of aeration efficiency on ergosterol production by S. cerevisiae in batch and fed-batch fermentations, by considering different levels of mixing intensity, aeration rate, and n-dodecane concentration. The effects of the studied factors are quantitatively described by means of the mathematical correlations proposed for each of the two fermentation systems, valid both for the absence and presence of oxygen-vector inside the broth. The experiments were carried out in a laboratory stirred bioreactor, provided with computer-controlled and recorded parameters. n-Dodecane was used as oxygen-vector and the ergosterol content inside the yeasts cells has been considered at the fermentation moment related to the maximum concentration of ergosterol, 9 hrs for batch process and 20 hrs for fed-batch one. Ergosterol biosynthesis is strongly dependent on the dissolved oxygen concentration. The hydrocarbon concentration exhibits a significant influence on ergosterol production mainly by accelerating the oxygen transfer rate. Regardless of n-dodecane addition, by maintaining the glucose concentration at a constant level in the fed-batch process, the amount of ergosterol accumulated into the yeasts cells has been almost tripled. In the presence of hydrocarbon, the ergosterol concentration increased by over 50%. The value of oxygen-vector concentration corresponding to the maximum level of ergosterol depends mainly on biomass concentration, due to its negative influences on broth viscosity and interfacial phenomena of air bubbles blockage through the adsorption of hydrocarbon droplets–yeast cells associations. Therefore, for the batch process, the maximum ergosterol amount was reached for 5% vol. n-dodecane, while for the fed-batch process for 10% vol. hydrocarbon.

Keywords: bioreactors, ergosterol, fermentation, oxygen-vector

Procedia PDF Downloads 190

Authors: Nalini C. Iyer, Shraddha H., Anagha B. Varahamurthy, Dikshith C. S., Ishwar G. Kubasad, Vinayak I. Karalatti, Pavan B. Mulimani

Abstract:

The current scenario of the pandemic due to COVID-19 has led to the awareness among the people to avoid unneces-sary contact in public places. There is a need to avoid contact with physical objects to stop the spreading of infection. The contactless feature has to be included in the systems in public places wherever possible. For example, attendance monitoring systems with fingerprint biometric can be replaced with a contactless feature. One more important protocol followed in the current situation is temperature monitoring and screening. The paper describes an attendance system with a contactless feature and temperature screening for the university. The system displays a QR code to scan, which redirects to the student login web page only if the location is valid (the location where the student scans the QR code should be the location of the display of the QR code). Once the student logs in, the temperature of the student is scanned by the contactless temperature sensor (mlx90614) with an error of 0.5°C. If the temperature falls in the range of the desired value (range of normal body temperature), then the attendance of the student is marked as present, stored in the database, and the door opens automatically. The attendance is marked as absent in the other case, alerted with the display of temperature, and the door remains closed. The door is automated with the help of a servomotor. To avoid the proxy, IR sensors are used to count the number of students in the classroom. The hardware system consisting of a contactless temperature sensor and IR sensor is implemented on the microcontroller, NodeMCU.

Keywords: NodeMCU, IR sensor, attendance monitoring, contactless, temperature

Procedia PDF Downloads 188

Authors: Kilari Nikhil, Ankur Tibrewal, Srinivas Kruthiventi S. S.

Abstract:

Conventional speaker identification systems often fall short of capturing the diverse variations present in speech data due to fixed-scale architectures. In this research, we propose a CNN-based architecture, USENet, designed to overcome these limitations. Leveraging two key techniques, our approach achieves superior performance on the VoxCeleb 1 Dataset without any pre-training. Firstly, we adopt a U-net-inspired design to extract features at multiple scales, empowering our model to capture speech characteristics effectively. Secondly, we introduce the squeeze and excitation block to enhance spatial feature learning. The proposed architecture showcases significant advancements in speaker identification, outperforming existing methods, and holds promise for future research in this domain.

Keywords: multi-scale feature extraction, squeeze and excitation, VoxCeleb1 speaker identification, mel-spectrograms, USENet

Procedia PDF Downloads 74

Authors: Olena Grygorieva

Abstract:

Nowadays mechanisms of thymocytes emigration from the thymus to the periphery are investigated actively. We have proposed a hypothesis of thymocytes’ migration from the thymus through lymphatic vessels during periodical short-term local edema. By morphological, hystochemical methods we have examined quantity of lymphocytes, epitelioreticulocytes, mast cells, blood and lymphatic vessels in morpho-functional areas of rats’ thymuses during the first week after birth in 4 hours interval. In newborn and beginning from 8 hour after birth every 12 hours specific density of the thymus, absolute quantity of microcirculatory vessels, especially of lymphatic ones, lymphcyte-epithelial index, quantity of mast cells and their degranulative forms increase. Structure of extracellular matrix, intrathymical microenvironment and lymphocytes’ adhesive properties change. Absolute quantity of small lymphocytes in thymic cortex changes wavy. All these changes are straightly expressed from 0 till 2, from 12 till 16, from 108 till 120 hours of postnatal life. During this periods paravasal lymphatic vessels are stuffed with lymphocytes, i.e. discrete migration of lymphocytes from the thymus occurs. After rapid edema reduction, quantity of lymphatic vessels decrease, they become empty. Therefore, in the thymus of newborn periodical short-term local edema is observed, on its top discrete migration of lymphocytes from the thymus occurs.

Keywords: lymphocytes, lymphatic vessels, mast cells, thymus

Procedia PDF Downloads 227

Authors: Matthew Baucum

Abstract:

With the increasing popularity of fMRI as an experimental method, psychology and neuroscience can greatly benefit from advanced techniques for summarizing and synthesizing large amounts of data from brain imaging studies. One promising avenue is automated meta-analyses, in which natural language processing methods are used to identify the brain regions consistently associated with certain semantic concepts (e.g. “social”, “reward’) across large corpora of studies. This study builds on this approach by demonstrating how, in fMRI meta-analyses, individual voxels can be treated as vectors in a semantic space and evaluated for their “proximity” to terms of interest. In this technique, a low-dimensional semantic space is built from brain imaging study texts, allowing words in each text to be represented as vectors (where words that frequently appear together are near each other in the semantic space). Consequently, each voxel in a brain mask can be represented as a normalized vector sum of all of the words in the studies that showed activation in that voxel. The entire brain mask can then be visualized in terms of each voxel’s proximity to a given term of interest (e.g., “vision”, “decision making”) or collection of terms (e.g., “theory of mind”, “social”, “agent”), as measured by the cosine similarity between the voxel’s vector and the term vector (or the average of multiple term vectors). Analysis can also proceed in the opposite direction, allowing word cloud visualizations of the nearest semantic neighbors for a given brain region. This approach allows for continuous, fine-grained metrics of voxel-term associations, and relies on state-of-the-art “open vocabulary” methods that go beyond mere word-counts. An analysis of over 11,000 neuroimaging studies from an existing meta-analytic fMRI database demonstrates that this technique can be used to recover known neural bases for multiple psychological functions, suggesting this method’s utility for efficient, high-level meta-analyses of localized brain function. While automated text analytic methods are no replacement for deliberate, manual meta-analyses, they seem to show promise for the efficient aggregation of large bodies of scientific knowledge, at least on a relatively general level.

Keywords: FMRI, machine learning, meta-analysis, text analysis

Procedia PDF Downloads 450

Authors: Kun Xu, Yuan Xu, Jia Qiao

Abstract:

The document detection plays an important role in optical character recognition and text analysis. Because the traditional detection methods have weak generalization ability, and deep neural network has complex structure and large number of parameters, which cannot be well applied in mobile devices, this paper proposes a lightweight Document Corner Detection Network (DCDNet). DCDNet is a two-stage architecture. The first stage with Encoder-Decoder structure adopts depthwise separable convolution to greatly reduce the network parameters. After introducing the Feature Attention Union (FAU) module, the second stage enhances the feature information of spatial and channel dim and adaptively adjusts the size of receptive field to enhance the feature expression ability of the model. Aiming at solving the problem of the large difference in the number of pixel distribution between corner and non-corner, Weighted Binary Cross Entropy Loss (WBCE Loss) is proposed to define corner detection problem as a classification problem to make the training process more efficient. In order to make up for the lack of Dataset of document corner detection, a Dataset containing 6620 images named Document Corner Detection Dataset (DCDD) is made. Experimental results show that the proposed method can obtain fast, stable and accurate detection results on DCDD.

Keywords: document detection, corner detection, attention mechanism, lightweight

Procedia PDF Downloads 354

Authors: Paolo Sassi, Jorge Freiria, Gabriel Usera

Abstract:

In this work, a finite volume fluid flow solver is coupled with a discrete element method module for the simulation of the dynamics of free and elastic bodies in interaction with the fluid and between themselves. The open source fluid flow solver, caffa3d.MBRi, includes the capability to work with nested overlapping grids in order to easily refine the grid in the region where the bodies are moving. To do so, it is necessary to implement a recognition function able to identify the specific mesh block in which the device is moving in. The set of overlapping finer grids might be displaced along with the set of bodies being simulated. The interaction between the bodies and the fluid is computed through a two-way coupling. The velocity field of the fluid is first interpolated to determine the drag force on each object. After solving the objects displacements, subject to the elastic bonding among them, the force is applied back onto the fluid through a Gaussian smoothing considering the cells near the position of each object. The fishnet is represented as lumped masses connected by elastic lines. The internal forces are derived from the elasticity of these lines, and the external forces are due to drag, gravity, buoyancy and the load acting on each element of the system. When solving the ordinary differential equations system, that represents the motion of the elastic and flexible bodies, it was found that the Runge Kutta solver of fourth order is the best tool in terms of performance, but requires a finer grid than the fluid solver to make the system converge, which demands greater computing power. The coupled solver is demonstrated by simulating the interaction between the fluid, an elastic fishnet and a set of free bodies being captured by the net as they are dragged by the fluid. The deformation of the net, as well as the wake produced in the fluid stream are well captured by the method, without requiring the fluid solver mesh to adapt for the evolving geometry. Application of the same strategy to the simulation of elastic structures subject to the action of wind is also possible with the method presented, and one such application is currently under development.

Keywords: computational fluid dynamics, discrete element method, fishnets, nested overlapping grids

Procedia PDF Downloads 417

Authors: Benghenia Hadj Abd El Kader

Abstract:

Sleep apnea events as obstructive, central, mixed or hypopnea are characterized by frequent breathing cessations or reduction in upper airflow during sleep. An advanced method for analyzing the patterning of biomedical signals to recognize obstructive sleep apnea and hypopnea is presented. In the aim to extract characteristic parameters, which will be used for classifying the above stated (obstructive, central, mixed) sleep apnea and hypopnea, the proposed method is based first on the analysis of polysomnography signals such as electrocardiogram signal (ECG) and electromyogram (EMG), then classification of the (obstructive, central, mixed) sleep apnea and hypopnea. The analysis is carried out using the wavelet transform technique in order to extract characteristic parameters whereas classification is carried out by applying the SVM (support vector machine) technique. The obtained results show good recognition rates using characteristic parameters.

Keywords: obstructive, central, mixed, sleep apnea, hypopnea, ECG, EMG, wavelet transform, SVM classifier

Procedia PDF Downloads 371

Authors: E. Ghasemi Ardi, K. J. Dong, A. B. Yu, R. Y. Yang

Abstract:

In current work, a numerical model based on the discrete element method (DEM) was developed which provided information about particle dynamic and impact event condition inside a laboratory scale impact mill (Fritsch). It showed that each particle mostly experiences three impacts inside the mill. While the first impact frequently happens at front surface of the rotor’s rib, the frequent location of the second impact is side surfaces of the rotor’s rib. It was also showed that while the first impact happens at small impact angle mostly varying around 35º, the second impact happens at around 70º which is close to normal impact condition. Also analyzing impact energy revealed that varying mill speed from 6000 to 14000 rpm, the ratio of first impact’s average impact energy and minimum required energy to break particle (Wₘᵢₙ) increased from 0.30 to 0.85. Moreover, it was seen that second impact poses intense impact energy on particle which can be considered as the main cause of particle splitting. Finally, obtained information from DEM simulation along with obtained data from conducted experiments was implemented in semi-empirical equations in order to find selection and breakage functions. Then, using a back-calculation approach, those parameters were used to predict the PSDs of ground particles under different impact energies. Results were compared with experiment results and showed reasonable accuracy and prediction ability.

Keywords: single particle breakage, particle dynamic, population balance model, particle size distribution, discrete element method

Procedia PDF Downloads 291

Authors: Ceren Kaya, Okan Erkaymaz, Orhan Ayar, Mahmut Özer

Abstract:

Diabetes Mellitus (Diabetes) is a disease based on insulin hormone disorders and causes high blood glucose. Clinical findings determine that diabetes can be diagnosed by electrophysiological signals obtained from the vital organs. 'Diabetic Retinopathy' is one of the most common eye diseases resulting on diabetes and it is the leading cause of vision loss due to structural alteration of the retinal layer vessels. In this study, features of horizontal and vertical Video-Oculography (VOG) signals have been used to classify non-proliferative and proliferative diabetic retinopathy disease. Twenty-five features are acquired by using discrete wavelet transform with VOG signals which are taken from 21 subjects. Two models, based on multi-layer perceptron and radial basis function, are recommended in the diagnosis of Diabetic Retinopathy. The proposed models also can detect level of the disease. We show comparative classification performance of the proposed models. Our results show that proposed the RBF model (100%) results in better classification performance than the MLP model (94%).

Keywords: diabetic retinopathy, discrete wavelet transform, multi-layer perceptron, radial basis function, video-oculography (VOG)

Procedia PDF Downloads 260

Authors: Jingting Luo, Yong Wang, Ying Wang

Abstract:

Pedestrian detection in image or video data is a very important and challenging task in security surveillance. The difficulty of this task is to locate and detect pedestrians of different scales in complex scenes accurately. To solve these problems, a deep neural network (RT-YOLOv3) is proposed to realize real-time pedestrian detection at different scales in security monitoring. RT-YOLOv3 improves the traditional YOLOv3 algorithm. Firstly, the deep residual network is added to extract vehicle features. Then six convolutional neural networks with different scales are designed and fused with the corresponding scale feature maps in the residual network to form the final feature pyramid to perform pedestrian detection tasks. This method can better characterize pedestrians. In order to further improve the accuracy and generalization ability of the model, a hybrid pedestrian data set training method is used to extract pedestrian data from the VOC data set and train with the INRIA pedestrian data set. Experiments show that the proposed RT-YOLOv3 method achieves 93.57% accuracy of mAP (mean average precision) and 46.52f/s (number of frames per second). In terms of accuracy, RT-YOLOv3 performs better than Fast R-CNN, Faster R-CNN, YOLO, SSD, YOLOv2, and YOLOv3. This method reduces the missed detection rate and false detection rate, improves the positioning accuracy, and meets the requirements of real-time detection of pedestrian objects.

Keywords: pedestrian detection, feature detection, convolutional neural network, real-time detection, YOLOv3

Procedia PDF Downloads 143

Authors: Amine Ben Slama, Aymen Mouelhi, Sondes Manoubi, Chiraz Mbarek, Hedi Trabelsi, Mounir Sayadi, Farhat Fnaiech

Abstract:

Vertigo is a sensation of feeling off balance; the cause of this symptom is very difficult to interpret and needs a complementary exam. Generally, vertigo is caused by an ear problem. Some of the most common causes include: benign paroxysmal positional vertigo (BPPV), Meniere's disease and vestibular neuritis (VN). In clinical practice, different tests of videonystagmographic (VNG) technique are used to detect the presence of vestibular neuritis (VN). The topographical diagnosis of this disease presents a large diversity in its characteristics that confirm a mixture of problems for usual etiological analysis methods. In this study, a vestibular neuritis analysis method is proposed with videonystagmography (VNG) applications using an estimation of pupil movements in the case of an uncontrolled motion to obtain an efficient and reliable diagnosis results. First, an estimation of the pupil displacement vectors using with Hough Transform (HT) is performed to approximate the location of pupil region. Then, temporal and frequency features are computed from the rotation angle variation of the pupil motion. Finally, optimized features are selected using Fisher criterion evaluation for discrimination and classification of the VN disease.Experimental results are analyzed using two categories: normal and pathologic. By classifying the reduced features using the Support Vector Machine (SVM), 94% is achieved as classification accuracy. Compared to recent studies, the proposed expert system is extremely helpful and highly effective to resolve the problem of VNG analysis and provide an accurate diagnostic for medical devices.

Keywords: nystagmus, vestibular neuritis, videonystagmographic system, VNG, Fisher criterion, support vector machine, SVM

Procedia PDF Downloads 139

Authors: Sokkhey Phauk, Takeo Okazaki

Abstract:

The challenging task in educational institutions is to maximize the high performance of students and minimize the failure rate of poor-performing students. An effective method to leverage this task is to know student learning patterns with highly influencing factors and get an early prediction of student learning outcomes at the timely stage for setting up policies for improvement. Educational data mining (EDM) is an emerging disciplinary field of data mining, statistics, and machine learning concerned with extracting useful knowledge and information for the sake of improvement and development in the education environment. The study is of this work is to propose techniques in EDM and integrate it into a web-based system for predicting poor-performing students. A comparative study of prediction models is conducted. Subsequently, high performing models are developed to get higher performance. The hybrid random forest (Hybrid RF) produces the most successful classification. For the context of intervention and improving the learning outcomes, a feature selection method MICHI, which is the combination of mutual information (MI) and chi-square (CHI) algorithms based on the ranked feature scores, is introduced to select a dominant feature set that improves the performance of prediction and uses the obtained dominant set as information for intervention. By using the proposed techniques of EDM, an academic performance prediction system (APPS) is subsequently developed for educational stockholders to get an early prediction of student learning outcomes for timely intervention. Experimental outcomes and evaluation surveys report the effectiveness and usefulness of the developed system. The system is used to help educational stakeholders and related individuals for intervening and improving student performance.

Keywords: academic performance prediction system, educational data mining, dominant factors, feature selection method, prediction model, student performance

Procedia PDF Downloads 107

Authors: Youngjae Jin, Daeshik Kim

Abstract:

This paper describes a cycle accurate simulation results of weight values learned by an auto-encoder behavior model in terms of pre-route simulation. Given the results we visualized the first layer representations with natural images. Many common deep learning threads have focused on learning high-level abstraction of unlabeled raw data by unsupervised feature learning. However, in the process of handling such a huge amount of data, the learning method’s computation complexity and time limited advanced research. These limitations came from the fact these algorithms were computed by using only single core CPUs. For this reason, parallel-based hardware, FPGAs, was seen as a possible solution to overcome these limitations. We adopted and simulated the ready-made auto-encoder to design a behavior model in Verilog HDL before designing hardware. With the auto-encoder behavior model pre-route simulation, we obtained the cycle accurate results of the parameter of each hidden layer by using MODELSIM. The cycle accurate results are very important factor in designing a parallel-based digital hardware. Finally this paper shows an appropriate operation of behavior model based pre-route simulation. Moreover, we visualized learning latent representations of the first hidden layer with Kyoto natural image dataset.

Keywords: auto-encoder, behavior model simulation, digital hardware design, pre-route simulation, Unsupervised feature learning

Procedia PDF Downloads 447

Authors: P. L. D. N. M. de Silva, S. G. Edirisinghe, R. Weerasuriya

Abstract:

High peak-to-average power ratio (PAPR) is a concern of orthogonal frequency division multiplexing (OFDM) based visible light communication (VLC) systems. Discrete Fourier Transform spread (DFT-s) OFDM is an alternative single carrier modulation scheme which would address this concern. Employing channel coding techniques is another mechanism to reduce the PAPR. Previous research has been conducted to study the impact of these techniques separately. However, to the best of the knowledge of the authors, no study has been done so far to identify the improvement which can be harnessed by hybridizing these two techniques for VLC systems. Therefore, this is a novel study area under this research. In addition, channel coding techniques such as Polar codes and Turbo codes have been tested in the VLC domain. However, other efficient techniques such as Hamming coding and Convolutional coding have not been studied too. Therefore, the authors present the impact of the hybrid of DFT-s OFDM and Channel coding (Hamming coding and Convolutional coding) on PAPR in VLC systems using Matlab simulations.

Keywords: convolutional coding, discrete Fourier transform spread orthogonal frequency division multiplexing, hamming coding, peak-to-average power ratio, visible light communications

Procedia PDF Downloads 154

Authors: Asad Abbas, Muhammad Fezan Afzal, Muhammad Latif Anjum, Muhammad Azmat

Abstract:

The Internet of Things (IoT) is used to link up real objects that use the internet to interact. IoT applications allow handling and operating the equipment in accordance with environmental needs, such as transportation and healthcare. IoT devices are linked together via a number of agents that act as a middleman for communications. The operation of a heat sensor differs indoors and outside because agent applications work with environmental variables. In this article, we suggest using Software Product Line (SPL) to model IoT agents and applications' features on an XML-based basis. The contextual diversity within the same domain of application can be handled, and the reusability of features is increased by XML-based feature modelling. For the purpose of managing contextual variability, we have embraced XML for modelling IoT applications, agents, and internet-connected devices.

Keywords: IoT agents, IoT applications, software product line, feature model, XML

Procedia PDF Downloads 95

Authors: Rachid Belhachemi, Pierre Rostan, Alexandra Rostan

Abstract:

This paper develops a discrete-time option pricing model for index options. The model consists of two key ingredients. First, daily stock return innovations are driven by a continuous hidden threshold mixed skew-normal (HTSN) distribution which generates conditional non-normality that is needed to fit daily index return. The most important feature of the HTSN is the inclusion of a latent state variable with a continuum of states, unlike the traditional mixture distributions where the state variable is discrete with little number of states. The HTSN distribution belongs to the class of univariate probability distributions where parameters of the distribution capture the dependence between the variable of interest and the continuous latent state variable (the regime). The distribution has an interpretation in terms of a mixture distribution with time-varying mixing probabilities. It has been shown empirically that this distribution outperforms its main competitor, the mixed normal (MN) distribution, in terms of capturing the stylized facts known for stock returns, namely, volatility clustering, leverage effect, skewness, kurtosis and regime dependence. Second, heteroscedasticity in the model is captured by a threeexogenous-factor GARCH model (GARCHX), where the factors are taken from the principal components analysis of various world indices and presents an application to option pricing. The factors of the GARCHX model are extracted from a matrix of world indices applying principal component analysis (PCA). The empirically determined factors are uncorrelated and represent truly different common components driving the returns. Both factors and the eight parameters inherent to the HTSN distribution aim at capturing the impact of the state of the economy on price levels since distribution parameters have economic interpretations in terms of conditional volatilities and correlations of the returns with the hidden continuous state. The PCA identifies statistically independent factors affecting the random evolution of a given pool of assets -in our paper a pool of international stock indices- and sorting them by order of relative importance. The PCA computes a historical cross asset covariance matrix and identifies principal components representing independent factors. In our paper, factors are used to calibrate the HTSN-GARCHX model and are ultimately responsible for the nature of the distribution of random variables being generated. We benchmark our model to the MN-GARCHX model following the same PCA methodology and the standard Black-Scholes model. We show that our model outperforms the benchmark in terms of RMSE in dollar losses for put and call options, which in turn outperforms the analytical Black-Scholes by capturing the stylized facts known for index returns, namely, volatility clustering, leverage effect, skewness, kurtosis and regime dependence.

Keywords: continuous hidden threshold, factor models, GARCHX models, option pricing, risk-premium

Procedia PDF Downloads 297

Authors: Deeman Yousif Mahmood, Mohammed Abdullah Hussein

Abstract:

The goal of a network-based intrusion detection system is to classify activities of network traffics into two major categories: normal and attack (intrusive) activities. Nowadays, data mining and machine learning plays an important role in many sciences; including intrusion detection system (IDS) using both supervised and unsupervised techniques. However, one of the essential steps of data mining is feature selection that helps in improving the efficiency, performance and prediction rate of proposed approach. This paper applies unsupervised K-means clustering algorithm with information gain (IG) for feature selection and reduction to build a network intrusion detection system. For our experimental analysis, we have used the new NSL-KDD dataset, which is a modified dataset for KDDCup 1999 intrusion detection benchmark dataset. With a split of 60.0% for the training set and the remainder for the testing set, a 2 class classifications have been implemented (Normal, Attack). Weka framework which is a java based open source software consists of a collection of machine learning algorithms for data mining tasks has been used in the testing process. The experimental results show that the proposed approach is very accurate with low false positive rate and high true positive rate and it takes less learning time in comparison with using the full features of the dataset with the same algorithm.

Keywords: information gain (IG), intrusion detection system (IDS), k-means clustering, Weka

Procedia PDF Downloads 296