Search results for: adversarial sample

Authors: Yaxin Bi

Abstract:

Accurate prediction and understanding of the evolution mechanisms of earthquakes remain challenging in the fields of geology, geophysics, and seismology. This study leverages Long Short-Term Memory (LSTM) networks and Generative Adversarial Networks (GANs), a generative model tailored to time-series data, for generating synthetic time series data based on Swarm satellite data, which will be used for detecting seismic anomalies. LSTMs demonstrated commendable predictive performance in generating synthetic data across multiple countries. In contrast, the GAN models struggled to generate synthetic data, often producing non-informative values, although they were able to capture the data distribution of the time series. These findings highlight both the promise and challenges associated with applying deep learning techniques to generate synthetic data, underscoring the potential of deep learning in generating synthetic electromagnetic satellite data.

Keywords: LSTM, GAN, earthquake, synthetic data, generative AI, seismic precursors

Procedia PDF Downloads 32

Authors: Haoqi Gao, Koichi Ogawara

Abstract:

Retinal vascular segmentation of color fundus is the basis of ophthalmic computer-aided diagnosis and large-scale disease screening systems. Early screening of fundus diseases has great value for clinical medical diagnosis. The traditional methods depend on the experience of the doctor, which is time-consuming, labor-intensive, and inefficient. Furthermore, medical images are scarce and fraught with legal concerns regarding patient privacy. In this paper, we propose a new Generative Adversarial Network based on CycleGAN for retinal fundus images. This method can generate not only synthetic fundus images but also generate corresponding segmentation masks, which has certain application value and challenge in computer vision and computer graphics. In the results, we evaluate our proposed method from both quantitative and qualitative. For generated segmented images, our method achieves dice coefficient of 0.81 and PR of 0.89 on DRIVE dataset. For generated synthetic fundus images, we use ”Toy Experiment” to verify the state-of-the-art performance of our method.

Keywords: retinal vascular segmentations, generative ad-versarial network, cyclegan, fundus images

Procedia PDF Downloads 144

Authors: Michael F. Mascolo

Abstract:

Western democratic traditions are being strained. Western nations are losing the common agonistic ground needed to engage in traditional forms of democracy – adversarial debate, voting, and the peaceful transfer of power. Political polarization among party elites has become commonplace. Because it seeks to resolve conflict through the integration of opposites, a dialectical approach to resolving partisan conflict offers the promise of helping political partisans bridge ideological divides. This paper contains an analysis of dialectical engagement as a collaborative alternative to adversarial politics. Dialectical engagement involves two broad phases: collaborative political problem-solving and dialectical problem-solving. The paper contains a description of an 18-month longitudinal study assessing the effectiveness of dialectical engagement as a method for bridging divides on contentious socio-political issues. The study shows how dialectical engagement produced dramatic consensus among a small group of individuals from different political orientations as they worked together to resolve the issue of capital punishment.

Keywords: collaborative democracy, dialectical thinking, capital punishment, partisan conflict

Procedia PDF Downloads 71

Authors: P. Karthick, K. Mahesh

Abstract:

Video has become an increasingly significant component of our digital everyday contact. With the advancement of greater contents and shows of the resolution, its significant volume poses serious obstacles to the objective of receiving, distributing, compressing, and revealing video content of high quality. In this paper, we propose the primary beginning to complete a deep video compression model that jointly upgrades all video compression components. The video compression method involves splitting the video into frames, comparing the images using convolutional neural networks (CNN) to remove duplicates, repeating the single image instead of the duplicate images by recognizing and detecting minute changes using generative adversarial network (GAN) and recorded with long short-term memory (LSTM). Instead of the complete image, the small changes generated using GAN are substituted, which helps in frame level compression. Pixel wise comparison is performed using K-nearest neighbours (KNN) over the frame, clustered with K-means, and singular value decomposition (SVD) is applied for each and every frame in the video for all three color channels [Red, Green, Blue] to decrease the dimension of the utility matrix [R, G, B] by extracting its latent factors. Video frames are packed with parameters with the aid of a codec and converted to video format, and the results are compared with the original video. Repeated experiments on several videos with different sizes, duration, frames per second (FPS), and quality results demonstrate a significant resampling rate. On average, the result produced had approximately a 10% deviation in quality and more than 50% in size when compared with the original video.

Keywords: video compression, K-means clustering, convolutional neural network, generative adversarial network, singular value decomposition, pixel visualization, stochastic gradient descent, frame per second extraction, RGB channel extraction, self-detection and deciding system

Procedia PDF Downloads 187

Authors: Arya Prakash Padhi, Anupam Chakrabarti, Rajib Chowdhury

Abstract:

Topology or layout optimization often gives better performing economic structures and is very helpful in the conceptual design phase. But traditionally it is being done in finite element-based optimization schemes which, although gives a good result, is very time-consuming especially in 3D structures. Among other alternatives machine learning, especially deep learning-based methods, have a very good potential in resolving this computational issue. Here convolutional neural network (3D-CNN) based variational auto encoder (VAE) is trained using a dataset generated from commercially available topology optimization code ABAQUS Tosca using solid isotropic material with penalization (SIMP) method for compliance minimization. The encoded data in latent space is then fed to a 3D generative adversarial network (3D-GAN) to generate the outcome in 64x64x64 size. Here the network consists of 3D volumetric CNN with rectified linear unit (ReLU) activation in between and sigmoid activation in the end. The proposed network is seen to provide almost optimal results with significantly reduced computational time, as there is no iteration involved.

Keywords: 3D generative adversarial network, deep learning, structural topology optimization, variational auto encoder

Procedia PDF Downloads 174

Authors: Hongyu Chen, Li Jiang

Abstract:

Ubiquitous anomalies endanger the security of our system con- stantly. They may bring irreversible damages to the system and cause leakage of privacy. Thus, it is of vital importance to promptly detect these anomalies. Traditional supervised methods such as Decision Trees and Support Vector Machine (SVM) are used to classify normality and abnormality. However, in some case, the abnormal status are largely rarer than normal status, which leads to decision bias of these methods. Generative adversarial network (GAN) has been proposed to handle the case. With its strong generative ability, it only needs to learn the distribution of normal status, and identify the abnormal status through the gap between it and the learned distribution. Nevertheless, existing GAN-based models are not suitable to process data with discrete values, leading to immense degradation of detection performance. To cope with the discrete features, in this paper, we propose an efficient GAN-based model with specifically-designed loss function. Experiment results show that our model outperforms state-of-the-art models on discrete dataset and remarkably reduce the overhead.

Keywords: GAN, discrete feature, Wasserstein distance, multiple intermediate layers

Procedia PDF Downloads 129

Authors: Agastya Pratap Singh

Abstract:

This review paper examines the emerging applications of generative adversarial networks (GANs) in the fields of image recognition and anomaly detection. With the rapid growth of digital image data, the need for efficient and accurate methodologies to identify and classify images has become increasingly critical. GANs, known for their ability to generate realistic data, have gained significant attention for their potential to enhance traditional image recognition systems and improve anomaly detection performance. The paper systematically analyzes various GAN architectures and their modifications tailored for image recognition tasks, highlighting their strengths and limitations. Additionally, it delves into the effectiveness of GANs in detecting anomalies in diverse datasets, including medical imaging, industrial inspection, and surveillance. The review also discusses the challenges faced in training GANs, such as mode collapse and stability issues, and presents recent advancements aimed at overcoming these obstacles.

Keywords: generative adversarial networks, image recognition, anomaly detection, synthetic data generation, deep learning, computer vision, unsupervised learning, pattern recognition, model evaluation, machine learning applications

Procedia PDF Downloads 25

Authors: Inga Žukovaitė

Abstract:

This paper aims to present postdoc research on remote criminal proceedings in court. In this period, when most countries have introduced the possibility of remote criminal proceedings in their procedural laws, it is not only possible to identify the weaknesses and strengths of the legal regulation but also assess the effectiveness of the instrument used and to develop an approach to the process. The example of some countries (for example, Italy) shows, on the one hand, that criminal procedure, based on orality and immediacy, does not lend itself to easy modifications that pose even a slight threat of devaluation of these principles in a society with well-established traditions of this procedure. On the other hand, such strong opposition and criticism make us ask whether we are facing the possibility of rethinking the traditional ways to understand the safeguards in order to preserve their essence without devaluing their traditional package but looking for new components to replace or compensate for the so-called “loss” of safeguards. The reflection on technological progress in the field of criminal procedural law indicates the need to rethink, on the basis of fundamental procedural principles, the safeguards that can replace or compensate for those that are in crisis as a result of the intervention of technological progress. Discussions in academic doctrine on the impact of technological interventions on the proceedings as such or on the limits of such interventions refer to the principles of criminal procedure as to a point of reference. In the context of the inferiority of technology, scholarly debate still addresses the issue of whether the court will not gradually become a mere site for the exercise of penal power with the resultant consequences – the deformation of the procedure itself as a physical ritual. In this context, this work seeks to illustrate the relationship between remote criminal proceedings in court and the principle of immediacy, the concept of which is based on the application of different models of criminal procedure (inquisitorial and adversarial), the aim is to assess the challenges posed for legal regulation by the interaction of technological progress with the principles of criminal procedure. The main hypothesis to be tested is that the adoption of remote proceedings is directly linked to the prevailing model of criminal procedure, arguing that the more principles of the inquisitorial model are applied to the criminal process, the more remote criminal trial is acceptable, and conversely, the more the criminal process is based on an adversarial model, more the remote criminal process is seen as incompatible with the principle of immediacy. In order to achieve this goal, the following tasks are set: to identify whether there is a difference in assessing remote proceedings with the immediacy principle between the adversarial model and the inquisitorial model, to analyse the main aspects of the regulation of remote criminal proceedings based on the examples of different countries (for example Lithuania, Italy, etc.).

Keywords: remote criminal proceedings, principle of orality, principle of immediacy, adversarial model inquisitorial model

Procedia PDF Downloads 68

Authors: Muthukuda Arachchige Dona Shiroma Jeeva Shirajanie Niriella

Abstract:

The necessity of protection of the rights of victims of crime is a matter of concerns today. In the criminal justice system, child victims who are subjected to sexual abuse/violence are more vulnerable than the other crime victims. When they go to the police to lodge the complaint and until the end of the court proceedings, these victims are re-victimized in the criminal justice system. The rights of the suspects, accused and convicts are recognized and guaranteed by the constitution under fair trial norm, contemporary penal laws where crime is viewed as an offence against the State and existing criminal justice system in many jurisdictions including Sri Lanka. In this backdrop, a reasonable question arises as to whether the existing criminal justice system, especially which follow the adversarial mode of judicial trial protect the fair trial norm in the criminal justice process. Therefore, this paper intends to discuss the rights of the sexually abused child victims in the criminal justice system in order to restore imbalance between the rights of the wrongdoer and victim and suggest legal reforms to strengthen their rights in the criminal justice system which is essential to end secondary victimization. The paper considers Sri Lanka as a sample to discuss this issue. The paper looks at how the child victims are marginalized in the traditional adversarial model of the justice process, whether the contemporary penal laws adequately protect the right of these victims and whether the current laws set out the provisions to provide sufficient assistance and protection to them. The study further deals with the important principles adopted in international human rights law relating to the protection of the rights of the child victims in sexual offences cases. In this research paper, rights of the child victims in the investigation, trial and post-trial stages in the criminal justice process will be assessed. This research contains an extensive scrutiny of relevant international standards and local statutory provisions. Case law, books, journal articles, government publications such as commissions’ reports under this topic are rigorously reviewed as secondary resources. Further, randomly selected 25 child victims of sexual offences from the decided cases in last two years, police officers from 5 police divisions where the highest numbers of sexual offences were reported in last two years and the judicial officers both Magistrates and High Court Judges from the same judicial zones are interviewed. These data will be analyzed in order to find out the reasons for this specific sexual victimization, needs of these victims in various stages of the criminal justice system, relationship between victimization and offending and the difficulties and problems that these victims come across in criminal justice system. The author argues that the child victims are considerably neglected and their rights are not adequately protected in the adversarial model of the criminal justice process.

Keywords: child victims of sexual violence, criminal justice system, international standards, rights of child victims, Sri Lanka

Procedia PDF Downloads 368

Authors: O. G. Onuoha, O. G. Akagu

Abstract:

The potentials of acha (Digitaria exiles), aya (Cyperus esculentus) and defatted water melon seed (Citrullis lanatus) as a weaning formula was investigated using the following blends for acha, aya and defatted water melon seed respectively in percentage proportion to obtain the weaning formulae; WS1(20:50:30); WS2(30:40:30); WS3(40:30:30); WS4(50:20:30). The result of the chemical analysis showed that; the sample WS1 had the highest value (15.6%) for protein while sample WS4 had the least value (14.1%). The fat content sample WS4 having the highest value (30.8%) while sample WS1 had the least value (27.3%). The ash content sample WS4 had the highest value (3.22%) while sample WS1 had the least value (2.63%). The carbohydrate content showed that sample WS1 having the highest value (50.5%) while sample WS4 had the least value (46.58%). While sample WS4 had the highest energy value (528.32 Kcal) and sample WS2 had the least value (515.06 Kcal). However, all the sample results fell within the dietary daily reference intake for infants between 0-3 years and required only local technology in its production.

Keywords: weaning formula, acha, aya, deffted water melon seed

Procedia PDF Downloads 270

Authors: Agastya Pratap Singh

Abstract:

Generative Adversarial Networks (GANs) have emerged as powerful tools in the fields of image recognition and anomaly detection due to their ability to model complex data distributions and generate realistic images. This systematic review explores recent advancements and applications of GANs in both image recognition and anomaly detection tasks. We discuss various GAN architectures, such as DCGAN, CycleGAN, and StyleGAN, which have been tailored to improve accuracy, robustness, and efficiency in visual data analysis. In image recognition, GANs have been used to enhance data augmentation, improve classification models, and generate high-quality synthetic images. In anomaly detection, GANs have proven effective in identifying rare and subtle abnormalities across various domains, including medical imaging, cybersecurity, and industrial inspection. The review also highlights the challenges and limitations associated with GAN-based methods, such as instability during training and mode collapse, and suggests future research directions to overcome these issues. Through this review, we aim to provide researchers with a comprehensive understanding of the capabilities and potential of GANs in transforming image recognition and anomaly detection practices.

Keywords: generative adversarial networks, image recognition, anomaly detection, DCGAN, CycleGAN, StyleGAN, data augmentation

Procedia PDF Downloads 20

Authors: Jacqueline Rose T. Alipo-on, Francesca Isabelle F. Escobar, Myles Joshua T. Tan, Hezerul Abdul Karim, Nouar Al Dahoul

Abstract:

Electrocardiogram (ECG) signal analysis and processing are crucial in the diagnosis of cardiovascular diseases, which are considered one of the leading causes of mortality worldwide. However, the traditional rule-based analysis of large volumes of ECG data is time-consuming, labor-intensive, and prone to human errors. With the advancement of the programming paradigm, algorithms such as machine learning have been increasingly used to perform an analysis of ECG signals. In this paper, various deep learning algorithms were adapted to classify five classes of heartbeat types. The dataset used in this work is the synthetic MIT-BIH Arrhythmia dataset produced from generative adversarial networks (GANs). Various deep learning models such as ResNet-50 convolutional neural network (CNN), 1-D CNN, and long short-term memory (LSTM) were evaluated and compared. ResNet-50 was found to outperform other models in terms of recall and F1 score using a five-fold average score of 98.88% and 98.87%, respectively. 1-D CNN, on the other hand, was found to have the highest average precision of 98.93%.

Keywords: heartbeat classification, convolutional neural network, electrocardiogram signals, generative adversarial networks, long short-term memory, ResNet-50

Procedia PDF Downloads 128

Authors: Adebayo B., Omotehinse A. O.

Abstract:

The performance and characteristics of blocks produced from dredged sample was investigated. Blocks were produced using appropriate mixes of dredged sample and sharp sand. Some geotechnical properties (moisture content, grain size distribution) of the dredged sample (Igbokoda dredged sample) were determined using the British Standard. The physico-mechanical properties (water absorption, density and compressive strength) of blocks produced were evaluated. The dredged sample is classified as a silty material. Seven replacement levels of sharp sand were considered in the study (SS- Sharp Sand and DS – Dredged Sample) was done with constant amount of cement. 1- 85 % DS and 15 % SS, 2- 70 % DS and 30 % SS, 3- 55 % DS and 45 % SS, 4- 50 % DS and 50 % SS, 5- 45 % DS and 55 % SS, 6- 30 % DS and 70 % SS, 7- 15 % DS and 85 % SS and 8 – IS 100 % with cement; 9 – SS 100 % with cement) of different ages (7 days, 14 days, 21 days and 28 days) for the production of blocks. The compressive strength of the blocks produced ranges between 0.52 MPa to 3.0 MPa and considering the mixes, the highest compressive strength was found in mix of 15 % DS and 85 % SS.

Keywords: dredge sample, silt, sharp sand, block, cement

Procedia PDF Downloads 366

Authors: Riznaldi Akbar

Abstract:

In this study, we compared the performance of the Artificial Neural Network (ANN) model with back-propagation algorithm in correctly predicting in-sample and out-of-sample external debt crisis in Indonesia. We found that exchange rate, foreign reserves, and exports are the major determinants to experiencing external debt crisis. The ANN in-sample performance provides relatively superior results. The ANN model is able to classify correctly crisis of 89.12 per cent with reasonably low false alarms of 7.01 per cent. In out-of-sample, the prediction performance fairly deteriorates compared to their in-sample performances. It could be explained as the ANN model tends to over-fit the data in the in-sample, but it could not fit the out-of-sample very well. The 10-fold cross-validation has been used to improve the out-of-sample prediction accuracy. The results also offer policy implications. The out-of-sample performance could be very sensitive to the size of the samples, as it could yield a higher total misclassification error and lower prediction accuracy. The ANN model could be used to identify past crisis episodes with some accuracy, but predicting crisis outside the estimation sample is much more challenging because of the presence of uncertainty.

Keywords: debt crisis, external debt, artificial neural network, ANN

Procedia PDF Downloads 442

Authors: Esther Chiramal, Kelvin Soh Boon Kai

Abstract:

Explainable AI is a strong strategy implemented to understand complex black-box model predictions in a human-interpretable language. It provides the evidence required to execute the use of trustworthy and reliable AI systems. On the other hand, however, it also opens the door to locating possible vulnerabilities in an AI model. Traditional adversarial text attack uses word substitution, data augmentation techniques, and gradient-based attacks on powerful pre-trained Bidirectional Encoder Representations from Transformers (BERT) variants to generate adversarial sentences. These attacks are generally white-box in nature and not practical as they can be easily detected by humans e.g., Changing the word from “Poor” to “Rich”. We proposed a simple yet effective Grey-box cum Black-box approach that does not require the knowledge of the model while using a set of surrogate Transformer/BERT models to perform the attack using Explainable AI techniques. As Transformers are the current state-of-the-art models for almost all Natural Language Processing (NLP) tasks, an attack generated from BERT1 is transferable to BERT2. This transferability is made possible due to the attention mechanism in the transformer that allows the model to capture long-range dependencies in a sequence. Using the power of BERT generalisation via attention, we attempt to exploit how transformers learn by attacking a few surrogate transformer variants which are all based on a different architecture. We demonstrate that this approach is highly effective to generate semantically good sentences by changing as little as one word that is not detectable by humans while still fooling other BERT models.

Keywords: BERT, explainable AI, Grey-box text attack, transformer

Procedia PDF Downloads 137

Authors: Mirjana Ruppel, Rajendra Persad, Amit Bahl, Sanja Dogramadzi, Chris Melhuish, Lyndon Smith

Abstract:

Multimodal image registration is a profoundly complex task which is why deep learning has been used widely to address it in recent years. However, two main challenges remain: Firstly, the lack of ground truth data calls for an unsupervised learning approach, which leads to the second challenge of defining a feasible loss function that can compare two images of different modalities to judge their level of alignment. To avoid this issue altogether we implement a generative adversarial network consisting of two registration networks GAB, GBA and two discrimination networks DA, DB connected by spatial transformation layers. GAB learns to generate a deformation field which registers an image of the modality B to an image of the modality A. To do that, it uses the feedback of the discriminator DB which is learning to judge the quality of alignment of the registered image B. GBA and DA learn a mapping from modality A to modality B. Additionally, a cycle-consistency loss is implemented. For this, both registration networks are employed twice, therefore resulting in images ˆA, ˆB which were registered to ˜B, ˜A which were registered to the initial image pair A, B. Thus the resulting and initial images of the same modality can be easily compared. A dataset of liver CT and MRI was used to evaluate the quality of our approach and to compare it against learning and non-learning based registration algorithms. Our approach leads to dice scores of up to 0.80 ± 0.01 and is therefore comparable to and slightly more successful than algorithms like SimpleElastix and VoxelMorph.

Keywords: cycle consistency, deformable multimodal image registration, deep learning, GAN

Procedia PDF Downloads 131

Authors: Zdeněk Veselý, Milan Honner, Jiří Mach

Abstract:

The aim of the performed work is to establish the 2D and 3D model of direct unsteady task of sample heat treatment by moving source employing computer model on the basis of finite element method. The complex boundary condition on heat loaded sample surface is the essential feature of the task. Computer model describes heat treatment of the sample during heat source movement over the sample surface. It is started from the 2D task of sample cross section as a basic model. Possibilities of extension from 2D to 3D task are discussed. The effect of the addition of third model dimension on the temperature distribution in the sample is showed. Comparison of various model parameters on the sample temperatures is observed. Influence of heat source motion on the depth of material heat treatment is shown for several velocities of the movement. Presented computer model is prepared for the utilization in laser treatment of machine parts.

Keywords: computer simulation, unsteady model, heat treatment, complex boundary condition, moving heat source

Procedia PDF Downloads 393

Authors: Srinivas Peri, Siva Abhishek Sirivella, Tejaswini Kallakuri, Uzair Ahmad

Abstract:

Effective traffic management and infrastructure planning are crucial for the development of smart cities and intelligent transportation systems. This study addresses the challenge of data scarcity by generating realistic synthetic traffic data using the PeMS-Bay dataset, improving the accuracy and reliability of predictive modeling. Advanced synthetic data generation techniques, including TimeGAN, GaussianCopula, and PAR Synthesizer, are employed to produce synthetic data that replicates the statistical and structural characteristics of real-world traffic. Future integration of Spatial-Temporal Generative Adversarial Networks (ST-GAN) is planned to capture both spatial and temporal correlations, further improving data quality and realism. The performance of each synthetic data generation model is evaluated against real-world data to identify the best models for accurately replicating traffic patterns. Long Short-Term Memory (LSTM) networks are utilized to model and predict complex temporal dependencies within traffic patterns. This comprehensive approach aims to pinpoint areas with low vehicle counts, uncover underlying traffic issues, and inform targeted infrastructure interventions. By combining GAN-based synthetic data generation with LSTM-based traffic modeling, this study supports data-driven decision-making that enhances urban mobility, safety, and the overall efficiency of city planning initiatives.

Keywords: GAN, long short-term memory, synthetic data generation, traffic management

Procedia PDF Downloads 26

Authors: Serge B. Provost

Abstract:

Numerous statistical inference and modeling methodologies are based on sample moments rather than the actual observations. A result justifying the validity of this approach is introduced. More specifically, it will be established that given the first n moments of a sample of size n, one can recover the original n sample points. This implies that a sample of size n and its first associated n moments contain precisely the same amount of information. However, it is efficient to make use of a limited number of initial moments as most of the relevant distributional information is included in them. Two types of density estimation techniques that rely on such moments will be discussed. The first one expresses a density estimate as the product of a suitable base density and a polynomial adjustment whose coefficients are determined by equating the moments of the density estimate to the sample moments. The second one assumes that the derivative of the logarithm of a density function can be represented as a rational function. This gives rise to a system of linear equations involving sample moments, the density estimate is then obtained by solving a differential equation. Unlike kernel density estimation, these methodologies are ideally suited to model ‘big data’ as they only require a limited number of moments, irrespective of the sample size. What is more, they produce simple closed form expressions that are amenable to algebraic manipulations. They also turn out to be more accurate as will be shown in several illustrative examples.

Keywords: density estimation, log-density, polynomial adjustments, sample moments

Procedia PDF Downloads 165

Authors: Z. Jannoo, B. W. Yap, N. Auchoybur, M. A. Lazim

Abstract:

The two common approaches to Structural Equation Modeling (SEM) are the Covariance-Based SEM (CB-SEM) and Partial Least Squares SEM (PLS-SEM). There is much debate on the performance of CB-SEM and PLS-SEM for small sample size and when distributions are non-normal. This study evaluates the performance of CB-SEM and PLS-SEM under normality and non-normality conditions via a simulation. Monte Carlo Simulation in R programming language was employed to generate data based on the theoretical model with one endogenous and four exogenous variables. Each latent variable has three indicators. For normal distributions, CB-SEM estimates were found to be inaccurate for small sample size while PLS-SEM could produce the path estimates. Meanwhile, for a larger sample size, CB-SEM estimates have lower variability compared to PLS-SEM. Under non-normality, CB-SEM path estimates were inaccurate for small sample size. However, CB-SEM estimates are more accurate than those of PLS-SEM for sample size of 50 and above. The PLS-SEM estimates are not accurate unless sample size is very large.

Keywords: CB-SEM, Monte Carlo simulation, normality conditions, non-normality, PLS-SEM

Procedia PDF Downloads 410

Authors: Yoganathan Karthik, Guhanathan Poravi

Abstract:

Colorizing near-infrared (NIR) images poses unique challenges due to the absence of color information and the nuances in light absorption. In this paper, we present an approach to NIR image colorization utilizing a synthetic dataset generated from visible light images. Our method addresses two major challenges encountered in NIR image colorization: accurately colorizing objects with color variations and avoiding over/under saturation in dimly lit scenes. To tackle these challenges, we propose a Generative Adversarial Network (GAN)-based framework that learns to map NIR images to their corresponding colorized versions. The synthetic dataset ensures diverse color representations, enabling the model to effectively handle objects with varying hues and shades. Furthermore, the GAN architecture facilitates the generation of realistic colorizations while preserving the integrity of dimly lit scenes, thus mitigating issues related to over/under saturation. Experimental results on benchmark NIR image datasets demonstrate the efficacy of our approach in producing high-quality colorizations with improved color accuracy and naturalness. Quantitative evaluations and comparative studies validate the superiority of our method over existing techniques, showcasing its robustness and generalization capability across diverse NIR image scenarios. Our research not only contributes to advancing NIR image colorization but also underscores the importance of synthetic datasets and GANs in addressing domain-specific challenges in image processing tasks. The proposed framework holds promise for various applications in remote sensing, medical imaging, and surveillance where accurate color representation of NIR imagery is crucial for analysis and interpretation.

Keywords: computer vision, near-infrared images, automatic image colorization, generative adversarial networks, synthetic data

Procedia PDF Downloads 43

Authors: Mohd Asrul Affendi Bin Abdullah

Abstract:

Sample size calculation is especially important for zero inflated models because a large sample size is required to detect a significant effect with this model. This paper verify how to present percentage of power approximation for categorical and then extended to zero inflated models. Wald test was chosen to determine power sample size of AIDS death rate because it is frequently used due to its approachability and its natural for several major recent contribution in sample size calculation for this test. Power calculation can be conducted when covariates are used in the modeling ‘excessing zero’ data and assist categorical covariate. Analysis of AIDS death rate study is used for this paper. Aims of this study to determine the power of sample size (N = 945) categorical death rate based on parameter estimate in the simulation of the study.

Keywords: power sample size, Wald test, standardize rate, ZINBDR

Procedia PDF Downloads 435

Authors: Getaneh Berie Tarekegn

Abstract:

A precise localization system is crucial for many artificial intelligence Internet of Things (AI-IoT) applications in the era of smart cities. Their applications include traffic monitoring, emergency alarming, environmental monitoring, location-based advertising, intelligent transportation, and smart health care. The most common method for providing continuous positioning services in outdoor environments is by using a global navigation satellite system (GNSS). Due to nonline-of-sight, multipath, and weather conditions, GNSS systems do not perform well in dense urban, urban, and suburban areas.This paper proposes a generative AI-based positioning scheme for large-scale wireless settings using fingerprinting techniques. In this article, we presented a semi-supervised deep convolutional generative adversarial network (S-DCGAN)-based radio map construction method for real-time device localization. It also employed a reliable signal fingerprint feature extraction method with t-distributed stochastic neighbor embedding (t-SNE), which extracts dominant features while eliminating noise from hybrid WLAN and long-term evolution (LTE) fingerprints. The proposed scheme reduced the workload of site surveying required to build the fingerprint database by up to 78.5% and significantly improved positioning accuracy. The results show that the average positioning error of GAILoc is less than 0.39 m, and more than 90% of the errors are less than 0.82 m. According to numerical results, SRCLoc improves positioning performance and reduces radio map construction costs significantly compared to traditional methods.

Keywords: location-aware services, feature extraction technique, generative adversarial network, long short-term memory, support vector machine

Procedia PDF Downloads 59

Authors: Malik Muhammad Arslan, Muneeb Ullah, Dai Shihan, Daniyal Haider, Xiaodong Yang

Abstract:

Chest X-rays are instrumental in the detection and monitoring of a wide array of diseases, including viral infections such as COVID-19, tuberculosis, pneumonia, lung cancer, and various cardiac and pulmonary conditions. To enhance the accuracy of diagnosis, artificial intelligence (AI) algorithms, particularly deep learning models like Convolutional Neural Networks (CNNs), are employed. However, these deep learning models demand a substantial and varied dataset to attain optimal precision. Generative Adversarial Networks (GANs) can be employed to create new data, thereby supplementing the existing dataset and enhancing the accuracy of deep learning models. Nevertheless, GANs have their limitations, such as issues related to stability, convergence, and the ability to distinguish between authentic and fabricated data. In order to overcome these challenges and advance the detection and classification of CXR normal and abnormal images, this study introduces a distinctive technique known as DCWGAN (Diverse Conditional Wasserstein GAN) for generating synthetic chest X-ray (CXR) images. The study evaluates the effectiveness of this Idiosyncratic DCWGAN technique using the ResNet50 model and compares its results with those obtained using the traditional GAN approach. The findings reveal that the ResNet50 model trained on the DCWGAN-generated dataset outperformed the model trained on the classic GAN-generated dataset. Specifically, the ResNet50 model utilizing DCWGAN synthetic images achieved impressive performance metrics with an accuracy of 0.961, precision of 0.955, recall of 0.970, and F1-Measure of 0.963. These results indicate the promising potential for the early detection of diseases in CXR images using this Inimitable approach.

Keywords: CNN, classification, deep learning, GAN, Resnet50

Procedia PDF Downloads 88

Authors: Muneeb Ullah, Daishihan, Xiadong Young

Abstract:

Deep learning plays a crucial role in identifying COVID-19 and preventing its spread. To improve the accuracy of COVID-19 diagnoses, it is important to have access to a sufficient number of training images of CXRs (chest X-rays) depicting the disease. However, there is currently a shortage of such images. To address this issue, this paper introduces COVID-19 GAN, a model that uses generative adversarial networks (GANs) to generate realistic CXR images of COVID-19, which can be used to train identification models. Initially, a generator model is created that uses digressive channels to generate images of CXR scans for COVID-19. To differentiate between real and fake disease images, an efficient discriminator is developed by combining the dense connectivity strategy and instance normalization. This approach makes use of their feature extraction capabilities on CXR hazy areas. Lastly, the deep regret gradient penalty technique is utilized to ensure stable training of the model. With the use of 4,062 grape leaf disease images, the Leaf GAN model successfully produces 8,124 COVID-19 CXR images. The COVID-19 GAN model produces COVID-19 CXR images that outperform DCGAN and WGAN in terms of the Fréchet inception distance. Experimental findings suggest that the COVID-19 GAN-generated CXR images possess noticeable haziness, offering a promising approach to address the limited training data available for COVID-19 model training. When the dataset was expanded, CNN-based classification models outperformed other models, yielding higher accuracy rates than those of the initial dataset and other augmentation techniques. Among these models, ImagNet exhibited the best recognition accuracy of 99.70% on the testing set. These findings suggest that the proposed augmentation method is a solution to address overfitting issues in disease identification and can enhance identification accuracy effectively.

Keywords: classification, deep learning, medical images, CXR, GAN.

Procedia PDF Downloads 96

Authors: Cezary Kulesza, Katarzyna Lapinska

Abstract:

Regarding the nature of the notion of fair trial, one must see the source of the fair trial principle in the following acts of international law: art. 6 of the ECHR of 1950 and art.14 the International Covenant on Civil and Political Rights of 1966, as well as in art. 45 of the Polish Constitution. However, the problem is that the above-mentioned acts essentially apply the principle of a fair trial to the main hearing and not to appeal proceedings. Therefore, the main thesis of the work is to answer the question whether the Polish model of appeal proceedings is fair. The paper presents the problem of fair appeal proceedings in Poland in comparative perspective. Thus, the authors discuss the basic features of English, German and Russian appeal systems. The matter is also analysed in the context of the last reforms of Polish criminal procedure, because since 2013 Polish parliament has significantly changed criminal procedure almost three times: by the Act of 27th September, 2013, the Act of 20th February, 2015 which came into effect on 1st July, 2015 and the Act of 11th March, 2016. The most astonishing is that these three amendments have been varying from each other – changing Polish criminal procedure to more adversarial one and then rejecting all measures just involved in previous acts. Additional intent of the Polish legislator was amending the forms of plea bargaining: conviction of the defendant without trial or voluntary submission to a penalty, which were supposed to become tools allowing accelerating the criminal process and, at the same time, implementing the principle of speedy procedure. The next part of the paper will discuss the matter, how the changes of plea bargaining and the main trial influenced the appellate procedure in Poland. The authors deal with the right to appeal against judgments issued in negotiated case-ending settlements in the light of Art. 2 of Protocol No. 7 to the ECHR and the Polish Constitution. The last part of the presentation will focus on the basic changes in the appeals against judgments issued after the main trial. This part of the paper also presents the results of examination of court files held in the Polish Appeal Courts in Białystok, Łódź and Warsaw. From these considerations it is concluded that the Polish CCP of 1997 in ordinary proceedings basically meets both standards: the standard adopted in Protocol No. 7 of the Convention and the Polish constitutional standard. But the examination of case files shows in particular the following phenomena: low effectiveness of appeals and growing stability of the challenged judgments of district courts, extensive duration of appeal proceedings and narrow scope of evidence proceedings before the appellate courts. On the other hand, limitations of the right to appeal against the judgments issued in consensual modes of criminal proceedings justify the fear that such final judgments may violate the principle of criminal accurate response or the principle of material truth.

Keywords: adversarial trial, appeal, ECHR, England, evidence, fair trial, Germany, Polish criminal procedure, reform, Russia

Procedia PDF Downloads 147

Authors: Katerina Zaharieva, Vicente Rives, Martin Tsvetkov, Raquel Trujillano, Boris Kunev, Ivan Mitov, Maria Milanova, Zara Cherkezova-Zheleva

Abstract:

The nanostructured cobalt ferrite-type materials Sample A - Co0.25Fe2.75O4, Sample B - Co0.5Fe2.5O4, and Sample C - CoFe2O4 were prepared by co-precipitation in our previous investigations. The co-precipitated Sample B and Sample C were mechanochemically activated in order to produce Sample D - Co0.5Fe2.5O4 and Sample E- CoFe2O4. The PXRD, Moessbauer and FTIR spectroscopies, specific surface area determination by the BET method, thermal analysis, element chemical analysis and temperature-programmed reduction were used to investigate the prepared nano-sized samples. The changes of the Malachite green dye concentration during reaction of the photocatalytic decolorization using nanostructured cobalt ferrite-type catalysts with different chemical composition are included. The photocatalytic results show that the increase in the degree of incorporation of cobalt ions in the magnetite host structure for co-precipitated cobalt ferrite-type samples results in an increase of the photocatalytic activity: Sample A (4 х10-3 min-1) < Sample B (5 х10-3 min-1) < Sample C (7 х10-3 min-1). Mechanochemically activated photocatalysts showed a higher activity than the co-precipitated ferrite materials: Sample D (16 х10-3 min-1) > Sample E (14 х10-3 min-1) > Sample C (7 х10-3 min-1) > Sample B (5 х10-3 min-1) > Sample A (4 х10-3 min-1). On decreasing the degree of substitution of iron ions by cobalt ones a higher sorption ability of the dye after the dark period for the co-precipitated cobalt ferrite materials was observed: Sample C (72 %) < Sample B (78 %) < Sample A (80 %). Mechanochemically treated ferrite catalysts and co-precipitated Sample B possess similar sorption capacities, Sample D (78 %) ~ Sample E (78 %) ~ Sample B (78 %). The prepared nano-sized cobalt ferrite-type materials demonstrate good photocatalytic and sorption properties. Mechanochemically activated Sample D - Co0.5Fe2.5O4 (16х10-3 min-1) and Sample E-CoFe2O4 (14х10-3 min-1) possess higher photocatalytic activity than that of the most common used UV-light catalyst Degussa P25 (12х10-3 min-1). The dependence of the photo-catalytic activity and sorption properties on the preparation method and different degree of substitution of iron ions by cobalt ions in synthesized cobalt ferrite samples is established. The mechanochemical activation leads to formation of nano-structured cobalt ferrite-type catalysts (Sample D and Sample E) with higher rate constants than those of the ferrite materials (Sample A, Sample B, and Sample C) prepared by the co-precipitation procedure. The increase in the degree of substitution of iron ions by cobalt ones leads to improved photocatalytic properties and lower sorption capacities of the co-precipitated ferrite samples. The good sorption properties between 72 and 80% of the prepared ferrite-type materials show that they could be used as potential cheap absorbents for purification of polluted waters.

Keywords: nanodimensional cobalt ferrites, photocatalyst, synthesis, mechanochemical activation

Procedia PDF Downloads 264

Authors: Getaneh Berie Tarekegn

Abstract:

A precise localization system is crucial for many artificial intelligence Internet of Things (AI-IoT) applications in the era of smart cities. Their applications include traffic monitoring, emergency alarming, environmental monitoring, location-based advertising, intelligent transportation, and smart health care. The most common method for providing continuous positioning services in outdoor environments is by using a global navigation satellite system (GNSS). Due to nonline-of-sight, multipath, and weather conditions, GNSS systems do not perform well in dense urban, urban, and suburban areas.This paper proposes a generative AI-based positioning scheme for large-scale wireless settings using fingerprinting techniques. In this article, we presented a novel semi-supervised deep convolutional generative adversarial network (S-DCGAN)-based radio map construction method for real-time device localization. We also employed a reliable signal fingerprint feature extraction method with t-distributed stochastic neighbor embedding (t-SNE), which extracts dominant features while eliminating noise from hybrid WLAN and long-term evolution (LTE) fingerprints. The proposed scheme reduced the workload of site surveying required to build the fingerprint database by up to 78.5% and significantly improved positioning accuracy. The results show that the average positioning error of GAILoc is less than 39 cm, and more than 90% of the errors are less than 82 cm. That is, numerical results proved that, in comparison to traditional methods, the proposed SRCLoc method can significantly improve positioning performance and reduce radio map construction costs.

Keywords: location-aware services, feature extraction technique, generative adversarial network, long short-term memory, support vector machine

Procedia PDF Downloads 71

Authors: Emmanuel Ogundimu, Esther Akinlabi, Mutiu Erinosho

Abstract:

The aim of this paper is to study the effect of welding current on the microstructure and the mechanical properties. Material characterizations were conducted on a 6 mm thick plates of type-304 austenite stainless steel, welded by TIG welding process at two different welding currents of 150 A (Sample F3) and 170 A (Sample F4). The tensile strength and the elongation obtained from sample F4 weld were approximately 584 MPa and 19.3 %; which were higher than sample F3 weld. The average microhardness value of sample F4 weld was found to be 235.7 HV, while that of sample F3 weld was 233.4 HV respectively. Homogenous distribution of iron (Fe), chromium (Cr) and nickel (Ni) were observed at the welded joint of the two samples. The energy dispersive spectroscopy (EDS) analysis revealed that Fe, Cr, and Ni made up the composition formed in the weld zone. The optimum welding current of 170 A for TIG welding of type-304 austenite stainless steel can be recommended for high-tech industrial applications.

Keywords: microhardness, microstructure, tensile, MIG welding, process, tensile, shear stress TIG welding, TIG-MIG welding

Procedia PDF Downloads 194

Authors: Getaneh Berie Tarekegn

Abstract:

A precise localization system is crucial for many artificial intelligence Internet of Things (AI-IoT) applications in the era of smart cities. Their applications include traffic monitoring, emergency alarming, environmental monitoring, location-based advertising, intelligent transportation, and smart health care. The most common method for providing continuous positioning services in outdoor environments is by using a global navigation satellite system (GNSS). Due to nonline-of-sight, multipath, and weather conditions, GNSS systems do not perform well in dense urban, urban, and suburban areas.This paper proposes a generative AI-based positioning scheme for large-scale wireless settings using fingerprinting techniques. In this article, we presented a novel semi-supervised deep convolutional generative adversarial network (S-DCGAN)-based radio map construction method for real-time device localization. We also employed a reliable signal fingerprint feature extraction method with t-distributed stochastic neighbor embedding (t-SNE), which extracts dominant features while eliminating noise from hybrid WLAN and long-term evolution (LTE) fingerprints. The proposed scheme reduced the workload of site surveying required to build the fingerprint database by up to 78.5% and significantly improved positioning accuracy. The results show that the average positioning error of GAILoc is less than 39 cm, and more than 90% of the errors are less than 82 cm. That is, numerical results proved that, in comparison to traditional methods, the proposed SRCLoc method can significantly improve positioning performance and reduce radio map construction costs.

Keywords: location-aware services, feature extraction technique, generative adversarial network, long short-term memory, support vector machine

Procedia PDF Downloads 75