Search results for: graph-based feature filtering method

Authors: Maryam Mosleh, Mahmood Otadi

Abstract:

The hybrid differential equations have a wide range of applications in science and engineering. In this paper, the homotopy analysis method (HAM) is applied to obtain the series solution of the hybrid differential equations. Using the homotopy analysis method, it is possible to find the exact solution or an approximate solution of the problem. Comparisons are made between improved predictor-corrector method, homotopy analysis method and the exact solution. Finally, we illustrate our approach by some numerical example.

Keywords: Fuzzy number, parametric form of a fuzzy number, fuzzy integrodifferential equation, homotopy analysis method

Procedia PDF Downloads 536

Authors: Bengi Sonyel, Kheder Kasem

Abstract:

Nowadays technology is growing so fast. Everybody agrees that technology should be enhanced more in educational field in order to achieve maximum level of teaching and learning effectiveness. Collaborative learning is one of the most important subjects that have been discussed widely in the last 20 years. In this growing of technology and the widely spread of e-learning systems most of face-to-face processes are changing to be completely online base. Online collaborative learning considered one of the new feature that applied recently in some e-Learning systems but still there are much differences between face-to-face instance of collaborative learning and what really occur and happen in networked online environment.In this research we will compare face-to-face collaborative learning with online collaborative learning to define the key success for achieving course’s outcomes. We will also study the current teachers and students experience in today e-Learning systems, more specifically in online collaborative system and study them interaction to today’s technology that related to education. We will apply quantitative and qualitative research method in order to get accurate results. Finally we will gather all of our findings, analyze it and try to find the advantages and disadvantages as well as the current problems and possible solutions.

Keywords: collaborative learning, learning by doing, technology, teachers, learners experiences

Procedia PDF Downloads 506

Authors: S. M. Abdullah Al Mamun

Abstract:

Human Computer Interaction (HCI) is an excellent area for the researchers to make daily life more simple and fast. Necessary hardware equipments for any BCI are generally expensive and not affordable for most of the people. Emotiv is one of the solutions for this problem, which can provide electroencephalograph (EEG) signal and explain the brain activities. BCI virtual speller was one of the important applications for the people who have lost their hand or speaking ability because of diseases or unexpected accident. In this paper, a matrix speller has been designed for the first time for Bengali speaking people around the world. Bengali is one of the most commonly spoken languages. Among them, a lot of disabled person will be able to express their desire in their mother tongue. This application is also usable for the social networks and daily life communications. For this virtual keyboard, the well-known matrix speller method with column flashing is applied and controlled by single Emokey only. Emokey is a great feature which translates emotional state for application inputs. In this paper, it is presented that the ITR (Information Transfer Rate) were 29.4 bits/min and typing speed achieved up to 7.43 char/per min.

Keywords: brain computer interface, Emotiv EPOC, EEG, virtual keyboard, matrix speller

Procedia PDF Downloads 288

Authors: Jiaying Zhang, Xin Mu, Chang Ni, Jeff L. Zhang

Abstract:

Magnetic resonance elastography (MRE) non-invasively assesses tissue elastic properties, such as shear modulus, by measuring tissue’s displacement in response to mechanical waves. The estimated metrics on tissue elasticity or stiffness have been shown to be valuable for monitoring physiologic or pathophysiologic status of tissue, such as a tumor or fatty liver. To quantify tissue shear modulus from MRE-acquired displacements (essentially an inverse problem), multiple approaches have been proposed, including Local Frequency Estimation (LFE) and Direct Inversion (DI). However, one common problem with these methods is that the estimates are severely noise-sensitive due to either the inverse-problem nature or noise propagation in the pixel-by-pixel process. With the advent of deep learning (DL) and its promise in solving inverse problems, a few groups in the field of MRE have explored the feasibility of using DL methods for quantifying shear modulus from MRE data. Most of the groups chose to use real MRE data for DL model training and to cut training images into smaller patches, which enriches feature characteristics of training data but inevitably increases computation time and results in outcomes with patched patterns. In this study, simulated wave images generated by Finite Differential Time Domain (FDTD) simulation are used for network training, and U-Net is used to extract features from each training image without cutting it into patches. The use of simulated data for model training has the flexibility of customizing training datasets to match specific applications. The proposed method aimed to estimate tissue shear modulus from MRE data with high robustness to noise and high model-training efficiency. Specifically, a set of 3000 maps of shear modulus (with a range of 1 kPa to 15 kPa) containing randomly positioned objects were simulated, and their corresponding wave images were generated. The two types of data were fed into the training of a U-Net model as its output and input, respectively. For an independently simulated set of 1000 images, the performance of the proposed method against DI and LFE was compared by the relative errors (root mean square error or RMSE divided by averaged shear modulus) between the true shear modulus map and the estimated ones. The results showed that the estimated shear modulus by the proposed method achieved a relative error of 4.91%±0.66%, substantially lower than 78.20%±1.11% by LFE. Using simulated data, the proposed method significantly outperformed LFE and DI in resilience to increasing noise levels and in resolving fine changes of shear modulus. The feasibility of the proposed method was also tested on MRE data acquired from phantoms and from human calf muscles, resulting in maps of shear modulus with low noise. In future work, the method’s performance on phantom and its repeatability on human data will be tested in a more quantitative manner. In conclusion, the proposed method showed much promise in quantifying tissue shear modulus from MRE with high robustness and efficiency.

Keywords: deep learning, magnetic resonance elastography, magnetic resonance imaging, shear modulus estimation

Procedia PDF Downloads 48

Authors: Masoud Fathi Kazerouni, Jens Schlemper, Klaus-Dieter Kuhnert

Abstract:

Green planet is one of the Earth’s names which is known as a terrestrial planet and also can be named the fifth largest planet of the solar system as another scientific interpretation. Plants do not have a constant and steady distribution all around the world, and even plant species’ variations are not the same in one specific region. Presence of plants is not only limited to one field like botany; they exist in different fields such as literature and mythology and they hold useful and inestimable historical records. No one can imagine the world without oxygen which is produced mostly by plants. Their influences become more manifest since no other live species can exist on earth without plants as they form the basic food staples too. Regulation of water cycle and oxygen production are the other roles of plants. The roles affect environment and climate. Plants are the main components of agricultural activities. Many countries benefit from these activities. Therefore, plants have impacts on political and economic situations and future of countries. Due to importance of plants and their roles, study of plants is essential in various fields. Consideration of their different applications leads to focus on details of them too. Automatic recognition of plants is a novel field to contribute other researches and future of studies. Moreover, plants can survive their life in different places and regions by means of adaptations. Therefore, adaptations are their special factors to help them in hard life situations. Weather condition is one of the parameters which affect plants life and their existence in one area. Recognition of plants in different weather conditions is a new window of research in the field. Only natural images are usable to consider weather conditions as new factors. Thus, it will be a generalized and useful system. In order to have a general system, distance from the camera to plants is considered as another factor. The other considered factor is change of light intensity in environment as it changes during the day. Adding these factors leads to a huge challenge to invent an accurate and secure system. Development of an efficient plant recognition system is essential and effective. One important component of plant is leaf which can be used to implement automatic systems for plant recognition without any human interface and interaction. Due to the nature of used images, characteristic investigation of plants is done. Leaves of plants are the first characteristics to select as trusty parts. Four different plant species are specified for the goal to classify them with an accurate system. The current paper is devoted to principal directions of the proposed methods and implemented system, image dataset, and results. The procedure of algorithm and classification is explained in details. First steps, feature detection and description of visual information, are outperformed by using Scale invariant feature transform (SIFT), HARRIS-SIFT, and FAST-SIFT methods. The accuracy of the implemented methods is computed. In addition to comparison, robustness and efficiency of results in different conditions are investigated and explained.

Keywords: SIFT combination, feature extraction, feature detection, natural images, natural plant recognition, HARRIS-SIFT, FAST-SIFT

Procedia PDF Downloads 259

Authors: Elham Serkani, Hossein Gharaee Garakani, Naser Mohammadzadeh, Elaheh Vaezpour

Abstract:

Intrusion detection systems (IDS) are the main components of network security. These systems analyze the network events for intrusion detection. The design of an IDS is through the training of normal traffic data or attack. The methods of machine learning are the best ways to design IDSs. In the method presented in this article, the pruning algorithm of C5.0 decision tree is being used to reduce the features of traffic data used and training IDS by the least square vector algorithm (LS-SVM). Then, the remaining features are arranged according to the predictor importance criterion. The least important features are eliminated in the order. The remaining features of this stage, which have created the highest level of accuracy in LS-SVM, are selected as the final features. The features obtained, compared to other similar articles which have examined the selected features in the least squared support vector machine model, are better in the accuracy, true positive rate, and false positive. The results are tested by the UNSW-NB15 dataset.

Keywords: decision tree, feature selection, intrusion detection system, support vector machine

Procedia PDF Downloads 246

Authors: Yunwei Zhang, Qiaochu Tang, Yao Zhang, Jiabin Wang, Ulrich Stimming, Alpha Lee

Abstract:

Forecasting the state of health and remaining useful life of Li-ion batteries is an unsolved challenge that limits technologies such as consumer electronics and electric vehicles. Here we build an accurate battery forecasting system by combining electrochemical impedance spectroscopy (EIS) -- a real-time, non-invasive and information-rich measurement that is hitherto underused in battery diagnosis -- with Gaussian process machine learning. We collect over 20,000 EIS spectra of commercial Li-ion batteries at different states of health, states of charge and temperatures -- the largest dataset to our knowledge of its kind. Our Gaussian process model takes the entire spectrum as input, without further feature engineering, and automatically determines which spectral features predict degradation. Our model accurately predicts the remaining useful life, even without complete knowledge of past operating conditions of the battery. Our results demonstrate the value of EIS signals in battery management systems.

Keywords: battery degradation, machine learning method, electrochemical impedance spectroscopy, battery diagnosis

Procedia PDF Downloads 129

Authors: M. Tohidi, J. Yang, C. Baniotopoulos

Abstract:

Progressive collapse of buildings typically occurs when abnormal loading conditions cause local damages, which leads to a chain reaction of failure and ultimately catastrophic collapse. The tie force (TF) method is one of the main design approaches for progressive collapse. As the TF method is a simplified method, further investigations on the reliability of the method is necessary. This study aims to develop an improved TF method to design the cross wall structures for progressive collapse. To this end, the pullout behavior of strands in grout was firstly analyzed; and then, by considering the tie force-slip relationship in the friction stage together with the catenary action mechanism, a comprehensive analytical method was developed. The reliability of this approach is verified by the experimental results of concrete block pullout tests and full scale floor-to-floor joints tests undertaken by Portland Cement Association (PCA). Discrepancies in the tie force between the analytical results and codified specifications have suggested the deficiency of TF method, hence an improved model based on the analytical results has been proposed to address this concern.

Keywords: cross wall, progressive collapse, ties force method, catenary, analytical

Procedia PDF Downloads 451

Authors: Nidhi Patel, Amol Shinde, Amrin Moger

Abstract:

Mainstream Hindi cinema also known as Bollywood, is the largest film producing industry in India. The Indian film industry underwent a sea change since last few years. The industry adapted to the latest technologies and creative manpower to improve visual and cinematic effects. The changes helped the industry to improve its creative looks and ease on production budget. The research focuses on this very change, i.e. the use of VFX. There has been growing use of VFX in feature films. The primary focus is on how VFX can make a difference in the experience of watching a movie. The research examines the use of CGI/VFX in the narrative, which delivers a visually fulfilling film. It also focuses on the use of CGI/ VFX as a cost cutting tool. The research was exploratory in nature. It studies the industry’s evolvement, increment in its use by filmmakers and their intention to use it in their films. The researcher used qualitative method for data collection as an in-depth interview of 10 artists from VFX studios in Mumbai was conducted. The finding reveals the way VFX is used in Hindi cinema by the directors. The researcher learnt that VFX is majorly used as a tool to enhance creativity and provide the audience with creative viewing experience.

Keywords: Bollywood, Hindi cinema, VFX, CGI, technology, creativity, cost cutting

Procedia PDF Downloads 344

Authors: Imen Debbabi, Hédi BelHadjSalah

Abstract:

The Improved Element Free Galerkin (IEFG) method is presented to treat the steady states and the transient heat transfer problems. As a result of a combination between the Improved Moving Least Square (IMLS) approximation and the Element Free Galerkin (EFG) method, the IEFG's shape functions don't have the Kronecker delta property and the penalty method is used to impose the Dirichlet boundary conditions. In this paper, two heat transfer problems, transient and steady states, are studied to improve the efficiency of this meshfree method for 2D heat transfer problems. The performance of the IEFG method is shown using the comparison between numerical and analytic results.

Keywords: meshfree methods, the Improved Moving Least Square approximation (IMLS), the Improved Element Free Galerkin method (IEFG), heat transfer problems

Procedia PDF Downloads 379

Authors: Haifeng Zhou, Tsungyang Liow, Xiaoguang Tu, Eujin Lim, Chao Li, Junfeng Song, Xianshu Luo, Ying Huang, Lianxi Jia, Lianwee Luo, Kim Dowon, Qing Fang, Mingbin Yu, Guoqiang Lo

Abstract:

Several Germanium photodetectors (PD) built on silicon micro-disks are fabricated on the standard Si photonics multiple project wafers (MPW) and demonstrated to exhibit very low dark current, satisfactory operation bandwidth and moderate responsivity. Among them, a vertical p-i-n Ge PD based on a 2.0 µm-radius micro-disk has a dark current of as low as 35 nA, compared to a conventional PD current of 1 µA with an area of 100 µm2. The operation bandwidth is around 15 GHz at a reverse bias of 1V. The responsivity is about 0.6 A/W. Microdisk is a striking planar structure in integrated optics to enhance light-matter interaction and construct various photonics devices. The disk geometries feature in strongly and circularly confining light into an ultra-small volume in the form of whispering gallery modes. A laser may benefit from a microdisk in which a single mode overlaps the gain materials both spatially and spectrally. Compared to microrings, micro-disk removes the inner boundaries to enable even better compactness, which also makes it very suitable for some scenarios that electrical connections are needed. For example, an ultra-low power (≈ fJ) athermal Si modulator has been demonstrated with a bit rate of 25Gbit/s by confining both photons and electrically-driven carriers into a microscale volume.In this work, we study Si-based PDs with Ge selectively grown on a microdisk with the radius of a few microns. The unique feature of using microdisk for Ge photodetector is that mode selection is not important. In the applications of laser or other passive optical components, microdisk must be designed very carefully to excite the fundamental mode in a microdisk in that essentially the microdisk usually supports many higher order modes in the radial directions. However, for detector applications, this is not an issue because the local light absorption is mode insensitive. Light power carried by all modes are expected to be converted into photo-current. Another benefit of using microdisk is that the power circulation inside avoids any introduction of the reflector. A complete simulation model with all involved materials taken into account is established to study the promise of microdisk structures for photodetector by using finite difference time domain (FDTD) method. By viewing from the current preliminary data, the directions to further improve the device performance are also discussed.

Keywords: integrated optical devices, silicon photonics, micro-resonator, photodetectors

Procedia PDF Downloads 392

Authors: Mustafa Alhamdi

Abstract:

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

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

Procedia PDF Downloads 135

Authors: Hamdy M. Youssef, Eman A. Al-Lehaibi

Abstract:

This paper presents an iteration method for the numerical solutions of a one-dimensional problem of generalized thermoelasticity with one relaxation time under given initial and boundary conditions. The thermoelastic material with variable properties as a power functional graded has been considered. Adomian’s decomposition techniques have been applied to the governing equations. The numerical results have been calculated by using the iterations method with a certain algorithm. The numerical results have been represented in figures, and the figures affirm that Adomian’s decomposition method is a successful method for modeling thermoelastic problems. Moreover, the empirical parameter of the functional graded, and the lattice design parameter have significant effects on the temperature increment, the strain, the stress, the displacement.

Keywords: Adomian, decomposition method, generalized thermoelasticity, algorithm

Procedia PDF Downloads 124

Authors: Hana Rabbouch

Abstract:

In recent years, there has been considerable growth of denoising techniques mainly devoted to medical imaging. This important evolution is not only due to the progress of computing techniques, but also to the emergence of multi-resolution analysis (MRA) on both mathematical and algorithmic bases. In this paper, a comparative study is conducted between the two best-known MRA-based decomposition techniques: the Empirical Mode Decomposition (EMD) and the Discrete Wavelet Transform (DWT). The comparison is carried out in a framework of multi-scale denoising, where a Non-Local Means (NLM) filter is performed scale-by-scale to a sample of benchmark medical images. The results prove the effectiveness of the multiscaled denoising, especially when the NLM filtering is coupled with the EMD.

Keywords: medical imaging, non local means, denoising, multiscaled analysis, empirical mode decomposition, wavelets

Procedia PDF Downloads 126

Authors: Khairil I. Othman, Mahfuzah Mahayaddin, Zarina Bibi Ibrahim

Abstract:

We develop and demonstrate a computationally efficient numerical technique to solve first order stiff differential equations. This technique is based on block method whereby three approximate points are calculated. The Cholistani of varied step sizes are presented in divided difference form. Stability regions of the formulae are briefly discussed in this paper. Numerical results show that this block method perform very well compared to existing methods.

Keywords: block method, divided difference, stiff, computational

Procedia PDF Downloads 408

Authors: H. Majour, L. Djabri

Abstract:

Many methods in the groundwater vulnerability have been developed in the world (methods like PRAST, DRIST, APRON/ARAA, PRASTCHIM, GOD). In this study, our choice dealt with two recent complementary methods using category mapping of index with weighting criteria (Point County Systems Model MSCP) namely the standard DRASTIC method and SI (Susceptibility Index). At present, these two methods are the most used for the mapping of the intrinsic vulnerability of groundwater. Two classes of groundwater vulnerability in the Biskra sandy aquifer were identified by the DRASTIC method (average and high) and the SI method (very high and high). Integrated analysis has revealed that the high class is predominant for the DRASTIC method whereas for that of SI the preponderance is for the very high class. Furthermore, we notice that the method SI estimates better the vulnerability for the pollution in nitrates, with a rate of 85 % between the concentrations in nitrates of groundwater and the various established classes of vulnerability, against 75 % for the DRASTIC method. By including the land use parameter, the SI method produced more realistic results.

Keywords: DRASTIC, SI, GIS, Biskra sandy aquifer, Algeria

Procedia PDF Downloads 470

Authors: Rubin Dan, Xingcai Wang, Ziyang Chen

Abstract:

A chaotic time series noise reduction method based on the fusion of the local projection method, wavelet transform, and particle swarm algorithm (referred to as the LW-PSO method) is proposed to address the problem of false recognition due to noise in the recognition process of chaotic time series containing noise. The method first uses phase space reconstruction to recover the original dynamical system characteristics and removes the noise subspace by selecting the neighborhood radius; then it uses wavelet transform to remove D1-D3 high-frequency components to maximize the retention of signal information while least-squares optimization is performed by the particle swarm algorithm. The Lorenz system containing 30% Gaussian white noise is simulated and verified, and the phase space, SNR value, RMSE value, and K value of the 0-1 test method before and after noise reduction of the Schreiber method, local projection method, wavelet transform method, and LW-PSO method are compared and analyzed, which proves that the LW-PSO method has a better noise reduction effect compared with the other three common methods. The method is also applied to the classical system to evaluate the noise reduction effect of the four methods and the original system identification effect, which further verifies the superiority of the LW-PSO method. Finally, it is applied to the Chengdu rainfall chaotic sequence for research, and the results prove that the LW-PSO method can effectively reduce the noise and improve the chaos recognition rate.

Keywords: Schreiber noise reduction, wavelet transform, particle swarm optimization, 0-1 test method, chaotic sequence denoising

Procedia PDF Downloads 180

Authors: Chamnan Kumsap, Somsarit Sinnung, Suriyawate Boonthalarath, Teeranai Srithamarong

Abstract:

This research paper addresses the GIS analysis approach to the investigation of suitable sites for a vertical takeoff and landing drone. The study manipulated GIS and terrain layers into a proper input before the spatial analysis that included slope, reclassify, classify, and buffer was applied to the individual layers. The output layers were weighted, and multi-criteria analyzed before those patches failing to comply with filtering out criteria were discarded. Field survey for each suitable candidate site was conducted to cross-check the proposed approach with the real world. Conclusion was extracted for the VTOL takeoff and landing sites, and discussion was provided with further study being suggested on the mission simulation of selected takeoff and landing sites.

Keywords: GIS approach, site selection, VTOL, takeoff and landing

Procedia PDF Downloads 85

Authors: Lanchi Xie, Zhihui Li, Zhigang Li, Guiqiang Wang, Lei Xu, Yuwen Yan

Abstract:

Image-based facial features can be classified into category recognition features and individual recognition features. Current automated face recognition systems extract a specific feature vector of different dimensions from a facial image according to their pre-trained neural network. However, to improve the efficiency of parameter calculation, an algorithm generally reduces the image details by pooling. The operation will overlook the details concerned much by forensic experts. In our experiment, we adopted a variety of face recognition algorithms based on deep learning, compared a large number of naturally collected face images with the known data of the same person's frontal ID photos. Downscaling and manual handling were performed on the testing images. The results supported that the facial recognition algorithms based on deep learning detected structural and morphological information and rarely focused on specific markers such as stains and moles. Overall performance, distribution of genuine scores and impostor scores, and likelihood ratios were tested to evaluate the accuracy of biometric systems and forensic experts. Experiments showed that the biometric systems were skilled in distinguishing category features, and forensic experts were better at discovering the individual features of human faces. In the proposed approach, a fusion was performed at the score level. At the specified false accept rate, the framework achieved a lower false reject rate. This paper contributes to improving the interpretability of the objective method of facial comparison and provides a novel method for human-machine collaboration in this field.

Keywords: likelihood ratio, automated facial recognition, facial comparison, biometrics

Procedia PDF Downloads 113

Authors: Archit Yajnik, Rustam Ali

Abstract:

In this paper, numerical method based on discrete GHM multiwavelets is presented for solving the Fredholm integral equations of second kind. There is hardly any article available in the literature in which the integral equations are numerically solved using discrete GHM multiwavelet. A number of examples are demonstrated to justify the applicability of the method. In GHM multiwavelets, the values of scaling and wavelet functions are calculated only at t = 0, 0.5 and 1. The numerical solution obtained by the present approach is compared with the traditional Quadrature method. It is observed that the present approach is more accurate and computationally efficient as compared to quadrature method.

Keywords: GHM multiwavelet, fredholm integral equations, quadrature method, function approximation

Procedia PDF Downloads 451

Authors: Joseph Gear, Yue Xu, Ernest Foo, Praveen Gauravaran, Zahra Jadidi, Leonie Simpson

Abstract:

Deep learning methods have been seeing an increasing application to the long-standing security research goal of automatic vulnerability detection for source code. Attention, however, must still be paid to the task of producing vector representations for source code (code embeddings) as input for these deep learning models. Graphical representations of code, most predominantly Abstract Syntax Trees and Code Property Graphs, have received some use in this task of late; however, for very large graphs representing very large code snip- pets, learning becomes prohibitively computationally expensive. This expense may be reduced by intelligently pruning this input to only vulnerability-relevant information; however, little research in this area has been performed. Additionally, most existing work comprehends code based solely on the structure of the graph at the expense of the information contained by the node in the graph. This paper proposes Semantic-enhanced Code Embedding for Vulnerability Discovery (SCEVD), a deep learning model which uses semantic-based feature selection for its vulnerability classification model. It uses information from the nodes as well as the structure of the code graph in order to select features which are most indicative of the presence or absence of vulnerabilities. This model is implemented and experimentally tested using the SARD Juliet vulnerability test suite to determine its efficacy. It is able to improve on existing code graph feature selection methods, as demonstrated by its improved ability to discover vulnerabilities.

Keywords: code representation, deep learning, source code semantics, vulnerability discovery

Procedia PDF Downloads 140

Authors: Hyuk-Jin Lee

Abstract:

Even though 23 years have passed in the 21st century, nation-state and nationality-centered cultural identities are still the sentiments and ideologies that dominate the world. Nevertheless, as seen in many cases in Europe, a new perspective is needed to recognize mutual exchanges and influences and to view them as natural cultural exchanges between countries. The situation in East Asia is completely different from Europe. This is presumed to be from the long tradition of having an ethnocentric state concept for at least hundreds of years, quite different from Europe, where the concept of a nation-state was established relatively recently. In other words, unlike Europe, where active exchanges took place, the problem stems from the unique characteristics of East Asia, which has a strong tradition of finding its identity in 'difference'. Thus, it would not be hard to find cultural studies or news of the three East Asian countries emphasizing differences among one another. This applies to all cultural areas, including traditional architecture. For example, in the Korean traditional architecture field, buildings with effects from neighboring countries tend to be ignored, even if they are traditional Korean architecture. In addition to this, in the case of Korea, there seems to be one more cultural harmful aftereffect caused by the 36 years of Japanese colonial rule in the early 20th century; the obsessive filtering concept of 'it must be different from Japan'. In other words, the implicit ideological coercion that the definition of 'Korean cultural heritage' should not be influenced by exchanges with Japan may be found throughout Korean studies. The architectural and cultural aspects of the vast period of time, from the Three Kingdoms era to the beginning of Joseon, which was a period in which cultural influence exchanges with neighboring countries were relatively strong compared to the late Joseon Dynasty, also reflect the 'distorted filtering' caused by finding a repulsive identity against the Japanese colonial period. It is important to look the cultural heritage and traditions as they are inductively, not deductively. If not, we may often ignore or limit our own precious cultural heritage. Conversely, If Baekje, the ancient Korean Kingdom, helped Japan in construction and craftsmen played a big role in building the ancient temple, it would be a healthier perspective to view it as a cultural exchange rather than proudly seeing it as a cultural owner's perspective because this point of view is a proper reconstruction of our ancient and medieval Asian culture (strictly speaking, the color common to East Asia at the time). In particular, this study will examine this topic by giving specific examples from each field of Korean cultural studies. In the search for cultural identity, it would be more helpful for healthy relations between countries and collaborative research in the sensitive part of the interpretation of historical facts as well as cultural circles to minimize excessive meanings on originality and difference.

Keywords: cultural heritage identity, cultural ideology, East Asia, Korea

Procedia PDF Downloads 59

Authors: Yulan Wu

Abstract:

With the rapid development of social media, the issue of fake news has gained considerable prominence, drawing the attention of both the public and governments. The widespread dissemination of false information poses a tangible threat across multiple domains of society, including politics, economy, and health. However, much research has concentrated on supervised training models within specific domains, their effectiveness diminishes when applied to identify fake news across multiple domains. To solve this problem, some approaches based on domain labels have been proposed. By segmenting news to their specific area in advance, judges in the corresponding field may be more accurate on fake news. However, these approaches disregard the fact that news records can pertain to multiple domains, resulting in a significant loss of valuable information. In addition, the datasets used for training must all be domain-labeled, which creates unnecessary complexity. To solve these problems, an unsupervised domain knowledge discovery framework for fake news detection is proposed. Firstly, to effectively retain the multidomain knowledge of the text, a low-dimensional vector for each news text to capture domain embeddings is generated. Subsequently, a feature extraction module utilizing the unsupervisedly discovered domain embeddings is used to extract the comprehensive features of news. Finally, a classifier is employed to determine the authenticity of the news. To verify the proposed framework, a test is conducted on the existing widely used datasets, and the experimental results demonstrate that this method is able to improve the detection performance for fake news across multiple domains. Moreover, even in datasets that lack domain labels, this method can still effectively transfer domain knowledge, which can educe the time consumed by tagging without sacrificing the detection accuracy.

Keywords: fake news, deep learning, natural language processing, multiple domains

Procedia PDF Downloads 69

Authors: Prodromos E. Atlamazoglou

Abstract:

The method of moments combined with the method of symmetrical components is used for the analysis of interstitial hyperthermia applicators. The basis and testing functions are both piecewise sinusoids, qualifying our technique as a Galerkin one. The dielectric coatings are modeled by equivalent volume polarization currents, which are simply related to the conduction current distribution, avoiding in that way the introduction of additional unknowns or numerical integrations. The results of our method for a four dipole circular array, are in agreement with those already published in literature for a same hyperthermia configuration. Apart from being accurate, our approach is more general, more computationally efficient and takes into account the coupling between the antennas.

Keywords: hyperthermia, integral equations, insulated antennas, method of symmetrical components

Procedia PDF Downloads 244

Authors: Shaomei Li, Yawen Wang, Chao Gao

Abstract:

To improve tracking drift which often occurs in adaptive tracking, an algorithm based on the fusion of tracking and detection is proposed in this paper. Firstly, object tracking is posed as a binary classification problem and is modeled by partial least squares (PLS) analysis. Secondly, tracking object frame by frame via particle filtering. Thirdly, validating the tracking reliability based on both positive and negative models matching. Finally, relocating the object based on SIFT features matching and voting when drift occurs. Object appearance model is updated at the same time. The algorithm cannot only sense tracking drift but also relocate the object whenever needed. Experimental results demonstrate that this algorithm outperforms state-of-the-art algorithms on many challenging sequences.

Keywords: object tracking, tracking drift, partial least squares analysis, positive and negative models matching

Procedia PDF Downloads 511

Authors: B. Ramesh Naik, T. Venugopal

Abstract:

This paper presents a novel approach which improves the high-level semantics of images based on machine learning approach. The contemporary approaches for image retrieval and object recognition includes Fourier transforms, Wavelets, SIFT and HoG. Though these descriptors helpful in a wide range of applications, they exploit zero order statistics, and this lacks high descriptiveness of image features. These descriptors usually take benefit of primitive visual features such as shape, color, texture and spatial locations to describe images. These features do not adequate to describe high-level semantics of the images. This leads to a gap in semantic content caused to unacceptable performance in image retrieval system. A novel method has been proposed referred as discriminative learning which is derived from machine learning approach that efficiently discriminates image features. The analysis and results of proposed approach were validated thoroughly on WANG and Caltech-101 Databases. The results proved that this approach is very competitive in content-based image retrieval.

Keywords: CBIR, discriminative learning, region weight learning, scale invariant feature transforms

Procedia PDF Downloads 164

Authors: B. Sellami, Y. Laskri, M. Belloufi

Abstract:

Conjugate gradient methods are an important class of methods for unconstrained optimization, especially for large-scale problems. Recently, they have been much studied. In this paper, a new family of conjugate gradient method is proposed for unconstrained optimization. This method includes the already existing two practical nonlinear conjugate gradient methods, which produces a descent search direction at every iteration and converges globally provided that the line search satisfies the Wolfe conditions. The numerical experiments are done to test the efficiency of the new method, which implies the new method is promising. In addition the methods related to this family are uniformly discussed.

Keywords: conjugate gradient method, global convergence, line search, unconstrained optimization

Procedia PDF Downloads 388

Authors: Muhammad Farooq Baig

Abstract:

Objective: The purpose of this study was to compare results obtained using a single fecal specimen for O&P examination, direct immunofluorescence assay (DFA), and two conventional staining methods. Design: Hundred and fifty children fecal specimens were collected and examined by each method. The O&P and the DFA were used as the reference method. Setting: The study was performed at the laboratory in the Basic Medical Science Institute JPMC Karachi. Patients or Other Participants: The fecal specimens were collected from children with a suspected Giardia lamblia infection. Main Outcome Measures: The amount of agreement and disagreement between methods.1) Presence of giardiasis in our population. 2) The sensitivity and specificity of each method. Results: There was 45(30%) positive 105 (70%) negative on DFA, 41 (27.4%) positive 109 (72.6%) negative on iodine and 34 (22.6%) positive 116(77.4%) on saline method. The sensitivity and specificity of DFA in comparision to iodine were 92.2%, 92.7% respectively. The sensitivity and specificity of DFA in comparisoin to saline method were 91.2%, 87.9% respectively. The sensitivity of iodine method and saline method in compariosn to DFA were 82.2%, 68.8% respectively. There is mark diffrence in sensitivity of DFA to conventional method. Conclusion: The study supported findings of other investigators who concluded that DFA method have the greater sensitivity. The immunologic methods were more efficient and quicker than the conventional O&P method.

Keywords: direct immunofluorescence assay (DFA), ova and parasite (O&P), Giardia lamblia, children, medical science

Procedia PDF Downloads 397

Authors: Uduak Umoh, Imo Eyoh, Emmauel Nyoho

Abstract:

This paper compares fuzzy-machine learning algorithms such as Support Vector Machine (SVM), and K-Nearest Neighbor (KNN) for the predicting cases of fire outbreak. The paper uses the fire outbreak dataset with three features (Temperature, Smoke, and Flame). The data is pre-processed using Interval Type-2 Fuzzy Logic (IT2FL) algorithm. Min-Max Normalization and Principal Component Analysis (PCA) are used to predict feature labels in the dataset, normalize the dataset, and select relevant features respectively. The output of the pre-processing is a dataset with two principal components (PC1 and PC2). The pre-processed dataset is then used in the training of the aforementioned machine learning models. K-fold (with K=10) cross-validation method is used to evaluate the performance of the models using the matrices – ROC (Receiver Operating Curve), Specificity, and Sensitivity. The model is also tested with 20% of the dataset. The validation result shows KNN is the better model for fire outbreak detection with an ROC value of 0.99878, followed by SVM with an ROC value of 0.99753.

Keywords: Machine Learning Algorithms , Interval Type-2 Fuzzy Logic, Fire Outbreak, Support Vector Machine, K-Nearest Neighbour, Principal Component Analysis

Procedia PDF Downloads 163

Authors: C. C. Lv, Y. L. Sun, D. W. Zuo

Abstract:

Cemented carbide balls are usually implemented in industry under the environment of high speed, high temperature, corrosiveness and strong collisions. However, its application is limited due to high fabrication cost, processing efficiency and quality. A novel eccentric lapping method with two rotatable lapping plates was proposed in this paper. A mathematical model was constructed to analyze the influence of each design parameter on this lapping method. To validate this new lapping method, an orthogonal experiment was conducted with cemented carbide balls (YG6). The simulation model was verified and the optimal lapping parameters were derived. The results show that the surface roundness of the balls reaches to 0.65um from 2um in 1 hour using this lapping method. So, using this novel lapping method, it can effectively improve the machining precision and efficiency of cemented carbide balls.

Keywords: cemented carbide balls, eccentric lapping, high precision, lapping tracks, V-groove

Procedia PDF Downloads 384