Search results for: image generation

Authors: Parisa Mansour

Abstract:

The coronavirus disease 2019 (COVID-19) was discovered and rapidly spread to various countries around the world since the end of 2019. Computed tomography (CT) images have been used as an important alternative to the time-consuming RT. PCR test. However, manual segmentation of CT images alone is a major challenge as the number of suspected cases increases. Thus, accurate and automatic segmentation of COVID-19 infections is urgently needed. Because the imaging features of the COVID-19 infection are different and similar to the background, existing medical image segmentation methods cannot achieve satisfactory performance. In this work, we try to build a deep convolutional neural network adapted for the segmentation of chest CT images with COVID-19 infections. First, we maintain a large and novel chest CT image database containing 165,667 annotated chest CT images from 861 patients with confirmed COVID-19. Inspired by the observation that the boundary of an infected lung can be improved by global intensity adjustment, we introduce a feature variable block into the proposed deep CNN, which adjusts the global features of features to segment the COVID-19 infection. The proposed PV array can effectively and adaptively improve the performance of functions in different cases. We combine features of different scales by proposing a progressive atrocious space pyramid fusion scheme to deal with advanced infection regions with various aspects and shapes. We conducted experiments on data collected in China and Germany and showed that the proposed deep CNN can effectively produce impressive performance.

Keywords: chest, COVID-19, chest Image, coronavirus, CT image, chest CT

Procedia PDF Downloads 57

Authors: A. J. S. P. Nileema, S. Kulatunga , S. H. Palihawadana

Abstract:

Computer aided detection (CAD) system was developed for the diagnosis of pulmonary tuberculosis using digital chest X-rays with MATLAB image processing techniques using a statistical approach. The study comprised of 200 digital chest radiographs collected from the National Hospital for Respiratory Diseases - Welisara, Sri Lanka. Pre-processing was done to remove identification details. Lung fields were segmented and then divided into four quadrants; right upper quadrant, left upper quadrant, right lower quadrant, and left lower quadrant using the image processing techniques in MATLAB. Contrast, correlation, homogeneity, energy, entropy, and maximum probability texture features were extracted using the gray level co-occurrence matrix method. Descriptive statistics and normal distribution analysis were performed using SPSS. Depending on the radiologists’ interpretation, chest radiographs were classified manually into PTB - positive (PTBP) and PTB - negative (PTBN) classes. Features with standard normal distribution were analyzed using an independent sample T-test for PTBP and PTBN chest radiographs. Among the six features tested, contrast, correlation, energy, entropy, and maximum probability features showed a statistically significant difference between the two classes at 95% confidence interval; therefore, could be used in the classification of chest radiograph for PTB diagnosis. With the resulting value ranges of the five texture features with normal distribution, a classification algorithm was then defined to recognize and classify the quadrant images; if the texture feature values of the quadrant image being tested falls within the defined region, it will be identified as a PTBP – abnormal quadrant and will be labeled as ‘Abnormal’ in red color with its border being highlighted in red color whereas if the texture feature values of the quadrant image being tested falls outside of the defined value range, it will be identified as PTBN–normal and labeled as ‘Normal’ in blue color but there will be no changes to the image outline. The developed classification algorithm has shown a high sensitivity of 92% which makes it an efficient CAD system and with a modest specificity of 70%.

Keywords: chest radiographs, computer aided detection, image processing, pulmonary tuberculosis

Procedia PDF Downloads 126

Authors: Mohammad Esmaeilpour

Abstract:

One of the important open problems in the field of medical image processing is detection and quantification of small changes. In this poster, we try to investigate that, how the algebraic decomposition techniques can be used for semiautomatically detecting and quantifying subtle changes in Magnetic Resonance (MR) neuroimaging volumes. We mostly focus on the low-rank values of the matrices achieved from decomposing MR image pairs during a period of time. Besides, a skillful neuroradiologist will help the algorithm to distinguish between noises and small changes.

Keywords: magnetic resonance neuroimaging, subtle change detection and quantification, algebraic decomposition, basis functions

Procedia PDF Downloads 474

Authors: Karima Qayumi, Alex Norta

Abstract:

The rapid generation of high volume and a broad variety of data from the application of new technologies pose challenges for the generation of business-intelligence. Most organizations and business owners need to extract data from multiple sources and apply analytical methods for the purposes of developing their business. Therefore, the recently decentralized data management environment is relying on a distributed computing paradigm. While data are stored in highly distributed systems, the implementation of distributed data-mining techniques is a challenge. The aim of this technique is to gather knowledge from every domain and all the datasets stemming from distributed resources. As agent technologies offer significant contributions for managing the complexity of distributed systems, we consider this for next-generation data-mining processes. To demonstrate agent-based business intelligence operations, we use agent-oriented modeling techniques to develop a new artifact for mining massive datasets.

Keywords: agent-oriented modeling (AOM), business intelligence model (BIM), distributed data mining (DDM), multi-agent system (MAS)

Procedia PDF Downloads 432

Authors: Mohammad A. U. Khan, Tariq M. Khan, Yinan Kong

Abstract:

Fingerprint image enhancement is one of the most important step in an automatic fingerprint identification recognition (AFIS) system which directly affects the overall efficiency of AFIS. The conventional fingerprint enhancement like Gabor and Anisotropic filters do fill the gaps in ridge lines but they fail to tackle scar lines. To deal with this problem we are proposing a method for enhancing the ridges and valleys with scar so that true minutia points can be extracted with accuracy. Our results have shown an improved performance in terms of enhancement.

Keywords: fingerprint image enhancement, removing noise, coherence, enhanced diffusion

Procedia PDF Downloads 516

Authors: Sami M. Alshareef

Abstract:

The rapid growth of smart grid technology has brought significant advancements to the power industry. However, with the increasing interconnectivity and reliance on information and communication technologies, smart grids have become vulnerable to cyber-attacks, posing significant threats to the reliable operation of power systems. Among the critical components of smart grids, the Automatic Generation Control (AGC) system plays a vital role in maintaining the balance between generation and load demand. Therefore, protecting the AGC system from cyber threats is of paramount importance to maintain grid stability and prevent disruptions. Traditional security measures often fall short in addressing sophisticated and evolving cyber threats, necessitating the exploration of innovative approaches. Machine learning, with its ability to analyze vast amounts of data and learn patterns, has emerged as a promising solution to enhance AGC system security. Therefore, this research proposal aims to address the challenges associated with detecting and mitigating cyber-attacks on AGC in smart grids by leveraging machine learning techniques on automatic generation control of two-area power systems. By utilizing historical data, the proposed system will learn the normal behavior patterns of AGC and identify deviations caused by cyber-attacks. Once an attack is detected, appropriate mitigation strategies will be employed to safeguard the AGC system. The outcomes of this research will provide power system operators and administrators with valuable insights into the vulnerabilities of AGC systems in smart grids and offer practical solutions to enhance their cyber resilience.

Keywords: machine learning, cyber-attacks, automatic generation control, smart grid

Procedia PDF Downloads 85

Authors: Rominkumar Busa, Shahira K. C., Lijiya A.

Abstract:

Text recognition is an important area in computer vision which deals with detecting and recognising text from an image. The Optical Character Recognition (OCR) is a saturated area these days and with very good text recognition accuracy. However the same OCR methods when applied on text with small font sizes like the text data of chart images, the recognition rate is less than 30%. In this work, aims to extract small text in images using the deep learning model, CRNN with CTC loss. The text recognition accuracy is found to improve by applying image enhancement by super resolution prior to CRNN model. We also observe the text recognition rate further increases by 18% by applying the proposed method, which involves super resolution and character segmentation followed by CRNN with CTC loss. The efficiency of the proposed method shows that further pre-processing on chart image text and other small text images will improve the accuracy further, thereby helping text extraction from chart images.

Keywords: small text extraction, OCR, scene text recognition, CRNN

Procedia PDF Downloads 125

Authors: Halimatu S. Abdullahi, Ray E. Sheriff, Fatima Mahieddine

Abstract:

Agriculture is essential to the continuous existence of human life as they directly depend on it for the production of food. The exponential rise in population calls for a rapid increase in food with the application of technology to reduce the laborious work and maximize production. Technology can aid/improve agriculture in several ways through pre-planning and post-harvest by the use of computer vision technology through image processing to determine the soil nutrient composition, right amount, right time, right place application of farm input resources like fertilizers, herbicides, water, weed detection, early detection of pest and diseases etc. This is precision agriculture which is thought to be solution required to achieve our goals. There has been significant improvement in the area of image processing and data processing which has being a major challenge. A database of images is collected through remote sensing, analyzed and a model is developed to determine the right treatment plans for different crop types and different regions. Features of images from vegetations need to be extracted, classified, segmented and finally fed into the model. Different techniques have been applied to the processes from the use of neural network, support vector machine, fuzzy logic approach and recently, the most effective approach generating excellent results using the deep learning approach of convolution neural network for image classifications. Deep Convolution neural network is used to determine soil nutrients required in a plantation for maximum production. The experimental results on the developed model yielded results with an average accuracy of 99.58%.

Keywords: convolution, feature extraction, image analysis, validation, precision agriculture

Procedia PDF Downloads 316

Authors: Moncef Balghouthi, Mahmoud Ben Amara, Abdessalem Ben Hadj Ali, Amenallah Guizani

Abstract:

Concentrated solar power technology constitutes an interesting option to meet a part of future energy demand, especially when considering the high levels of solar radiation and clearness index that are available particularly in Tunisia. In this work, we present three experimental prototypes of solar concentrators installed in the research center of energy CRTEn in Tunisia. Two are medium temperature parabolic trough solar collector used to drive a cooling installation and for steam generation. The third is a parabolic dish concentrator used for hybrid generation of thermal and electric power. Optical and thermal evaluations were presented. Solutions and possibilities to construct locally the mirrors of the concentrator were discussed. In addition, the enhancement of the performances of the receivers by nano selective absorption coatings was studied. The improvement of heat transfer between the receiver and the heat transfer fluid was discussed for each application.

Keywords: solar concentrators, optical and thermal evaluations, cooling and process heat, hybrid thermal and electric generation

Procedia PDF Downloads 255

Authors: Thomas Louis, Irina Primac, Florent Morfoisse, Tania Durre, Silvia Blacher, Agnes Noel

Abstract:

In vitro and in vivo lymphangiogenesis assays are essential for the identification of potential lymphangiogenic agents and the screening of pharmacological inhibitors. In the present study, we analyse three biological models: in vitro lymphatic endothelial cell spheroids, in vivo ear sponge assay, and in vivo lymph node colonisation by tumour cells. These assays provide suitable 3D models to test pro- and anti-lymphangiogenic factors or drugs. 3D images were acquired by confocal laser scanning and light sheet fluorescence microscopy. Virtual scan microscopy followed by 3D reconstruction by image aligning methods was also used to obtain 3D images of whole large sponge and ganglion samples. 3D reconstruction, image segmentation, skeletonisation, and other image processing algorithms are described. Fixed and time-lapse imaging techniques are used to analyse lymphatic endothelial cell spheroids behaviour. The study of cell spatial distribution in spheroid models enables to detect interactions between cells and to identify invasion hierarchy and guidance patterns. Global measurements such as volume, length, and density of lymphatic vessels are measured in both in vivo models. Branching density and tortuosity evaluation are also proposed to determine structure complexity. Those properties combined with vessel spatial distribution are evaluated in order to determine lymphangiogenesis extent. Lymphatic endothelial cell invasion and lymphangiogenesis were evaluated under various experimental conditions. The comparison of these conditions enables to identify lymphangiogenic agents and to better comprehend their roles in the lymphangiogenesis process. The proposed methodology is validated by its application on the three presented models.

Keywords: 3D image segmentation, 3D image skeletonisation, cell invasion, confocal microscopy, ear sponges, light sheet microscopy, lymph nodes, lymphangiogenesis, spheroids

Procedia PDF Downloads 378

Authors: Tamseela Habib, Muhammad Amjad, Muhammad Edokali, Masome Moeni, Olivia Pickup, Ali Hassanpour

Abstract:

Nanofluid-assisted steam generation is rapidly attracting attention amongst the scientific community since it can be applied in a wide range of industrial processes. Because of its high absorption rate of solar energy, nanoparticle-based solar steam generation could be a major contributor to many applications, including water desalination, sterilization and power generation. Lithium bromide-based iron oxide nanofluids have been previously studied in steam generation, which showed promising results. However, the efficiency of the system could be improved if a more heat-conductive nanofluid system could be utilised. In the current paper, we report on an experimental investigation of the photothermal conversion properties of functionalised Copper oxide (CuO) nanoparticles used in Lithium Bromide salt solutions. CuO binary nanofluid was prepared by chemical functionalization with polyethyleneimine (PEI). Long-term stability evaluation of prepared binary nanofluid was done by a high-speed centrifuge analyser which showed a 0.06 Instability index suggesting low agglomeration and sedimentation tendencies. This stability is also supported by the measurements from dynamic light scattering (DLS), transmission electron microscope (TEM), and ultraviolet-visible (UV-Vis) spectrophotometer. The fluid rheology is also characterised, which suggests the system exhibits a Newtonian fluid behavior. The photothermal conversion efficiency of different concentrations of CuO was experimentally investigated under a solar simulator. Experimental results reveal that the binary nanofluid in this study can remarkably increase the solar energy trapping efficiency and evaporation rate as compared to conventional fluids due to localized solar energy harvesting by the surface of the nanofluid. It was found that 0.1wt% CuO NP is the optimum nanofluid concentration for enhanced sensible and latent heat efficiencies.

Keywords: nanofluids, vapor absorption refrigeration system, steam generation, high salinity

Procedia PDF Downloads 84

Authors: Junjie Liu, David Selby, Mark Obermajer, Andy Mort

Abstract:

The inaugural application of Re-Os dating, which is based on the beta decay of 187Re to 187Os with a long half-life of 41.577 ± 0.12 Byr and initially used for sulphide minerals and organic rich rocks, to petroleum systems was performed on bitumen of the Polaris Mississippi Valley Type Pb-Zn deposit, Canada. To further our understanding of the Re-Os system and its application to petroleum systems, here we present a study on Duvernay Petroleum System, Western Canadian Sedimentary Basin. The Late Devonian Duvernay Formation organic-rich shales are the only source of the petroleum system. The Duvernay shales reached maturation only during the Laramide Orogeny (80 – 35 Ma) and the generated oil migrated short distances into the interfingering Leduc reefs and overlying Nisku carbonates with no or little secondary alteration post oil-generation. Although very low in Re and Os, the asphaltenes of Duvernay-sourced Leduc and Nisku oils define a Laramide Re-Os age. In addition, the initial Os isotope compositions of the oil samples are similar to that of the Os isotope composition of the Duvernay Formation at the time of oil generation, but are very different to other oil-prone intervals of the basin, showing the ability of the Os isotope composition as an inorganic oil-source correlation tool. In summary, the ability of the Re-Os geochronometer to record the timing of oil generation and trace the source of an oil is confirmed in the Re-Os study of Duvernay Petroleum System.

Keywords: Duvernay petroleum system, oil generation, oil-source correlation, Re-Os

Procedia PDF Downloads 310

Authors: Syed Bilawal Ali Shah

Abstract:

The investigation of the hydrocarbon source rock potential of Eocene-Paleocene formations of Potwar Basin, part of Upper Indus Basin Pakistan, was done using geochemical and petrological techniques. Analysis was performed on forty-five core-cutting samples from two wells. The sequences analysed are Sakesar, Lockhart and Patala formations of Potwar Basin. Patala Formation is one of Potwar Basin's major petroleum-bearing source rocks. The Lockhart Formation samples VR (%Ro) and Tmax data indicate that the formation is early mature to immature for petroleum generation for hydrocarbon generation; samples from the Patala and Sakesar formations, however, have a peak oil generation window and an early maturity (oil window). With 3.37 weight percent mean TOC and HI levels up to 498 mg HC/g TOC, the source rock characteristics of the Sakesar and Patala formations generally exhibit good to very strong petroleum generative potential. The majority of sediments representing Lockhart Formation have 1.5 wt.% mean TOC having fair to good potential with HI values ranging between 203-498 mg HC/g TOC. 1. The analysed sediments of all formations possess primarily mixed Type II/III and Type III kerogen. Analysed sediments indicate that both the Sakesar and Patala formations can possess good oil-generation potential and may act as an oil source rock in the Potwar Basin.

Keywords: Potwar Basin, Patala Shale, Rock-Eval pyrolysis, Indus Basin, VR %Ro

Procedia PDF Downloads 88

Authors: G. V. Siva Krishna Rao, B. Srinivasa Rao

Abstract:

Electrical energy is vital in every aspect of day-to-day life. Keen interest is taken on all possible sources of energy from which it can be generated and this led to the encouragement of generating electrical power using renewable energy resources such as solar, tidal waves and wind energy. Due to the increasing interest on renewable sources in recent times, the studies on integration of distributed generation to the power grid have rapidly increased. Distributed Generation (DG) is a promising solution to many power system problems such as voltage regulation, power loss and reduction in operational cost, etc. To reduce production cost, it is important to minimize the losses by determining the location and size of local generators to be placed in the radial distribution systems. In this paper, reduction of production cost by optimal size of DG unit operated at optimal power factor is dealt. The optimal size of the DG unit is calculated analytically using approximate reasoning suitable nodes and DG placement to minimize production cost with minimum loss is determined by fuzzy technique. Total Cost of Power generation is compared with and without DG unit for 1 year duration. The suggested method is programmed under MATLAB software and is tested on IEEE 33 bus system and the results are presented.

Keywords: distributed generation, operational cost, exact loss formula, optimum size, optimum location

Procedia PDF Downloads 484

Authors: Hussain Sajid, Jung-Hun Shin, Kum-Won Cho

Abstract:

Image super-resolution is the most common computer vision problem with many important applications. Generative adversarial networks (GANs) have promoted remarkable advances in single-image super-resolution (SR) by recovering photo-realistic images. However, high memory requirements of GAN-based SR (mainly generators) lead to performance degradation and increased energy consumption, making it difficult to implement it onto resource-constricted devices. To relieve such a problem, In this paper, we introduce an optimized and highly efficient architecture for SR-GAN (generator) model by utilizing model compression techniques such as Knowledge Distillation and pruning, which work together to reduce the storage requirement of the model also increase in their performance. Our method begins with distilling the knowledge from a large pre-trained model to a lightweight model using different loss functions. Then, iterative weight pruning is applied to the distilled model to remove less significant weights based on their magnitude, resulting in a sparser network. Knowledge Distillation reduces the model size by 40%; pruning then reduces it further by 18%. To accelerate the learning process, we employ the Horovod framework for distributed training on a cluster of 2 nodes, each with 8 GPUs, resulting in improved training performance and faster convergence. Experimental results on various benchmarks demonstrate that the proposed compressed model significantly outperforms state-of-the-art methods in terms of peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), and image quality for x4 super-resolution tasks.

Keywords: single-image super-resolution, generative adversarial networks, knowledge distillation, pruning

Procedia PDF Downloads 96

Authors: Achmad Muchadam Fahham, Sony Hendra Permana

Abstract:

Millennial Muslims are a generation of young people between 20-30 years. They will play an important role in various aspects of life for the next 10 to 20 years. In Indonesia, the population of this generation is quite large and in the next ten to twenty years they will occupy strategic position in various fields of social, economic and political life. One of the characteristics of the millenials generation are always connected to the internet and independence to learn anything from the internet. In terms of religion, the majority of millennial are Muslim. In digital era, the generation of millenial Muslim is vulnerable to the influence of radical Islamic thinking because of their easy access to that thought on social media, new media, and the books they read. This study seeks to examine the religious views of millennial Muslim women in four main focuses, namely religious identity, religious leaders, the role of the state on religious issues, and religious radicalism. This study was conducted with a qualitative approach, the data collection was carried out by the interview method. The study was conducted in Jakarta, mainly in religious study groups located in several mosques and shopping center in Jakarta. This study is expected to portray the religious views of millennial Muslim women, especially their commitment to Islamic identity, their views on the authority of religious leaders, the role of the state in various religious problems, and religious radicalism.

Keywords: millenial Muslims, radicalism, muslim mowen, religious identity

Procedia PDF Downloads 152

Authors: R. K. D. G. Kaluarachchi

Abstract:

The generation of solid waste and its effective management are debated topics in Sri Lanka as well as in the global environment. It was estimated that the most of the waste generated in global was originated from construction and demolition of buildings. Thus, the proportion of construction waste in solid waste generation cannot be underestimated. The construction waste, which is the by-product generated and removed from work sites is collected in direct and indirect processes. Hence, the objectives of this research are to identify the proportion of construction waste which can be reused and identify the methods to reduce the waste generation without reducing the quality of the process. A 6-storey building construction site was selected for this research. The site was divided into six zones depending on the process. Ten waste materials were identified by considering the adverse effects on safety and health of people and the economic value of them. The generated construction waste in each zone was recorded per week for a period of five months. The data revealed that sand, cement, wood used for form work and rusted steel rods were the generated waste which has higher economic value in all zones. Structured interviews were conducted to gather information on how the materials are categorized as waste and the capability of reducing, reusing and recycling the waste. It was identified that waste is generated in following processes; ineffective storage of material for a longer time and improper handling of material during the work process. Further, the alteration of scheduled activities of construction work also yielded more waste. Finally, a proper management of construction waste is suggested to reduce and reuse waste.

Keywords: construction-waste, effective management, reduce, reuse

Procedia PDF Downloads 202

Authors: M. Nageswara Rao, V. S. N. K. Chaitanya, K. Amarendranath

Abstract:

This paper presents an optimal allocation and sizing of Distributed Generation (DG) in Radial Distribution Network (RDN) for total power loss minimization and enhances the voltage profile of the system. The two main important part of this study first is to find optimal allocation and second is optimum size of DG. The locations of DGs are identified by Analytical expressions and crow search algorithm has been employed to determine the optimum size of DG. In this study, the DG has been placed on single and multiple allocations.CSA is a meta-heuristic algorithm inspired by the intelligent behavior of the crows. Crows stores their excess food in different locations and memorizes those locations to retrieve it when it is needed. They follow each other to do thievery to obtain better food source. This analysis is tested on IEEE 33 bus and IEEE 69 bus under MATLAB environment and the results are compared with existing methods.

Keywords: analytical expression, distributed generation, crow search algorithm, power loss, voltage profile

Procedia PDF Downloads 235

Authors: Iyad M. Muslih, Yehya Abdellatif, Sara Qutishat

Abstract:

Renewable energy and in particular solar photovoltaic energy is emerging as a reasonable power generation source. The intermittent and unpredictable nature of solar energy can represent a serious challenge to the utility grids, specifically at relatively high penetration. To minimize the impact of PV power systems on the grid, self-consumption is encouraged. Self-consumption can be improved by matching the PV power generation with the electrical load consumption profile. This study will focus in studying different load profiles and comparing them to typical solar PV power generation at the selected sites with the purpose of analyzing the mismatch in consumption load profile for different users; residential, commercial, and industrial versus the solar photovoltaic output generation. The PV array orientation can be adjusted to reduce the mismatch effects. The orientation shift produces a corresponding shift in the energy production curve. This shift has a little effect on the mismatch for residential loads due to the fact the peak load occurs at night due to lighting loads. This minor gain does not justify the power production loss associated with the orientation shift. The orientation shift for both commercial and industrial cases lead to valuable decrease in the mismatch effects. Such a design is worth considering for reducing grid penetration. Furthermore, the proposed orientation shift yielded better results during the summer time due to the extended daylight hours.

Keywords: grid impact, HOMER, power mismatch, solar PV energy

Procedia PDF Downloads 604

Authors: Nabilah Ibrahim, Khaliza Musa

Abstract:

The increment thickness of intima-media thickness (IMT) which involves the changes of diameter of the carotid artery is one of the early symptoms of the atherosclerosis lesion. The manual measurement of arterial diameter is time consuming and lack of reproducibility. Thus, this study reports the automatic approach to find the arterial diameter behavior for different gender, and body mass index (BMI) categories, focus on tracked region. BMI category is divided into underweight, normal, and overweight categories. Canny edge detection is employed to the B-mode image to extract the important information to be deal as the carotid wall boundary. The result shows the significant difference of arterial diameter between male and female groups which is 2.5% difference. In addition, the significant result of differences of arterial diameter for BMI category is the decreasing of arterial diameter proportional to the BMI.

Keywords: B-mode Ultrasound Image, carotid artery diameter, canny edge detection, body mass index

Procedia PDF Downloads 444

Authors: Jonathan Sohn

Abstract:

Deep neural networks (DNNs) have shown state-of-the-art performance for many applications, including computer vision, natural language processing, and speech recognition. Recently, adversarial attacks have been studied in the context of deep neural networks, which aim to alter the results of deep neural networks by modifying the inputs slightly. For example, an adversarial attack on a DNN used for object detection can cause the DNN to miss certain objects. As a result, the reliability of DNNs is undermined by their lack of robustness against adversarial attacks, raising concerns about their use in safety-critical applications such as autonomous driving. In this paper, we focus on studying the adversarial attacks and defenses on DNNs for image classification. There are two types of adversarial attacks studied which are fast gradient sign method (FGSM) attack and projected gradient descent (PGD) attack. A DNN forms decision boundaries that separate the input images into different categories. The adversarial attack slightly alters the image to move over the decision boundary, causing the DNN to misclassify the image. FGSM attack obtains the gradient with respect to the image and updates the image once based on the gradients to cross the decision boundary. PGD attack, instead of taking one big step, repeatedly modifies the input image with multiple small steps. There is also another type of attack called the target attack. This adversarial attack is designed to make the machine classify an image to a class chosen by the attacker. We can defend against adversarial attacks by incorporating adversarial examples in training. Specifically, instead of training the neural network with clean examples, we can explicitly let the neural network learn from the adversarial examples. In our experiments, the digit recognition accuracy on the MNIST dataset drops from 97.81% to 39.50% and 34.01% when the DNN is attacked by FGSM and PGD attacks, respectively. If we utilize FGSM training as a defense method, the classification accuracy greatly improves from 39.50% to 92.31% for FGSM attacks and from 34.01% to 75.63% for PGD attacks. To further improve the classification accuracy under adversarial attacks, we can also use a stronger PGD training method. PGD training improves the accuracy by 2.7% under FGSM attacks and 18.4% under PGD attacks over FGSM training. It is worth mentioning that both FGSM and PGD training do not affect the accuracy of clean images. In summary, we find that PGD attacks can greatly degrade the performance of DNNs, and PGD training is a very effective way to defend against such attacks. PGD attacks and defence are overall significantly more effective than FGSM methods.

Keywords: deep neural network, adversarial attack, adversarial defense, adversarial machine learning

Procedia PDF Downloads 195

Authors: Lakshay Kharbanda, Aabhas Chauhan

Abstract:

In this paper, an application of Normalized Compression Distance (NCD) to detect notable scene alterations occurring in videos is presented. Several research groups have been developing methods to perform image classification using NCD, a computable approximation to Normalized Information Distance (NID) by studying the degree of similarity in images. The timeframes where significant aberrations between the frames of a video have occurred have been identified by obtaining a threshold NCD value, using two compressors: LZMA and BZIP2 and defining scene alterations using Pixel Difference Percentage metrics.

Keywords: image compression, Kolmogorov complexity, normalized compression distance, root mean square error

Procedia PDF Downloads 340

Authors: Zhihao Zheng, Zhilin Wang, Linxin Liu

Abstract:

In the research of automated knowledge question-answering systems, accuracy and efficiency are critical challenges. This paper proposes a knowledge graph-enhanced Retrieval-Augmented Generation (RAG) method, combined with a Graph Neural Network (GNN) structure, to automatically determine the correctness of knowledge competition questions. First, a domain-specific knowledge graph was constructed from a large corpus of academic journal literature, with key entities and relationships extracted using Natural Language Processing (NLP) techniques. Then, the RAG method's retrieval module was expanded to simultaneously query both text databases and the knowledge graph, leveraging the GNN to further extract structured information from the knowledge graph. During answer generation, contextual information provided by the knowledge graph and GNN is incorporated to improve the accuracy and consistency of the answers. Experimental results demonstrate that the knowledge graph and GNN-enhanced RAG method perform excellently in determining the correctness of questions, achieving an accuracy rate of 95%. Particularly in cases involving ambiguity or requiring contextual information, the structured knowledge provided by the knowledge graph and GNN significantly enhances the RAG method's performance. This approach not only demonstrates significant advantages in improving the accuracy and efficiency of automated knowledge question-answering systems but also offers new directions and ideas for future research and practical applications.

Keywords: knowledge graph, graph neural network, retrieval-augmented generation, NLP

Procedia PDF Downloads 39

Authors: R. Nandhini, Gaurab Mudbhari

Abstract:

Ranging from the field of health care to self-driving cars, machine learning and deep learning algorithms have revolutionized the field with the proper utilization of images and visual-oriented data. Segmentation, regression, classification, clustering, dimensionality reduction, etc., are some of the Machine Learning tasks that helped Machine Learning and Deep Learning models to become state-of-the-art models for the field where images are key datasets. Among these tasks, classification and clustering are essential but difficult because of the intricate and high-dimensional characteristics of image data. This finding examines and assesses advanced techniques in supervised classification and unsupervised clustering for image datasets, emphasizing the relative efficiency of Convolutional Neural Networks (CNNs), Vision Transformers (ViTs), Deep Embedded Clustering (DEC), and self-supervised learning approaches. Due to the distinctive structural attributes present in images, conventional methods often fail to effectively capture spatial patterns, resulting in the development of models that utilize more advanced architectures and attention mechanisms. In image classification, we investigated both CNNs and ViTs. One of the most promising models, which is very much known for its ability to detect spatial hierarchies, is CNN, and it serves as a core model in our study. On the other hand, ViT is another model that also serves as a core model, reflecting a modern classification method that uses a self-attention mechanism which makes them more robust as this self-attention mechanism allows them to lean global dependencies in images without relying on convolutional layers. This paper evaluates the performance of these two architectures based on accuracy, precision, recall, and F1-score across different image datasets, analyzing their appropriateness for various categories of images. In the domain of clustering, we assess DEC, Variational Autoencoders (VAEs), and conventional clustering techniques like k-means, which are used on embeddings derived from CNN models. DEC, a prominent model in the field of clustering, has gained the attention of many ML engineers because of its ability to combine feature learning and clustering into a single framework and its main goal is to improve clustering quality through better feature representation. VAEs, on the other hand, are pretty well known for using latent embeddings for grouping similar images without requiring for prior label by utilizing the probabilistic clustering method.

Keywords: machine learning, deep learning, image classification, image clustering

Procedia PDF Downloads 10

Authors: Supriadi Hardianto, Aditya Daniswara

Abstract:

Today's workplace, flooded by millennial Generation or known also as Generation Y. A common problem that faced by the company towards Gen Y is a high turnover rate, attitudes problem, communication style, and different work style than the older generation. This is common in private sector. The objective of this study is to get a better understanding of the Gen Y Career Attitude at the workplace. The subject of this study is focusing on 430 respondent of Gen Y which age between 20 – 35 years old who works for a private company. The Questionnaire as primary data source captured 9 aspects of career attitude based on Career Attitudes Strategy Inventory (CASI). This Survey distributes randomly among Gen Y in the IT Industry (125 Respondent) and Manufacture Company (305 Respondent). A Random deep interview was conducted to get the better understanding of the etiology of their primary obstacles. The study showed that most of Indonesia Gen Y have a moderate score on Job satisfaction but in the other aspects, Gen Y has the lowest score on Skill Development, Career Worries, Risk-Taking Style, Dominant Style, Work Involvement, Geographical Barrier, Interpersonal Abuse, and Family Commitment. The top 5 obstacles outside that 9 aspects that faced by Gen Y are 1. Lower communication & networking support; 2. Self-confidence issues; 3. Financial Problem; 4. Emotional issues; 5. Age. We also found that parent perspective toward the way they are nurturing their child are not aligned with their child’s real life. This research fundamentally helps the organization and other Gen Y’s Stakeholders to have a better understanding of Gen Y Career Attitude at the workplace.

Keywords: career attitudes, CASI, Gen Y, career attitude at workplace

Procedia PDF Downloads 158

Authors: Abdul Khalique Baloch, Ali Okatan

Abstract:

The quality analysis of food and vegetable from image is hot topic now a day, where researchers make them better then pervious findings through different technique and methods. In this research we have review the literature, and find gape from them, and suggest better proposed approach, design the algorithm, developed a software to measure the quality from images, where accuracy of image show better results, and compare the results with Perouse work done so for. The Application we uses an open-source dataset and python language with tensor flow lite framework. In this research we focus to sort food and vegetable from image, in the images, the application can sorts and make them grading after process the images, it could create less errors them human base sorting errors by manual grading. Digital pictures datasets were created. The collected images arranged by classes. The classification accuracy of the system was about 94%. As fruits and vegetables play main role in day-to-day life, the quality of fruits and vegetables is necessary in evaluating agricultural produce, the customer always buy good quality fruits and vegetables. This document is about quality detection of fruit and vegetables using images. Most of customers suffering due to unhealthy foods and vegetables by suppliers, so there is no proper quality measurement level followed by hotel managements. it have developed software to measure the quality of the fruits and vegetables by using images, it will tell you how is your fruits and vegetables are fresh or rotten. Some algorithms reviewed in this thesis including digital images, ResNet, VGG16, CNN and Transfer Learning grading feature extraction. This application used an open source dataset of images and language used python, and designs a framework of system.

Keywords: deep learning, computer vision, image processing, rotten fruit detection, fruits quality criteria, vegetables quality criteria

Procedia PDF Downloads 70

Authors: A. Ikhlef

Abstract:

Image noise in computed tomography, is mainly caused by the statistical noise, system noise reconstruction algorithm filters. Since last few years, low dose x-ray imaging became more and more desired and looked as a technical differentiating technology among CT manufacturers. In order to achieve this goal, several technologies and techniques are being investigated, including both hardware (integrated electronics and photon counting) and software (artificial intelligence and machine learning) based solutions. From a hardware point of view, electronic noise could indeed be a potential driver for low and ultra-low dose imaging. We demonstrated that the reduction or elimination of this term could lead to a reduction of dose without affecting image quality. Also, in this study, we will show that we can achieve this goal using conventional electronics (low cost and affordable technology), designed carefully and optimized for maximum detective quantum efficiency. We have conducted the tests using large imaging objects such as 30 cm water and 43 cm polyethylene phantoms. We compared the image quality with conventional imaging protocols with radiation as low as 10 mAs (<< 1 mGy). Clinical validation of such results has been performed as well.

Keywords: computed tomography, electronic noise, scintillation detector, x-ray detector

Procedia PDF Downloads 126

Authors: Qian Pei, Hengjian Tong, Weitao Chen, Hai Wang, Yanrong Feng

Abstract:

Horizontal parallax is the foundation of stereoscopic viewing. However, the human eye will feel uncomfortable and it will occur diplopia if horizontal parallax is larger than eye separation. Therefore, we need to do parallax refining before conducting stereoscopic observation. Although some scholars have been devoted to online remote sensing refining, the main work of image refining is completed on the server side. There will be a significant delay when multiple users access the server at the same time. The emergence of HTML5 technology in recent years makes it possible to develop rich browser web application. Authors complete the image parallax refining on the browser side based on HTML5, while server side only need to transfer image data and parallax file to browser side according to the browser’s request. In this way, we can greatly reduce the server CPU load and allow a large number of users to access server in parallel and respond the user’s request quickly.

Keywords: 3D remote sensing images, parallax, online refining, rich browser web application, HTML5

Procedia PDF Downloads 461

Authors: E. Keramaris

Abstract:

In this study, laboratory experiments in open channel flows over a sand bed were conducted. A porous bed (sand bed) with porosity of ε=0.70 and porous thickness of s΄=3 cm was tested. Vertical distributions of velocity were evaluated by using a two-dimensional (2D) Particle Image Velocimetry (PIV). Velocity profiles are measured above the impermeable bed and above the sand bed for the same different total water heights (h= 6, 8, 10 and 12 cm) and for the same slope S=1.5. Measurements of mean velocity indicate the effects of the bed material used (sand bed) on the flow characteristics (Velocity distribution and Reynolds number) in comparison with those above the impermeable bed.

Keywords: particle image velocimetry, sand bed, velocity distribution, Reynolds number

Procedia PDF Downloads 374

Authors: Hoshang Kolivand, Mahyar Kolivand, Mohd Shahrizal Sunar, Mohd Azhar M. Arsad

Abstract:

Real-time shadow generation in virtual environments and Augmented Reality (AR) was always a hot topic in the last three decades. Lots of calculation for shadow generation among AR needs a fast algorithm to overcome this issue and to be capable of implementing in any real-time rendering. In this paper, a silhouette detection algorithm is presented to generate shadows for AR systems. Δ+ algorithm is presented based on extending edges of occluders to recognize which edges are silhouettes in the case of real-time rendering. An accurate comparison between the proposed algorithm and current algorithms in silhouette detection is done to show the reduction calculation by presented algorithm. The algorithm is tested in both virtual environments and AR systems. We think that this algorithm has the potential to be a fundamental algorithm for shadow generation in all complex environments.

Keywords: silhouette detection, shadow volumes, real-time shadows, rendering, augmented reality

Procedia PDF Downloads 443