Search results for: deep residual networks

Authors: Chen-Yin Kuo, Yung-Hsin Lee

Abstract:

Previous studies applying residual income valuation (RIV) model generally use panel data and single-equation model to forecast stock prices. Unlike these, this paper uses Taiwan longitudinal data to estimate multi-equation time-series models such as Vector Autoregressive (VAR), Vector Error Correction Model (VECM), and conduct out-of-sample forecasting. Further, this work assesses their forecasting performance by two instruments. In favor of extant research, the major finding shows that VECM outperforms other three models in forecasting for three stock sectors over entire horizons. It implies that an error correction term containing long-run information contributes to improve forecasting accuracy. Moreover, the pattern of composite shows that at longer horizon, VECM produces the greater reduction in errors, and performs substantially better than VAR.

Keywords: residual income valuation model, vector error correction model, out of sample forecasting, forecasting accuracy

Procedia PDF Downloads 290

Authors: Azeddine El-Hassouny, Chandrashekhar Meshram, Geraldin Nanfack

Abstract:

In recent years, learning from data with noisy labels (Label Noise) has been a major concern in supervised learning. This problem has become even more worrying in Deep Learning, where the generalization capabilities have been questioned lately. Indeed, deep learning requires a large amount of data that is generally collected by search engines, which frequently return data with unreliable labels. In this paper, we investigate the Label Noise in Deep Learning using variational inference. Our contributions are : (1) exploiting Label Noise concept where the true labels are learnt using reparameterization variational inference, while observed labels are learnt discriminatively. (2) the noise transition matrix is learnt during the training without any particular process, neither heuristic nor preliminary phases. The theoretical results shows how true label distribution can be learned by variational inference in any discriminate neural network, and the effectiveness of our approach is proved in several target datasets, such as MNIST and CIFAR32.

Keywords: label noise, deep learning, discrete latent variable, variational inference, MNIST, CIFAR32

Procedia PDF Downloads 92

Authors: Madhawa Basnayaka, Jouni Paltakari

Abstract:

Fully passive backscattering chipless RFID tags are an emerging wireless technology with low cost, higher reading distance, and fast automatic identification without human interference, unlike already available technologies like optical barcodes. The design optimization of chipless RFID tags is crucial as it requires replacing integrated chips found in conventional RFID tags with printed geometric designs. These designs enable data encoding and decoding through backscattered electromagnetic (EM) signatures. The applications of chipless RFID tags have been limited due to the constraints of data encoding capacity and the ability to design accurate yet efficient configurations. The traditional approach to accomplishing design parameters for a desired EM response involves iterative adjustment of design parameters and simulating until the desired EM spectrum is achieved. However, traditional numerical simulation methods encounter limitations in optimizing design parameters efficiently due to the speed and resource consumption. In this work, a deep learning neural network (DNN) is utilized to establish a correlation between the EM spectrum and the dimensional parameters of nested centric rings, specifically square and octagonal. The proposed bi-directional DNN has two simultaneously running neural networks, namely spectrum prediction and design parameters prediction. First, spectrum prediction DNN was trained to minimize mean square error (MSE). After the training process was completed, the spectrum prediction DNN was able to accurately predict the EM spectrum according to the input design parameters within a few seconds. Then, the trained spectrum prediction DNN was connected to the design parameters prediction DNN and trained two networks simultaneously. For the first time in chipless tag design, design parameters were predicted accurately after training bi-directional DNN for a desired EM spectrum. The model was evaluated using a randomly generated spectrum and the tag was manufactured using the predicted geometrical parameters. The manufactured tags were successfully tested in the laboratory. The amount of iterative computer simulations has been significantly decreased by this approach. Therefore, highly efficient but ultrafast bi-directional DNN models allow rapid and complicated chipless RFID tag designs.

Keywords: artificial intelligence, chipless RFID, deep learning, machine learning

Procedia PDF Downloads 19

Authors: Megha Agarwal

Abstract:

The research paper is an effort to compare the earnings based and cash flow based methods of valuation of an enterprise. The theoretically equivalent methods based on either earnings such as Residual Earnings Model (REM), Abnormal Earnings Growth Model (AEGM), Residual Operating Income Method (ReOIM), Abnormal Operating Income Growth Model (AOIGM) and its extensions multipliers such as price/earnings ratio, price/book value ratio; or cash flow based models such as Dividend Valuation Method (DVM) and Free Cash Flow Method (FCFM) all provide different estimates of valuation of the Indian giant corporate Reliance India Limited (RIL). An ex-post analysis of published accounting and financial data for four financial years from 2008-09 to 2011-12 has been conducted. A comparison of these valuation estimates with the actual market capitalization of the company shows that the complex accounting based model AOIGM provides closest forecasts. These different estimates may be derived due to inconsistencies in discount rate, growth rates and the other forecasted variables. Although inputs for earnings based models may be available to the investor and analysts through published statements, precise estimation of free cash flows may be better undertaken by the internal management. The estimation of value from more stable parameters as residual operating income and RNOA could be considered superior to the valuations from more volatile return on equity.

Keywords: earnings, cash flows, valuation, Residual Earnings Model (REM)

Procedia PDF Downloads 345

Authors: Girish J. Showkatramani, Arthi M. Krishna, Sashi Nareddi, Naresh Nula, Aaron Pepe, Glen Brown, Greg Gabel, Chris Doninger

Abstract:

Trademark examination and approval is a complex process that involves analysis and review of the design components of the marks such as the visual representation as well as the textual data associated with marks such as marks' description. Currently, the process of identifying marks with similar visual representation is done manually in United States Patent and Trademark Office (USPTO) and takes a considerable amount of time. Moreover, the accuracy of these searches depends heavily on the experts determining the trademark design codes used to catalog the visual design codes in the mark. In this study, we explore several methods to automate trademark design code classification. Based on recent successes of convolutional neural networks in image classification, we have used several different convolutional neural networks such as Google’s Inception v3, Inception-ResNet-v2, and Xception net. The study also looks into other techniques to augment the results from CNNs such as using Open Source Computer Vision Library (OpenCV) to pre-process the images. This paper reports the results of the various models trained on year of annotated trademark images.

Keywords: trademark design code, convolutional neural networks, trademark image classification, trademark image search, Inception-ResNet-v2

Procedia PDF Downloads 202

Authors: Oumaima Khlifati, Khadija Baba

Abstract:

Pavement distress is the main factor responsible for the deterioration of road structure durability, damage vehicles, and driver comfort. Transportation agencies spend a high proportion of their funds on pavement monitoring and maintenance. The auscultation of pavement distress was based on the manual survey, which was extremely time consuming, labor intensive, and required domain expertise. Therefore, the automatic distress detection is needed to reduce the cost of manual inspection and avoid more serious damage by implementing the appropriate remediation actions at the right time. Inspired by recent deep learning applications, this paper proposes an algorithm for automatic road distress detection and classification using on the Deep Convolutional Neural Network (DCNN). In this study, the types of pavement distress are classified as transverse or longitudinal cracking, alligator, pothole, and intact pavement. The dataset used in this work is composed of public asphalt pavement images. In order to learn the structure of the different type of distress, the DCNN models are trained and tested as a multi-label classification task. In addition, to get the highest accuracy for our model, we adjust the structural optimization hyper parameters such as the number of convolutions and max pooling, filers, size of filters, loss functions, activation functions, and optimizer and fine-tuning hyper parameters that conclude batch size and learning rate. The optimization of the model is executed by checking all feasible combinations and selecting the best performing one. The model, after being optimized, performance metrics is calculated, which describe the training and validation accuracies, precision, recall, and F1 score.

Keywords: distress pavement, hyperparameters, automatic classification, deep learning

Procedia PDF Downloads 60

Authors: Qitao Xie, Qingquan Zhang, Xiaofei Zhang, Di Tian, Ruixuan Wen, Ting Zhu, Ping Yi, Xin Li

Abstract:

Inspired by the recent movement of digital currency, we are building a question answering system concerning the subject of cryptocurrency using Bidirectional Encoder Representations from Transformers (BERT). The motivation behind this work is to properly assist digital currency investors by directing them to the corresponding knowledge bases that can offer them help and increase the querying speed. BERT, one of newest language models in natural language processing, was investigated to improve the quality of generated responses. We studied different combinations of hyperparameters of the BERT model to obtain the best fit responses. Further, we created an intelligent chatbot for cryptocurrency using BERT. A chatbot using BERT shows great potential for the further advancement of a cryptocurrency market tool. We show that the BERT neural networks generalize well to other tasks by applying it successfully to cryptocurrency.

Keywords: bidirectional encoder representations from transformers, BERT, chatbot, cryptocurrency, deep learning

Procedia PDF Downloads 112

Authors: Boukhiar Aissa, Halladj Fatima, Iguergaziz Nadia, Lamrani yasmina, Benamara Salem

Abstract:

Determining the alcohol content in alcoholic fermentation bioprocess is of great importance. In fact, it is a key indicator for monitoring this bioprocess. Several methodologies (chemical, spectrophotometric, chromatographic) are used to the determination of this parameter. However, these techniques are very long and they require: rigorous preparations, sometimes dangerous chemical reagents and/or expensive equipment. In the present study, the date juice is used as the substrate of alcoholic fermentation. The extracted juice undergoes an alcoholic fermentation by Saccharomyces cerevisiae. The study of the possible use of refractometry as a sole means for the in situ control of alcoholic fermentation revealed a good correlation (R2=0.98) between initial and final °Brix: °Brixf=0.377×°Brixi. In addition, the relationship between Δ°Brix and alcoholic content of the final product (A,%) has been determined: Δ°Brix/A=1.1. The obtained results allowed us to establish iso-responses abacus, which can be used for the determination of alcohol and residual sugar content, with a mean relative error (MRE) of 5.35%.

Keywords: alcoholic fermentation, date juice, refractometry, residual sugar

Procedia PDF Downloads 312

Authors: R. M. López-Gutiérrez, L. Cardoza-Avendaño, H. Cervantes-de Ávila, J. A. Michel-Macarty, C. Cruz-Hernández, A. Arellano-Delgado, R. Carmona-Rodríguez

Abstract:

In this paper, synchronization of multiple chaotic semiconductor lasers is achieved by appealing to complex system theory. In particular, we consider dynamical networks composed by semiconductor laser, as interconnected nodes, where the interaction in the networks are defined by coupling the first state of each node. An interesting case is synchronized with master-slave configuration in star topology. Nodes of these networks are modeled for the laser and simulated by Matlab. These results are applicable to private communication.

Keywords: chaotic laser, network, star topology, synchronization

Procedia PDF Downloads 536

Authors: Xiaoying Guo, Xiangyun Wang, Chunhua Jia

Abstract:

Web page has been one of the most important way of knowing the world. Humans catch a lot of information from it everyday. Thus, understanding where human looks when they surfing the web pages is rather important. In normal scenes, the down-top features and top-down tasks significantly affect humans’ eye movement. In this paper, we investigated if the conventional visual salience algorithm can properly predict humans’ visual attractive region when they viewing the web pages. First, we obtained the eye movement data when the participants viewing the web pages using an eye tracker. By the analysis of eye movement data, we studied the influence of visual saliency and thinking way on eye-movement pattern. The analysis result showed that thinking way affect human’ eye-movement pattern much more than visual saliency. Second, we compared the results of web page visual salience region extracted by Itti model and Spectral Residual (SR) model. The results showed that Spectral Residual (SR) model performs superior than Itti model by comparison with the heat map from eye movements. Considering the influence of mind habit on humans’ visual region of interest, we introduced one of the most important cue in mind habit-fixation position to improved the SR model. The result showed that the improved SR model can better predict the human visual region of interest in web pages.

Keywords: web page salience region, eye-tracker, spectral residual, visual salience

Procedia PDF Downloads 253

Authors: Shraddha Jain Sharma, Ratnalata Gupta

Abstract:

Predicting stock movements in the financial market is both difficult and rewarding. Analysts and academics are increasingly using advanced approaches such as machine learning techniques to anticipate stock price patterns, thanks to the expanding capacity of computing and the recent advent of graphics processing units and tensor processing units. Stock market prediction is a type of time series prediction that is incredibly difficult to do since stock prices are influenced by a variety of financial, socioeconomic, and political factors. Furthermore, even minor mistakes in stock market price forecasts can result in significant losses for companies that employ the findings of stock market price prediction for financial analysis and investment. Soft computing techniques are increasingly being employed for stock market prediction due to their better accuracy than traditional statistical methodologies. The proposed research looks at the need for soft computing techniques in stock market prediction, the numerous soft computing approaches that are important to the field, past work in the area with their prominent features, and the significant problems or issue domain that the area involves. For constructing a predictive model, the major focus is on neural networks and fuzzy logic. The stock market is extremely unpredictable, and it is unquestionably tough to correctly predict based on certain characteristics. This study provides a complete overview of the numerous strategies investigated for high accuracy prediction, with a focus on the most important characteristics.

Keywords: stock market prediction, artificial intelligence, artificial neural networks, fuzzy logic, accuracy, deep learning, machine learning, stock price, trading volume

Procedia PDF Downloads 61

Authors: Avatharam Ganivada, Krishna Shah

Abstract:

The Mask R-CNN is recently introduced by the team of Facebook AI Research (FAIR), which is mainly concerned with instance segmentation in images. Here, the Mask R-CNN is based on ResNet and feature pyramid network (FPN), where a single dropout method is employed. This paper provides a modified Mask R-CNN by adding multiple dropout methods into the Mask R-CNN. The proposed model has also utilized the concepts of Resnet and FPN to extract stage-wise network feature maps, wherein a top-down network path having lateral connections is used to obtain semantically strong features. The proposed model produces three outputs for each object in the image: class label, bounding box coordinates, and object mask. The performance of the proposed network is evaluated in the segmentation of every instance in images using COCO and cityscape datasets. The proposed model achieves better performance than the state-of-the-networks for the datasets.

Keywords: instance segmentation, object detection, convolutional neural networks, deep learning, computer vision

Procedia PDF Downloads 45

Authors: Varun Agarwal

Abstract:

Introduction: With the advent of personalized medicine, histopathological review of whole slide images (WSIs) for cancer diagnosis presents an exceedingly time-consuming, complex task. Specifically, detecting metastatic regions in WSIs of sentinel lymph node biopsies necessitates a full-scanned, holistic evaluation of the image. Thus, digital pathology, low-level image manipulation algorithms, and machine learning provide significant advancements in improving the efficiency and accuracy of WSI analysis. Using Camelyon16 data, this paper proposes a deep learning pipeline to automate and ameliorate breast cancer metastasis localization and WSI classification. Methodology: The model broadly follows five stages -region of interest detection, WSI partitioning into image tiles, convolutional neural network (CNN) image-segment classifications, probabilistic mapping of tumor localizations, and further processing for whole WSI classification. Transfer learning is applied to the task, with the implementation of Inception-ResNetV2 - an effective CNN classifier that uses residual connections to enhance feature representation, adding convolved outputs in the inception unit to the proceeding input data. Moreover, in order to augment the performance of the transfer learning CNN, a stack of convolutional denoising autoencoders (CDAE) is applied to produce embeddings that enrich image representation. Through a saliency-detection algorithm, visual training segments are generated, which are then processed through a denoising autoencoder -primarily consisting of convolutional, leaky rectified linear unit, and batch normalization layers- and subsequently a contrast-normalization function. A spatial pyramid pooling algorithm extracts the key features from the processed image, creating a viable feature map for the CNN that minimizes spatial resolution and noise. Results and Conclusion: The simplified and effective architecture of the fine-tuned transfer learning Inception-ResNetV2 network enhanced with the CDAE stack yields state of the art performance in WSI classification and tumor localization, achieving AUC scores of 0.947 and 0.753, respectively. The convolutional feature retention and compilation with the residual connections to inception units synergized with the input denoising algorithm enable the pipeline to serve as an effective, efficient tool in the histopathological review of WSIs.

Keywords: breast cancer, convolutional neural networks, metastasis mapping, whole slide images

Procedia PDF Downloads 107

Authors: Arnold I. Malag

Abstract:

The study wants to establish the data on the characteristics of coastal solid waste in main Island of Masbate as a model for technology interventions. The research utilized the Google Maps to measure the coastal length and Fishbowl Method for area identification. The solid wastes gathered were classified as residual, non-biodegradable, recyclable wastes, and special wastes, based on the waste analysis and characterization manual of Philippine Environmental Governance Project. The wastes were evaluated by weight in kg., dimension in cm., and characteristics as floating or non-floating. Based on the dimension of coastal solid waste, the biodegradable, recyclable, residual and special waste have the average of 40.95 cm., 16.25 cm., 31.37 cm., and 0.725cm. respectively. The waste in the coastal areas is dominated by biodegradable, followed by residual, then recyclable and special wastes with the data of 0.566 kg/m, 0.533 kg/m, 0.114 kg/m and .0007 kg/m respectively. The 97.15% of solid wastes collected is characterized as “floating”, where in the sources are the nearest rivers and waterways and/or the nearest populated areas adjacent to the island. This accumulation of solid wastes can be minimized and controlled by utilizing a floating equipment.

Keywords: solid waste, coastal waste, waste characterization, waste collector

Procedia PDF Downloads 58

Authors: Seyed Mahdi Jameii

Abstract:

Underwater wireless sensor networks have been attracting the interest of many ‎researchers lately, and the past three decades have beheld the rapid progress of ‎underwater acoustic communication. One of the major problems in underwater wireless ‎sensor networks is how to transfer data from the moving node to the base stations and ‎choose the optimized route for data transmission. Secure routing in underwater ‎wireless sensor network (UWCNs) is necessary for packet delivery. Some routing ‎protocols are proposed for underwater wireless sensor networks. However, a few ‎researches have been done on secure routing in underwater sensor networks. In this ‎article, a secure routing protocol is provided to resist against wormhole and sybil ‎attacks. The results indicated acceptable performance in terms of increasing the packet ‎delivery ratio with regards to the attacks, increasing network lifetime by creating ‎balance in the network energy consumption, high detection rates against the attacks, ‎and low-end to end delay.‎

Keywords: attacks, routing, security, underwater wireless sensor networks

Procedia PDF Downloads 386

Authors: Farina Riaz, Shahab Abdulla, Srinjoy Ganguly, Hajime Suzuki, Ravinesh C. Deo, Susan Hopkins

Abstract:

Recently, quantum machine learning has received significant attention. For various types of data, including text and images, numerous quantum machine learning (QML) models have been created and are being tested. Images are exceedingly complex data components that demand more processing power. Despite being mature, classical machine learning still has difficulties with big data applications. Furthermore, quantum technology has revolutionized how machine learning is thought of, by employing quantum features to address optimization issues. Since quantum hardware is currently extremely noisy, it is not practicable to run machine learning algorithms on it without risking the production of inaccurate results. To discover the advantages of quantum versus classical approaches, this research has concentrated on colored image data. Deep learning classification models are currently being created on Quantum platforms, but they are still in a very early stage. Black and white benchmark image datasets like MNIST and Fashion MINIST have been used in recent research. MNIST and CIFAR-10 were compared for binary classification, but the comparison showed that MNIST performed more accurately than colored CIFAR-10. This research will evaluate the performance of the QML algorithm on the colored benchmark dataset CIFAR-10 to advance QML's real-time applicability. However, deep learning classification models have not been developed to compare colored images like Quantum Convolutional Neural Network (QCNN) to determine how much it is better to classical. Only a few models, such as quantum variational circuits, take colored images. The methodology adopted in this research is a hybrid approach by using penny lane as a simulator. To process the 10 classes of CIFAR-10, the image data has been translated into grey scale and the 28 × 28-pixel image containing 10,000 test and 50,000 training images were used. The objective of this work is to determine how much the quantum approach can outperform a classical approach for a comprehensive dataset of color images. After pre-processing 50,000 images from a classical computer, the QCNN model adopted a hybrid method and encoded the images into a quantum simulator for feature extraction using quantum gate rotations. The measurements were carried out on the classical computer after the rotations were applied. According to the results, we note that the QCNN approach is ~12% more effective than the traditional classical CNN approaches and it is possible that applying data augmentation may increase the accuracy. This study has demonstrated that quantum machine and deep learning models can be relatively superior to the classical machine learning approaches in terms of their processing speed and accuracy when used to perform classification on colored classes.

Keywords: CIFAR-10, quantum convolutional neural networks, quantum deep learning, quantum machine learning

Procedia PDF Downloads 95

Authors: Ashkan Shafee, Ahmad Fahimifar

Abstract:

There is a growing demand for construction of high-rise buildings and infrastructures in large cities, which sometimes require deep excavations in the vicinity of pile foundations. In this study, a two-dimensional finite element analysis is used to gain insight into the response of pile groups adjacent to deep excavations in sand. The numerical code was verified by available experimental works, and a parametric study was performed on different working load combinations, excavation depth and supporting system. The results show that the simple two-dimensional plane strain model can accurately simulate the excavation induced changes on adjacent pile groups. It was found that further excavation than pile toe level and also inclined loading on adjacent pile group can severely affect the serviceability of the foundation.

Keywords: deep excavation, inclined loading, lateral deformation, pile group

Procedia PDF Downloads 241

Authors: Simone Leonardi, Luca Ardito

Abstract:

Micro-influencers are effective elements in the marketing strategies of companies and institutions because of their capability to create an hyper-engaged audience around a specific topic of interest. In recent years, many scientific approaches and commercial tools have handled the task of detecting this type of social media users. These strategies adopt solutions ranging from rule based machine learning models to deep neural networks and graph analysis on text, images, and account information. This work compares the existing solutions and proposes an ensemble method to generalize them with different input data and social media platforms. The deployed solution combines deep learning models on unstructured data with statistical machine learning models on structured data. We retrieve both social media accounts information and multimedia posts on Twitter and Instagram. These data are mapped into feature vectors for an eXtreme Gradient Boosting (XGBoost) classifier. Sixty different topics have been analyzed to build a rule based gold standard dataset and to compare the performances of our approach against baseline classifiers. We prove the effectiveness of our work by comparing the accuracy, precision, recall, and f1 score of our model with different configurations and architectures. We obtained an accuracy of 0.91 with our best performing model.

Keywords: deep learning, gradient boosting, image processing, micro-influencers, NLP, social media

Procedia PDF Downloads 146

Authors: Nouha Khediri, Mohammed Ben Ammar, Monji Kherallah

Abstract:

Recently, facial emotion recognition (FER) has become increasingly essential to understand the state of the human mind. Accurately classifying emotion from the face is a challenging task. In this paper, we present a facial emotion recognition approach named CV-FER, benefiting from deep learning, especially CNN and VGG16. First, the data is pre-processed with data cleaning and data rotation. Then, we augment the data and proceed to our FER model, which contains five convolutions layers and five pooling layers. Finally, a softmax classifier is used in the output layer to recognize emotions. Based on the above contents, this paper reviews the works of facial emotion recognition based on deep learning. Experiments show that our model outperforms the other methods using the same FER2013 database and yields a recognition rate of 92%. We also put forward some suggestions for future work.

Keywords: CNN, deep-learning, facial emotion recognition, machine learning

Procedia PDF Downloads 64

Authors: Souâad Boudebza, Omar Nouali, Faiçal Azouaou

Abstract:

Social networks have recently gained a growing interest on the web. Traditional formalisms for representing social networks are static and suffer from the lack of semantics. In this paper, we will show how semantic web technologies can be used to model social data. The SemTemp ontology aligns and extends existing ontologies such as FOAF, SIOC, SKOS and OWL-Time to provide a temporal and semantically rich description of social data. We also present a modeling scenario to illustrate how our ontology can be used to model social networks.

Keywords: ontology, semantic web, social network, temporal modeling

Procedia PDF Downloads 352

Authors: Samira Kalantary, Zohre Saatzade

Abstract:

Wireless Mesh Networks (WMNs) are low-cost access networks built on cooperative routing over a backbone composed of stationary wireless routers. WMNs must deal with the highly unstable wireless medium. Thus, routing metrics and protocols are evolving by designing algorithms that consider link quality to choose the best routes. In this work, we analyse the state of the art in WMN metrics and propose taxonomy for WMN routing protocols. Performance measurements of a wireless mesh network deployed using various routing metrics are presented and corroborate our analysis.

Keywords: wireless mesh networks, routing protocols, routing metrics, bioinformatics

Procedia PDF Downloads 424

Authors: Pawan S. Nagda, Purnank S. Bhatt, Mit K. Shah

Abstract:

Earing defect in drawing process is highly undesirable not only because it adds on an additional trimming operation but also because the uneven material flow demands extra care. The objective of this work is to study the earing problem in the Deep Drawing of circular cup and to optimize the blank shape to reduce the earing. A finite element model is developed for 3-D numerical simulation of cup forming process in ABAQUS. Extra-deep-drawing (EDD) steel sheet has been used for simulation. Properties and tool design parameters were used as input for simulation. Earing was observed in the simulated cup and it was measured at various angles with respect to rolling direction. To reduce the earing defect initial blank shape was modified with the help of anisotropy coefficient. Modified blanks showed notable reduction in earing.

Keywords: anisotropy, deep drawing, earing, finite element simulation

Procedia PDF Downloads 356

Authors: Shaira L. Kee, Michael Aaron G. Sy, Myles Joshua T. Tan, Hezerul Abdul Karim, Nouar AlDahoul

Abstract:

Skin diseases are considered the fourth most common disease, with melanoma and non-melanoma skin cancer as the most common type of cancer in Caucasians. The alarming increase in Skin Cancer cases shows an urgent need for further research to improve diagnostic methods, as early diagnosis can significantly improve the 5-year survival rate. Machine Learning algorithms for image pattern analysis in diagnosing skin lesions can dramatically increase the accuracy rate of detection and decrease possible human errors. Several studies have shown the diagnostic performance of computer algorithms outperformed dermatologists. However, existing methods still need improvements to reduce diagnostic errors and generate efficient and accurate results. Our paper proposes an ensemble method to classify dermoscopic images into benign and malignant skin lesions. The experiments were conducted using the International Skin Imaging Collaboration (ISIC) image samples. The dataset contains 3,297 dermoscopic images with benign and malignant categories. The results show improvement in performance with an accuracy of 88% and an F1 score of 87%, outperforming other existing models such as support vector machine (SVM), Residual network (ResNet50), EfficientNetB0, EfficientNetB4, and VGG16.

Keywords: deep learning - VGG16 - efficientNet - CNN – ensemble – dermoscopic images - melanoma

Procedia PDF Downloads 55

Authors: Evy Van Puymbroeck, Wim Nagy, Ken Schotte, Heng Fang, Hans De Backer

Abstract:

The knowledge of residual stresses for welded bridge components is essential to determine the effect of the residual stresses on the fatigue life behavior. The residual stresses of an orthotropic bridge deck are determined by simulating the welding process with finite element modelling. The stiffener is placed on top of the deck plate before welding. A chained thermal-mechanical analysis is set up to determine the distribution of residual stresses for the bridge deck. First, a thermal analysis is used to determine the temperatures of the orthotropic deck for different time steps during the welding process. Twin wire submerged arc welding is used to construct the orthotropic plate. A double ellipsoidal volume heat source model is used to describe the heat flow through a material for a moving heat source. The heat input is used to determine the heat flux which is applied as a thermal load during the thermal analysis. The heat flux for each element is calculated for different time steps to simulate the passage of the welding torch with the considered welding speed. This results in a time dependent heat flux that is applied as a thermal loading. Thermal material behavior is specified by assigning the properties of the material in function of the high temperatures during welding. Isotropic hardening behavior is included in the model. The thermal analysis simulates the heat introduced in the two plates of the orthotropic deck and calculates the temperatures during the welding process. After the calculation of the temperatures introduced during the welding process in the thermal analysis, a subsequent mechanical analysis is performed. For the boundary conditions of the mechanical analysis, the actual welding conditions are considered. Before welding, the stiffener is connected to the deck plate by using tack welds. These tack welds are implemented in the model. The deck plate is allowed to expand freely in an upwards direction while it rests on a firm and flat surface. This behavior is modelled by using grounded springs. Furthermore, symmetry points and lines are used to prevent the model to move freely in other directions. In the thermal analysis, a mechanical material model is used. The calculated temperatures during the thermal analysis are introduced during the mechanical analysis as a time dependent load. The connection of the elements of the two plates in the fusion zone is realized with a glued connection which is activated when the welding temperature is reached. The mechanical analysis results in a distribution of the residual stresses. The distribution of the residual stresses of the orthotropic bridge deck is compared with results from literature. Literature proposes uniform tensile yield stresses in the weld while the finite element modelling showed tensile yield stresses at a short distance from the weld root or the weld toe. The chained thermal-mechanical analysis results in a distribution of residual weld stresses for an orthotropic bridge deck. In future research, the effect of these residual stresses on the fatigue life behavior of welded bridge components can be studied.

Keywords: finite element modelling, residual stresses, thermal-mechanical analysis, welding simulation

Procedia PDF Downloads 148

Authors: Okoro Ikechukwu Ralph, Fuat Kara

Abstract:

The discoveries of hydrocarbon reserves has clearly drifted offshore, and in deeper waters - areas where the industry still has limited knowledge; and that were hitherto, regarded as being out of reach. This shift presents significant and increased challenges in technology requirements needed to guarantee safety of personnel, environment and equipment; ensure high reliability of installed equipment; and provide high level of confidence in security of investment and company reputation. Nowhere are these challenges more apparent than on subsea well integrity and production performance. The past two decades has witnessed enormous rise in deep and ultra-deep water offshore field developments for the recovery of hydrocarbons. Subsea installed equipment at the seabed has been the technology of choice for these developments. This paper discusses the role of Subsea Control module (SCM) as a vital factor for deep-water well integrity and production performance. A case study for Deep-water well integrity and production performance is analysed.

Keywords: offshore reliability, production performance, subsea control module, well integrity

Procedia PDF Downloads 483

Authors: Pius Marthin, Nihal Ata Tutkun

Abstract:

Survival analysis has become one of the paramount procedures in the modeling of time-to-event data. When we encounter complex survival problems, the traditional approach remains limited in accounting for the complex correlational structure between the covariates and the outcome due to the strong assumptions that limit the inference and prediction ability of the resulting models. Several studies exist on the deep learning approach to survival modeling; moreover, the application for the case of complex survival problems still needs to be improved. In addition, the existing models need to address the data structure's complexity fully and are subject to noise and redundant information. In this study, we design a deep learning technique (CmpXRnnSurv_AE) that obliterates the limitations imposed by traditional approaches and addresses the above issues to jointly predict the risk-specific probabilities and survival function for recurrent events with competing risks. We introduce the component termed Risks Information Weights (RIW) as an attention mechanism to compute the weighted cumulative incidence function (WCIF) and an external auto-encoder (ExternalAE) as a feature selector to extract complex characteristics among the set of covariates responsible for the cause-specific events. We train our model using synthetic and real data sets and employ the appropriate metrics for complex survival models for evaluation. As benchmarks, we selected both traditional and machine learning models and our model demonstrates better performance across all datasets.

Keywords: cumulative incidence function (CIF), risk information weight (RIW), autoencoders (AE), survival analysis, recurrent events with competing risks, recurrent neural networks (RNN), long short-term memory (LSTM), self-attention, multilayers perceptrons (MLPs)

Procedia PDF Downloads 58

Authors: Ming-Jen Huang, Chun-Fang Huang, Chiching Wei

Abstract:

With the recent advance of the deep neural network, we observe new applications of NLP (natural language processing) and CV (computer vision) powered by deep neural networks for processing business documents. However, creating a real-world document processing system needs to integrate several NLP and CV tasks, rather than treating them separately. There is a need to have a unified approach for processing documents containing textual and graphical elements with rich formats, diverse layout arrangement, and distinct semantics. In this paper, a framework that fulfills this unified approach is presented. The framework includes a representation model definition for holding the information generated by various tasks and specifications defining the coordination between these tasks. The framework is a blueprint for building a system that can process documents with rich formats, styles, and multiple types of elements. The flexible and lightweight design of the framework can help build a system for diverse business scenarios, such as contract monitoring and reviewing.

Keywords: document processing, framework, formal definition, machine learning

Procedia PDF Downloads 187

Authors: Jiangxia Han, Liang Xue, Keda Chen

Abstract:

Despite the significant progress over the last decades in reservoir simulation using numerical discretization, meshing is complex. Moreover, the high degree of freedom of the space-time flow field makes the solution process very time-consuming. Therefore, we present Physics-Informed Convolutional Neural Networks(PICNN) as a hybrid scientific theory and data method for reservoir modeling. Besides labeled data, the model is driven by the scientific theories of the underlying problem, such as governing equations, boundary conditions, and initial conditions. PICNN integrates governing equations and boundary conditions into the network architecture in the form of a customized convolution kernel. The loss function is composed of data matching, initial conditions, and other measurable prior knowledge. By customizing the convolution kernel and minimizing the loss function, the neural network parameters not only fit the data but also honor the governing equation. The PICNN provides a methodology to model and history-match flow and transport problems in porous media. Numerical results demonstrate that the proposed PICNN can provide an accurate physical solution from a limited dataset. We show how this method can be applied in the context of a forward simulation for continuous problems. Furthermore, several complex scenarios are tested, including the existence of data noise, different work schedules, and different good patterns.

Keywords: convolutional neural networks, deep learning, flow and transport in porous media, physics-informed neural networks, reservoir simulation

Procedia PDF Downloads 104

Authors: Hossam Abdelrahman, Sama Rostom, Reem Yassein, Yara Mohamed, Salma Salah, Nour Awny

Abstract:

In today’s environment, people are becoming increasingly interested in their appearance. However, they are afraid of their unknown appearance after a plastic surgery or treatment. Accidents, burns and genetic problems such as bowing of body parts of people have a negative impact on their mental health with their appearance and this makes them feel uncomfortable and underestimated. The approach presents a revolutionary deep learning-based image inpainting method that analyses the various picture structures and corrects damaged images. In this study, A model is proposed based on the in-painting of medical images with Stable Diffusion Inpainting method. Reconstructing missing and damaged sections of an image is known as image inpainting is a key progress facilitated by deep neural networks. The system uses the input of the user of an image to indicate a problem, the system will then modify the image and output the fixed image, facilitating for the patient to see the final result.

Keywords: generative adversarial network, large mask inpainting, stable diffusion inpainting, plastic surgery

Procedia PDF Downloads 48

Authors: Theena Thayalan, K. N. Ramesh Babu

Abstract:

Machining induced residual stress (RS) is one of the most important surface integrity parameters that characterize the near surface layer of a mechanical component, which plays a crucial role in controlling the performance, especially its fatigue life. Since experimental determination of RS is expensive and time consuming, it would be of great benefit if they could be predicted. In such case, it would be possible to select the cutting parameters required to produce a favorable RS profile. In the present study, an effort has been made to develop a 'two dimensional finite element model (FEM)' to simulate orthogonal cutting process and to predict surface and sub-surface RS using the commercial FEA software DEFORM-2D. The developed finite element model has been validated through experimental investigation of RS. In the experimentation, the orthogonal cutting tests were carried out on AISI 4340 by varying the cutting speed (VC) and uncut chip thickness (f) at three levels and the surface & sub-surface RS has been measured using XRD and Electro polishing techniques. The comparison showed that the RS obtained using developed numerical model is in reasonable agreement with that of experimental data.

Keywords: FEM, machining, residual stress, XRF

Procedia PDF Downloads 319