Search results for: Neeru Deep

Authors: Dhanuj M. Gandikota

Abstract:

Sensor-derived three-dimensional (3D) point clouds of trees are invaluable in remote sensing analysis for the accurate measurement of key structural metrics, bio-inventory values, spatial planning/visualization, and ecological modeling. Machine learning (ML) holds the potential in addressing the restrictive tradeoffs in cost, spatial coverage, resolution, and information gain that exist in current point cloud sensing methods. Terrestrial laser scanning (TLS) remains the highest fidelity source of both canopy and below-canopy structural features, but usage is limited in both coverage and cost, requiring manual deployment to map out large, forested areas. While aerial laser scanning (ALS) remains a reliable avenue of LIDAR active remote sensing, ALS is also cost-restrictive in deployment methods. Space-borne photogrammetry from high-resolution satellite constellations is an avenue of passive remote sensing with promising viability in research for the accurate construction of vegetation 3-D point clouds. It provides both the lowest comparative cost and the largest spatial coverage across remote sensing methods. However, both space-borne photogrammetry and ALS demonstrate technical limitations in the capture of valuable below-canopy point cloud data. Looking to minimize these tradeoffs, we explored a class of powerful ML algorithms called Deep Learning (DL) that show promise in recent research on 3-D point cloud reconstruction and interpolation. Our research details the efficacy of applying these DL techniques to reconstruct accurate below-canopy point clouds from space-borne and aerial remote sensing through learned patterns of tree species fractal symmetry properties and the supplementation of locally sourced bio-inventory metrics. From our dataset, consisting of tree point clouds obtained from TLS, we deconstructed the point clouds of each tree into those that would be obtained through ALS and satellite photogrammetry of varying resolutions. We fed this ALS/satellite point cloud dataset, along with the simulated local bio-inventory metrics, into the DL point cloud reconstruction architectures to generate the full 3-D tree point clouds (the truth values are denoted by the full TLS tree point clouds containing the below-canopy information). Point cloud reconstruction accuracy was validated both through the measurement of error from the original TLS point clouds as well as the error of extraction of key structural metrics, such as crown base height, diameter above root crown, and leaf/wood volume. The results of this research additionally demonstrate the supplemental performance gain of using minimum locally sourced bio-inventory metric information as an input in ML systems to reach specified accuracy thresholds of tree point cloud reconstruction. This research provides insight into methods for the rapid, cost-effective, and accurate construction of below-canopy tree 3-D point clouds, as well as the supported potential of ML and DL to learn complex, unmodeled patterns of fractal tree growth symmetry.

Keywords: deep learning, machine learning, satellite, photogrammetry, aerial laser scanning, terrestrial laser scanning, point cloud, fractal symmetry

Procedia PDF Downloads 89

Authors: Raed KOUTA, José-Alcebiades-Ernesto HLUNGUANE, Eric Châtele

Abstract:

The search for and exploitation of new fossil energy resources is taking place in the context of the gradual depletion of existing deposits. Despite the adoption of international targets to combat global warming, the demand for fuels continues to grow, contradicting the movement towards an energy-efficient society. The increase in the share of offshore in global hydrocarbon production tends to compensate for the depletion of terrestrial reserves, thus constituting a major challenge for the players in the sector. Through the economic potential it represents, and the energy independence it provides, offshore exploitation is also a challenge for States such as Mozambique, which have large maritime areas and whose environmental wealth must be considered. The exploitation of new reserves on economically viable terms depends on available technologies. The development of deep and ultra-deep offshore requires significant research and development efforts. Progress has also been made in managing the multiple risks inherent in this activity. Our study proposes a reliability approach to develop products and processes designed to live at sea. Indeed, the context of an offshore platform requires highly reliable solutions to overcome the difficulties of access to the system for regular maintenance and quick repairs and which must resist deterioration and degradation processes. One of the characteristics of failures that we consider is the actual conditions of use that are considered 'extreme.' These conditions depend on time and the interactions between the different causes. These are the two factors that give the degradation process its dynamic character, hence the need to develop dynamic reliability models. Our work highlights mathematical models that can explicitly manage interactions between components and process variables. These models are accompanied by numerical resolution methods that help to structure a dynamic reliability approach in a physical and probabilistic context. The application developed makes it possible to evaluate the reliability, availability, and maintainability of a floating storage and unloading platform for liquefied natural gas production.

Keywords: dynamic reliability, offshore plateform, stochastic process, uncertainties

Procedia PDF Downloads 114

Authors: Armin Nabaei, M. Omair Ahmad, M. N. S. Swamy

Abstract:

Many facial expression and emotion recognition methods in the traditional approaches of using LDA, PCA, and EBGM have been proposed. In recent years deep learning models have provided a unique platform addressing by automatically extracting the features for the detection of facial expression and emotions. However, deep networks require large training datasets to extract automatic features effectively. In this work, we propose an efficient emotion detection algorithm using face images when only small datasets are available for training. We design a deep network whose feature extraction capability is enhanced by utilizing several parallel modules between the input and output of the network, each focusing on the extraction of different types of coarse features with fined grained details to break the symmetry of produced information. In fact, we leverage long range dependencies, which is one of the main drawback of CNNs. We develop this work by introducing a Dynamic Soft-Margin SoftMax.The conventional SoftMax suffers from reaching to gold labels very soon, which take the model to over-fitting. Because it’s not able to determine adequately discriminant feature vectors for some variant class labels. We reduced the risk of over-fitting by using a dynamic shape of input tensor instead of static in SoftMax layer with specifying a desired Soft- Margin. In fact, it acts as a controller to how hard the model should work to push dissimilar embedding vectors apart. For the proposed Categorical Loss, by the objective of compacting the same class labels and separating different class labels in the normalized log domain.We select penalty for those predictions with high divergence from ground-truth labels.So, we shorten correct feature vectors and enlarge false prediction tensors, it means we assign more weights for those classes with conjunction to each other (namely, “hard labels to learn”). By doing this work, we constrain the model to generate more discriminate feature vectors for variant class labels. Finally, for the proposed optimizer, our focus is on solving weak convergence of Adam optimizer for a non-convex problem. Our noteworthy optimizer is working by an alternative updating gradient procedure with an exponential weighted moving average function for faster convergence and exploiting a weight decay method to help drastically reducing the learning rate near optima to reach the dominant local minimum. We demonstrate the superiority of our proposed work by surpassing the first rank of three widely used Facial Expression Recognition datasets with 93.30% on FER-2013, and 16% improvement compare to the first rank after 10 years, reaching to 90.73% on RAF-DB, and 100% k-fold average accuracy for CK+ dataset, and shown to provide a top performance to that provided by other networks, which require much larger training datasets.

Keywords: computer vision, facial expression recognition, machine learning, algorithms, depp learning, neural networks

Procedia PDF Downloads 63

Authors: Jiradeach Kalayaruan, Tosawat Seetawan

Abstract:

This paper studied the energy of the nature systems by looking at the overall image throughout the universe. The energy of the nature systems was developed from the Einstein’s energy equation. The researcher used the new ideas called even 2n and odd 3n light dimension energy states systems, which were developed from Einstein’s relativity energy theory equation. In this study, the major methodology the researchers used was the basic principle ideas or beliefs of some religions such as Buddhism, Christianity, Hinduism, Islam, or Tao in order to get new discoveries. The basic beliefs of each religion - Nivara, God, Ether, Atman, and Tao respectively, were great influential ideas on the researchers to use them greatly in the study to form new ideas from philosophy. Since the philosophy of each religion was alive with deep insight of the physical nature relative energy, it connected the basic beliefs to light dimension energy states systems. Unfortunately, Einstein’s original relative energy equation showed only even 2n light dimension energy states systems (if n = 1,…,∞). But in advance ideas, the researchers multiplied light dimension energy by Einstein’s original relative energy equation and get new idea of theoritical physics in odd 3n light dimension energy states systems (if n = 1,…,∞). Because from basic principle ideas or beliefs of some religions philosophy of each religion, you had to add the media light dimension energy into Einstein’s original relative energy equation. Consequently, the simple meaning picture in deep insight showed that you could touch light dimension energy of Nivara, God, Ether, Atman, and Tao by light dimension energy. Since light dimension energy was transferred by Nivara, God, Ether, Atman and Tao, the researchers got the new equation of odd 3n light dimension energy states systems. Moreover, the researchers expected to be able to solve overview problems of all light dimension energy in all nature relative energy, which are developed from Eistein’s relative energy equation.The finding of the study was called 'super nature relative energy' ( in odd 3n light dimension energy states systems (if n = 1,…,∞)). From the new ideas above you could do the summation of even 2n and odd 3n light dimension energy states systems in all of nature light dimension energy states systems. In the future time, the researchers will expect the new idea to be used in insight theoretical physics, which is very useful to the development of quantum mechanics, all engineering, medical profession, transportation, communication, scientific inventions, and technology, etc.

Keywords: 2n light dimension energy states systems effect, Ether, even 2n light dimension energy states systems, nature relativity, Nivara, odd 3n light dimension energy states systems, perturbation points energy, relax point energy states systems, stress perturbation energy states systems effect, super relative energy

Procedia PDF Downloads 329

Authors: Michael McMahon

Abstract:

The use of media (video/animation/graphics) has long been used by athletes, coaches, and sports scientists to analyse and improve performance in technical skills and team tactics. Sports educators are increasingly open to the use of technology to support coach and learner development. However, an overreliance is a concern., This paper is part of a larger Ph.D. study looking into these new challenges for Sports Educators. Most notably, how to exploit the deep-learning potential of Digital Media among expert learners, how to instruct sports educators to create effective media content that fosters deep learning, and finally, how to make the process manageable and cost-effective. Central to the study is Richard Mayers Cognitive Theory of Multimedia Learning. Mayers Multimedia Learning Theory proposes twelve principles that shape the design and organization of multimedia presentations to improve learning and reduce cognitive load. For example, the Prior Knowledge principle suggests and highlights different learning outcomes for Novice and Non-Novice learners, respectively. Little research, however, is available to support this principle in modified domains (e.g., sports tactics and strategy). As a foundation for further research, this paper compares and contrasts a range of contemporary multimedia sports coaching content and assesses how they perform as learning tools for Strategic and Tactical Play Acquisition among elite sports practitioners. The stress tests applied are guided by Mayers's twelve Multimedia Learning Principles. The focus is on the elite athletes and whether current coaching digital media content does foster improved sports learning among this cohort. The sport of Gaelic Football was selected as it has high strategic and tactical play content, a wide range of Practitioner skill levels (Novice to Elite), and also a significant volume of Multimedia Coaching Content available for analysis. It is hoped the resulting data will help identify and inform the future instructional content design and delivery for Sports Practitioners and help promote best design practices optimal for different levels of expertise.

Keywords: multimedia learning, e-learning, design for learning, ICT

Procedia PDF Downloads 87

Authors: Li Xiaoge, Wang Chaodong

Abstract:

We introduce the first Chinese Coreference Resolution Model based on BERT (CCRM-BERT) and show that it significantly outperforms all previous work. The key idea is to consider the features of the mention, such as part of speech, width of spans, distance between spans, etc. And the influence of each features on the model is analyzed. The model computes mention embeddings that combine BERT with features. Compared to the existing state-of-the-art span-ranking approach, our model significantly improves accuracy on the Chinese OntoNotes benchmark.

Keywords: BERT, coreference resolution, deep learning, nature language processing

Procedia PDF Downloads 198

Authors: Chanhoe Kang, Changhyun Lee, Seock-Hee Jun, Yeong-Tae Oh

Abstract:

Offshore floating structure under the various environmental conditions maintains a fixed position by mooring system. Environmental conditions, vessel motions and mooring loads are applied to mooring lines as the dynamic tension. Because global responses of mooring system in deep water are specified as wave frequency and low frequency response, they should be calculated from the time-domain analysis due to non-linear dynamic characteristics. To take into account all mooring loads, environmental conditions, added mass and damping terms at each time step, a lot of computation time and capacities are required. Thus, under the premise that reliable fatigue damage could be derived through reasonable analysis method, it is necessary to reduce the analysis cases through the sensitivity studies and appropriate assumptions. In this paper, effects in fatigue are studied for spread mooring system connected with oil FPSO which is positioned in deep water of West Africa offshore. The target FPSO with two Mbbls storage has 16 spread mooring lines (4 bundles x 4 lines). The various sensitivity studies are performed for environmental loads, type of responses, vessel offsets, mooring position, loading conditions and riser behavior. Each parameter applied to the sensitivity studies is investigated from the effects of fatigue damage through fatigue analysis. Based on the sensitivity studies, the following results are presented: Wave loads are more dominant in terms of fatigue than other environment conditions. Wave frequency response causes the higher fatigue damage than low frequency response. The larger vessel offset increases the mean tension and so it results in the increased fatigue damage. The external line of each bundle shows the highest fatigue damage by the governed vessel pitch motion due to swell wave conditions. Among three kinds of loading conditions, ballast condition has the highest fatigue damage due to higher tension. The riser damping occurred by riser behavior tends to reduce the fatigue damage. The various analysis results obtained from these sensitivity studies can be used for a simplified fatigue analysis of spread mooring line as the reference.

Keywords: mooring system, fatigue analysis, time domain, non-linear dynamic characteristics

Procedia PDF Downloads 324

Authors: Giovanna Borges Bottino, Luis Felipe Freitas do Nascimento Alves Teixeira

Abstract:

This article aims to present a case study of the National Civil Aviation Agency (ANAC) in Brazil, ANAC-id. ANAC-id is the artificial intelligence algorithm developed for image analysis that recognizes standard images of unobstructed and uprighted face without sunglasses, allowing to identify potential inconsistencies. It combines YOLO architecture and 3 libraries in python - face recognition, face comparison, and deep face, providing robust analysis with high level of accuracy.

Keywords: artificial intelligence, deepface, face compare, face recognition, YOLO, computer vision

Procedia PDF Downloads 144

Authors: B. R. Campomanes-Alvarez, P. Quiros, B. Fernandez

Abstract:

Automatic Speech Recognition (ASR) is a machine-based process of decoding and transcribing oral speech. A typical ASR system receives acoustic input from a speaker or an audio file, analyzes it using algorithms, and produces an output in the form of a text. Some speech recognition systems use Hidden Markov Models (HMMs) to deal with the temporal variability of speech and Gaussian Mixture Models (GMMs) to determine how well each state of each HMM fits a short window of frames of coefficients that represents the acoustic input. Another way to evaluate the fit is to use a feed-forward neural network that takes several frames of coefficients as input and produces posterior probabilities over HMM states as output. Deep neural networks (DNNs) that have many hidden layers and are trained using new methods have been shown to outperform GMMs on a variety of speech recognition systems. Acoustic models for state-of-the-art ASR systems are usually training on massive amounts of data. However, audio files with their corresponding transcriptions can be difficult to obtain, especially in the Spanish language. Hence, in the case of these low-resource scenarios, building an ASR model is considered as a complex task due to the lack of labeled data, resulting in an under-trained system. Semi-supervised learning approaches arise as necessary tasks given the high cost of transcribing audio data. The main goal of this proposal is to develop a procedure based on acoustic semi-supervised learning for Spanish ASR systems by using DNNs. This semi-supervised learning approach consists of: (a) Training a seed ASR model with a DNN using a set of audios and their respective transcriptions. A DNN with a one-hidden-layer network was initialized; increasing the number of hidden layers in training, to a five. A refinement, which consisted of the weight matrix plus bias term and a Stochastic Gradient Descent (SGD) training were also performed. The objective function was the cross-entropy criterion. (b) Decoding/testing a set of unlabeled data with the obtained seed model. (c) Selecting a suitable subset of the validated data to retrain the seed model, thereby improving its performance on the target test set. To choose the most precise transcriptions, three confidence scores or metrics, regarding the lattice concept (based on the graph cost, the acoustic cost and a combination of both), was performed as selection technique. The performance of the ASR system will be calculated by means of the Word Error Rate (WER). The test dataset was renewed in order to extract the new transcriptions added to the training dataset. Some experiments were carried out in order to select the best ASR results. A comparison between a GMM-based model without retraining and the DNN proposed system was also made under the same conditions. Results showed that the semi-supervised ASR-model based on DNNs outperformed the GMM-model, in terms of WER, in all tested cases. The best result obtained an improvement of 6% relative WER. Hence, these promising results suggest that the proposed technique could be suitable for building ASR models in low-resource environments.

Keywords: automatic speech recognition, deep neural networks, machine learning, semi-supervised learning

Procedia PDF Downloads 328

Authors: Kriddikorn Kaewwongsri, Nikom Suvonvorn

Abstract:

In the deep south of Thailand, checkpoints for people verification are necessary for the security management of risk zones, such as official buildings in the conflict area. In this paper, we propose an automatic checkpoint system that verifies persons using information from ID cards and facial features. The methods for a person’s information abstraction and verification are introduced based on useful information such as ID number and name, extracted from official cards, and facial images from videos. The proposed system shows promising results and has a real impact on the local society.

Keywords: face comparison, card recognition, OCR, checkpoint system, authentication

Procedia PDF Downloads 313

Authors: Jun Seung Woo, Shin Dong Ho

Abstract:

The Image Captioning models with Attention technology have developed significantly compared to previous models, but it is still unsatisfactory in recognizing images. We perform an extensive search over seven interesting Convolutional Neural Networks(CNN) architectures to analyze the behavior of different models for image captioning. We compared seven different CNN Architectures, according to batch size, using on public benchmarks: MS-COCO datasets. In our experimental results, DenseNet and InceptionV3 got about 14% loss and about 160sec training time per epoch. It was the most satisfactory result among the seven CNN architectures after training 50 epochs on GPU.

Keywords: deep learning, image captioning, CNN architectures, densenet, inceptionV3

Procedia PDF Downloads 119

Authors: Mahmood Niroobakhsh

Abstract:

This article deals with special structuralism approaches to explain a certain kind of social problem. Widespread presence of poverty is a reminder of deep-rooted unresolved problems of social relations. The expected role from an individual for the social system recognizes poverty derived from an interrelated social structure. By the time, enabled to act on his role in the course of social interaction, reintegration of the poor in society may take place. Poverty and housing type are reflections of the underlying social structure, primarily structure’s elements, systemic interrelations, and the overall strength or weakness of that structure. Poverty varies based on social structure in that the stronger structures are less likely to produce poverty.

Keywords: absolute poverty, relative poverty, social structure, urban poverty

Procedia PDF Downloads 666

Authors: Amitkumar R. Shelar, B. P. Ronge, Sridevi Seshabhattar, R. M. Wabale

Abstract:

This paper gives knowledge about the behavior of cold rolled steel IS 513_2008 CR2_D having grade D for the reduction of ductile damage. CR specifies Cold Rolled and D for Drawing grade. Problems encountered during sheet metal forming operations are dent, wrinkles, thinning, spring back, insufficient stretching etc. In this paper, wrinkle defect was studied experimentally and by using FE software on one of the auto components due to which its functionality was decreased. Experimental result and simulation result were found to be in agreement.

Keywords: deep drawing, FE software-LS DYNA, friction, wrinkling

Procedia PDF Downloads 479

Authors: Ananya Gangavarapu

Abstract:

Convolutional Neural Networks (CNN) based models are providing diagnostic capabilities on par with the medical specialists in many specialty areas. However, collecting the medical data for training purposes is very challenging because of the increased regulations around data collections and privacy concerns around personal health data. The gathering of the data becomes even more difficult if the capture devices are edge-based mobile devices (like smartphones) with feeble wireless connectivity in rural/remote areas. In this paper, I would like to highlight Federated Learning approach to mitigate data privacy and security issues.

Keywords: deep learning in healthcare, data privacy, federated learning, training in distributed environment

Procedia PDF Downloads 127

Authors: Fatima Al-Aswadi, Chan Yong

Abstract:

With the large volume of unstructured data that increases day by day on the web, the motivation of representing the knowledge in this data in the machine processable form is increased. Ontology is one of the major cornerstones of representing the information in a more meaningful way on the semantic Web. The goal of Ontology learning from text is to elicit and represent domain knowledge in the machine readable form. This paper aims to give a follow-up review on the ontology learning systems from text and some of their defects. Furthermore, it discusses how far the ontology learning process will enhance in the future.

Keywords: concept discovery, deep learning, ontology learning, semantic relation, semantic web

Procedia PDF Downloads 502

Authors: Raúl García de la Cruz

Abstract:

In the state of Hidalgo and to the vicinity to the state of Mexico, there is a network of people who also share a valley bordered by hills with agave landscape of cacti and shared a bond of building traditions inherited from pre-Hispanic times and according to their material resources, habits and needs have been adapted in time. Weather has played an important role in the way buildings and roofs are constructed. Throughout the centuries, the population has developed very sophisticated building techniques like the flat roof, made out of a layer of earth; that is usually identified as belonging to architecture of the desert, but it can also be found in other climates, such as semi-arid and even template climates. It is an example of a constructive logic applied efficiently to various cultures proving its thermal isolation. So far it has done a review and analysis of the use of the roof in different areas, from pre-Hispanic architecture to traditional Moroccan architecture , finding great similarities in the elements of the system to be incorporated into the contemporary architecture. The rescue of a lore that dissolves with the changing environment, depends in principle on the links created towards the use of environmental resources as the anchor of the people to retain and preserve a building tradition which has viability deep league with the possibility of obtaining the raw material from the immediate environment. The objective of the research is the documentation of existing earth flat roofs in the state of Hidalgo and Mexico, as evidence of the importance of constructive system and its historical value in the area, considering its environmental, social aspects, also understanding the process of transformation of public housing at the time replaced the traditional techniques for industrial materials on a path towards urbanization. So far it has done a review and analysis of the use of the roof in different areas, from pre-Hispanic architecture to traditional Moroccan architecture, finding great similarities in the elements of the system to be incorporated into the contemporary architecture. The rescue of a lore that dissolves with the changing environment, depends in principle on the links created towards the use of environmental resources as the anchor of the people to retain and preserve a building tradition which has viability deep league with the possibility of obtaining the raw material from the immediate environment.

Keywords: earth roof, low impact building system, sustainable architecture, vernacular architecture

Procedia PDF Downloads 446

Authors: Athena Johnson

Abstract:

Veganism has seen a rapid increase in members over recent years. Understanding the mechanisms of social change associated with these dietary practices in relation to gender is significant as these groups may seem small, but they have a large impact as they influence many and change the food market. This research article's basic methodology is primarily a deep article research literature review with empirical research. The research findings show that the popularity of veganism is growing, in large part due to the extensive use of social media, which dispels longstanding gendered connotations with food, such as the correlations between meat and masculinity.

Keywords: diversity, gender roles, social media, veganism

Procedia PDF Downloads 102

Authors: Constanza Levicán, Andrés Aparicio, Rodrigo F. Cádiz

Abstract:

The artistic usage of Brain-computer interfaces (BCI), initially intended for medical purposes, has increased in the past few years as they become more affordable and available for the general population. One interesting question that arises from this practice is whether it is possible to compose or perform music by using only the brain as a musical instrument. In order to approach this question, we propose a BCI for musical composition, based on the representation of some mental states as the musician thinks about sounds. We developed software, called Insight2OSC, that allows the usage of the Emotiv Insight device as a musical instrument, by sending the EEG data to audio processing software such as MaxMSP through the OSC protocol. We provide two compositional applications bundled with the software, which we call Mapping your Mental State and Thinking On. The signals produced by the brain have different frequencies (or rhythms) depending on the level of activity, and they are classified as one of the following waves: delta (0.5-4 Hz), theta (4-8 Hz), alpha (8-13 Hz), beta (13-30 Hz), gamma (30-50 Hz). These rhythms have been found to be related to some recognizable mental states. For example, the delta rhythm is predominant in a deep sleep, while beta and gamma rhythms have higher amplitudes when the person is awake and very concentrated. Our first application (Mapping your Mental State) produces different sounds representing the mental state of the person: focused, active, relaxed or in a state similar to a deep sleep by the selection of the dominants rhythms provided by the EEG device. The second application relies on the physiology of the brain, which is divided into several lobes: frontal, temporal, parietal and occipital. The frontal lobe is related to abstract thinking and high-level functions, the parietal lobe conveys the stimulus of the body senses, the occipital lobe contains the primary visual cortex and processes visual stimulus, the temporal lobe processes auditory information and it is important for memory tasks. In consequence, our second application (Thinking On) processes the audio output depending on the users’ brain activity as it activates a specific area of the brain that can be measured using the Insight device.

Keywords: BCI, music composition, emotiv insight, OSC

Procedia PDF Downloads 306

Authors: Anoop T. R., Otman Basir, Robert F. Hess, Eileen E. Birch, Brooke A. Koritala, Reed M. Jost, Becky Luu, David Stager, Ben Thompson

Abstract:

Strabismus refers to a misalignment of the eyes. Early detection and treatment of strabismus in childhood can prevent the development of permanent vision loss due to abnormal development of visual brain areas. We developed a two-stage method for strabismus detection and classification based on photographs of the face. The first stage detects the presence or absence of strabismus, and the second stage classifies the type of strabismus. The first stage comprises face detection using Haar cascade, facial landmark estimation, face alignment, aligned face landmark detection, segmentation of the eye region, and detection of strabismus using VGG 16 convolution neural networks. Face alignment transforms the face to a canonical pose to ensure consistency in subsequent analysis. Using facial landmarks, the eye region is segmented from the aligned face and fed into a VGG 16 CNN model, which has been trained to classify strabismus. The CNN determines whether strabismus is present and classifies the type of strabismus (exotropia, esotropia, and vertical deviation). If stage 1 detects strabismus, the eye region image is fed into stage 2, which starts with the estimation of pupil center coordinates using mask R-CNN deep neural networks. Then, the distance between the pupil coordinates and eye landmarks is calculated along with the angle that the pupil coordinates make with the horizontal and vertical axis. The distance and angle information is used to characterize the degree and direction of the strabismic eye misalignment. This model was tested on 100 clinically labeled images of children with (n = 50) and without (n = 50) strabismus. The True Positive Rate (TPR) and False Positive Rate (FPR) of the first stage were 94% and 6% respectively. The classification stage has produced a TPR of 94.73%, 94.44%, and 100% for esotropia, exotropia, and vertical deviations, respectively. This method also had an FPR of 5.26%, 5.55%, and 0% for esotropia, exotropia, and vertical deviation, respectively. The addition of one more feature related to the location of corneal light reflections may reduce the FPR, which was primarily due to children with pseudo-strabismus (the appearance of strabismus due to a wide nasal bridge or skin folds on the nasal side of the eyes).

Keywords: strabismus, deep neural networks, face detection, facial landmarks, face alignment, segmentation, VGG 16, mask R-CNN, pupil coordinates, angle deviation, horizontal and vertical deviation

Procedia PDF Downloads 72

Authors: Alona Faktor

Abstract:

In this work, we present a NN-based computational model that can perform attention shifts according to high-level instruction. The instruction specifies the type of attentional shift using explicit geometrical relation. The instruction also can be of cognitive nature, specifying more complex human-human interaction or human-object interaction, or object-object interaction. Applying this approach sequentially allows obtaining a structural description of an image. A novel data-set of interacting humans and objects is constructed using a computer graphics engine. Using this data, we perform systematic research of relational segmentation shifts.

Keywords: cognitive science, attentin, deep learning, generalization

Procedia PDF Downloads 186

Authors: Isahakyan Heghine

Abstract:

Intertextuality, being in the centre of attention of both linguists and literary critics, is vividly expressed in the outstanding British novelist and philosopher J. Fowles' works. 'The Magus’ is a deep psychological and philosophical novel with vivid intertextual links with the Greek mythology and authors from different epochs. The aim of the paper is to show how intertextuality might serve as a dialogue between two authors (J. Fowles and J. Donne) disguised in the dialogue of two protagonists of the novel : Conchis and Nicholas. Contrastive viewpoints concerning man's isolation, loneliness are stated in the dialogue. Due to the conceptual analysis of the text it becomes possible both to decode the conceptual information of the text and find out its intertextual links.

Keywords: dialogue, conceptual analysis, isolation, intertextuality

Procedia PDF Downloads 317

Authors: Rakesh Dogra, Arun Kumar, Arvind Kumar Sharma

Abstract:

This paper reports the thermoluminescence as well as optical properties of rare earth doped lithium fluoride (LiF) nanophosphor, synthesized via chemical route. The rare earth impurities (Yb and Sm) have been observed to increase the deep trap center capacity, which, in turn, enhance the radiation resistance of the LiF. This suggests the viability of these materials to be used as high dose thermoluminescent detectors at high temperature. Further, optical absorption measurements revealed the formation of radiation induced stable color centers in LiF at room temperature, which are independent of the rare earth dopant.

Keywords: lithium flouride, thermoluminescence, UV-VIS spectroscopy, Gamma radiations

Procedia PDF Downloads 133

Authors: Qianwei Cheng, A. K. M. Mahbubur Rahman, Anis Sarker, Abu Bakar Siddik Nayem, Ovi Paul, Amin Ahsan Ali, M. Ashraful Amin, Ryosuke Shibasaki, Moinul Zaber

Abstract:

Thomas Friedman, in his famous book, argued that the world in this 21st century is flat and will continue to be flatter. This is attributed to rapid globalization and the interdependence of humanity that engendered tremendous in-flow of human migration towards the urban spaces. In order to keep the urban environment sustainable, policy makers need to plan based on extensive analysis of the urban environment. With the advent of high definition satellite images, high resolution data, computational methods such as deep neural network analysis, and hardware capable of high-speed analysis; urban planning is seeing a paradigm shift. Legacy data on urban environments are now being complemented with high-volume, high-frequency data. However, the first step of understanding urban space lies in useful categorization of the space that is usable for data collection, analysis, and visualization. In this paper, we propose a pragmatic categorization method that is readily usable for machine analysis and show applicability of the methodology on a developing world setting. Categorization to plan sustainable urban spaces should encompass the buildings and their surroundings. However, the state-of-the-art is mostly dominated by classification of building structures, building types, etc. and largely represents the developed world. Hence, these methods and models are not sufficient for developing countries such as Bangladesh, where the surrounding environment is crucial for the categorization. Moreover, these categorizations propose small-scale classifications, which give limited information, have poor scalability and are slow to compute in real time. Our proposed method is divided into two steps-categorization and automation. We categorize the urban area in terms of informal and formal spaces and take the surrounding environment into account. 50 km × 50 km Google Earth image of Dhaka, Bangladesh was visually annotated and categorized by an expert and consequently a map was drawn. The categorization is based broadly on two dimensions-the state of urbanization and the architectural form of urban environment. Consequently, the urban space is divided into four categories: 1) highly informal area; 2) moderately informal area; 3) moderately formal area; and 4) highly formal area. In total, sixteen sub-categories were identified. For semantic segmentation and automatic categorization, Google’s DeeplabV3+ model was used. The model uses Atrous convolution operation to analyze different layers of texture and shape. This allows us to enlarge the field of view of the filters to incorporate larger context. Image encompassing 70% of the urban space was used to train the model, and the remaining 30% was used for testing and validation. The model is able to segment with 75% accuracy and 60% Mean Intersection over Union (mIoU). In this paper, we propose a pragmatic categorization method that is readily applicable for automatic use in both developing and developed world context. The method can be augmented for real-time socio-economic comparative analysis among cities. It can be an essential tool for the policy makers to plan future sustainable urban spaces.

Keywords: semantic segmentation, urban environment, deep learning, urban building, classification

Procedia PDF Downloads 174

Authors: Leila Keshavarz Afshar, Hedieh Sajedi

Abstract:

Estimation of biological brain age from MR images is a topic that has been much addressed in recent years due to the importance it attaches to early diagnosis of diseases such as Alzheimer's. In this paper, we use a 3D Convolutional Neural Network (CNN) to provide a method for estimating the biological age of the brain. The 3D-CNN model is trained by MRI data that has been normalized. In addition, to reduce computation while saving overall performance, some effectual slices are selected for age estimation. By this method, the biological age of individuals using selected normalized data was estimated with Mean Absolute Error (MAE) of 4.82 years.

Keywords: brain age estimation, biological age, 3D-CNN, deep learning, T1-weighted image, SPM, preprocessing, MRI, canny, gray matter

Procedia PDF Downloads 135

Authors: Asmaa Zaki M., Ahmed Abd El Aziz, Heba A. Fayed, Moustafa H. Aly

Abstract:

ISLs are the most popular choice for deep space communications because these links are attractive alternatives to present day microwave links. This paper explored the allowable high data rate in this link over different orbits, which is affected by variation in modulation scheme and detector type. Moreover, the objective of this paper is to optimize and analyze the performance of ISL in terms of Q-factor and Minimum Bit Error Rate (Min-BER) based on different detectors comprising some parameters.

Keywords: free space optics (FSO), field of view (FOV), inter satellite link (ISL), optical wireless communication (OWC)

Procedia PDF Downloads 383

Authors: Jonathan Gong

Abstract:

Purpose AI-driven solutions are at the forefront of many pathology and medical imaging methods. Using algorithms designed to better the experience of medical professionals within their respective fields, the efficiency and accuracy of diagnosis can improve. In particular, X-rays are a fast and relatively inexpensive test that can diagnose diseases. In recent years, X-rays have not been widely used to detect and diagnose COVID-19. The under use of Xrays is mainly due to the low diagnostic accuracy and confounding with pneumonia, another respiratory disease. However, research in this field has expressed a possibility that artificial neural networks can successfully diagnose COVID-19 with high accuracy. Models and Data The dataset used is the COVID-19 Radiography Database. This dataset includes images and masks of chest X-rays under the labels of COVID-19, normal, and pneumonia. The classification model developed uses an autoencoder and a pre-trained convolutional neural network (DenseNet201) to provide transfer learning to the model. The model then uses a deep neural network to finalize the feature extraction and predict the diagnosis for the input image. This model was trained on 4035 images and validated on 807 separate images from the ones used for training. The images used to train the classification model include an important feature: the pictures are cropped beforehand to eliminate distractions when training the model. The image segmentation model uses an improved U-Net architecture. This model is used to extract the lung mask from the chest X-ray image. The model is trained on 8577 images and validated on a validation split of 20%. These models are calculated using the external dataset for validation. The models’ accuracy, precision, recall, f1-score, IOU, and loss are calculated. Results The classification model achieved an accuracy of 97.65% and a loss of 0.1234 when differentiating COVID19-infected, pneumonia-infected, and normal lung X-rays. The segmentation model achieved an accuracy of 97.31% and an IOU of 0.928. Conclusion The models proposed can detect COVID-19, pneumonia, and normal lungs with high accuracy and derive the lung mask from a chest X-ray with similarly high accuracy. The hope is for these models to elevate the experience of medical professionals and provide insight into the future of the methods used.

Keywords: artificial intelligence, convolutional neural networks, deep learning, image processing, machine learning

Procedia PDF Downloads 118

Authors: Maxence Queyrel, Edi Prifti, Alexandre Templier, Jean-Daniel Zucker

Abstract:

Analysis of the human microbiome using metagenomic sequencing data has demonstrated high ability in discriminating various human diseases. Raw metagenomic sequencing data require multiple complex and computationally heavy bioinformatics steps prior to data analysis. Such data contain millions of short sequences read from the fragmented DNA sequences and stored as fastq files. Conventional processing pipelines consist in multiple steps including quality control, filtering, alignment of sequences against genomic catalogs (genes, species, taxonomic levels, functional pathways, etc.). These pipelines are complex to use, time consuming and rely on a large number of parameters that often provide variability and impact the estimation of the microbiome elements. Training Deep Neural Networks directly from raw sequencing data is a promising approach to bypass some of the challenges associated with mainstream bioinformatics pipelines. Most of these methods use the concept of word and sentence embeddings that create a meaningful and numerical representation of DNA sequences, while extracting features and reducing the dimensionality of the data. In this paper we present an end-to-end approach that classifies patients into disease groups directly from raw metagenomic reads: metagenome2vec. This approach is composed of four steps (i) generating a vocabulary of k-mers and learning their numerical embeddings; (ii) learning DNA sequence (read) embeddings; (iii) identifying the genome from which the sequence is most likely to come and (iv) training a multiple instance learning classifier which predicts the phenotype based on the vector representation of the raw data. An attention mechanism is applied in the network so that the model can be interpreted, assigning a weight to the influence of the prediction for each genome. Using two public real-life data-sets as well a simulated one, we demonstrated that this original approach reaches high performance, comparable with the state-of-the-art methods applied directly on processed data though mainstream bioinformatics workflows. These results are encouraging for this proof of concept work. We believe that with further dedication, the DNN models have the potential to surpass mainstream bioinformatics workflows in disease classification tasks.

Keywords: deep learning, disease prediction, end-to-end machine learning, metagenomics, multiple instance learning, precision medicine

Procedia PDF Downloads 113

Authors: Michel Moliere

Abstract:

In the next decades, the thermal power generation segment will survive only if it achieves deep mutations, including drastical abatements of CO2 emissions and strong efficiency gains. In this challenging perspective, stationary gas turbines appear as serious candidates to lead the energy transition. Indeed, during the past decades, these turbomachines have made brisk technological advances in terms of efficiency, reliability, fuel flex (including the combustion of hydrogen), and the ability to hybridize with regenrables. It is, therefore, timely to summarize the progresses achieved by gas turbines in the recent past and to examine what are their assets to face the challenges of the energy transition.

Keywords: energy transition, gas turbines, decarbonization, power generation

Procedia PDF Downloads 200

Authors: Dumont Maxime, Correia Carlos, Sauvage Jean-François, Schwartz Noah, Gray Morgan

Abstract:

Context: The concept of the segmented telescope is unavoidable to build extremely large telescopes (ELT) in the quest for spatial resolution, but it also allows one to fit a large telescope within a reduced volume of space (JWST) or into an even smaller volume (Standard Cubesat). Cubesats have tight constraints on the computational burden available and the small payload volume allowed. At the same time, they undergo thermal gradients leading to large and evolving optical aberrations. The pupil segmentation comes nevertheless with an obvious difficulty: to co-phase the different segments. The CubeSat constraints prevent the use of a dedicated wavefront sensor (WFS), making the focal-plane images acquired by the science detector the most practical alternative. Yet, one of the challenges for the wavefront sensing is the non-linearity between the image intensity and the phase aberrations. Plus, for Earth observation, the object is unknown and unrepeatable. Recently, several studies have suggested Neural Networks (NN) for wavefront sensing; especially convolutional NN, which are well known for being non-linear and image-friendly problem solvers. Aims: We study in this paper the prospect of using NN to measure the phasing aberrations of a segmented pupil from the focal-plane image directly without a dedicated wavefront sensing. Methods: In our application, we take the case of a deployable telescope fitting in a CubeSat for Earth observations which triples the aperture size (compared to the 10cm CubeSat standard) and therefore triples the angular resolution capacity. In order to reach the diffraction-limited regime in the visible wavelength, typically, a wavefront error below lambda/50 is required. The telescope focal-plane detector, used for imaging, will be used as a wavefront-sensor. In this work, we study a point source, i.e. the Point Spread Function [PSF] of the optical system as an input of a VGG-net neural network, an architecture designed for image regression/classification. Results: This approach shows some promising results (about 2nm RMS, which is sub lambda/50 of residual WFE with 40-100nm RMS of input WFE) using a relatively fast computational time less than 30 ms which translates a small computation burder. These results allow one further study for higher aberrations and noise.

Keywords: wavefront sensing, deep learning, deployable telescope, space telescope

Procedia PDF Downloads 88

Authors: Naeem Ullah, Menglan Duan, Mac Darlington Uche Onuoha

Abstract:

The lowering of subsea equipment into the deep waters is a challenging job due to the harsh offshore environment. Many researchers have introduced various installation systems to deploy the payload safely into the deep oceans. In general practice, dual floating vessels are not employed owing to the prevalent safety risks and hazards caused by ever-increasing dynamical effects sourced by mutual interaction between the bodies. However, while keeping in the view of the optimal grounds, such as economical one, the Y-method, the two conventional tugboats supporting the equipment by the two independent strands connected to a tri-plate above the equipment, has been employed to study multibody dynamics of the dual barge lifting operations. In this study, the two tugboats and the suspended payload (Y-method) are deployed for the lowering of subsea equipment into the deep waters as a multibody dynamic system. The two-wire ropes are used for the lifting and installation operation by this Y-method installation system. 6-dof (degree of freedom) for each body are considered to establish coupled 18-dof multibody model by embedding technique or velocity transformation technique. The fundamental and prompt advantage of this technique is that the constraint forces can be eliminated directly, and no extra computational effort is required for the elimination of the constraint forces. The inertial frame of reference is taken at the surface of the water as the time-independent frame of reference, and the floating frames of reference are introduced in each body as the time-dependent frames of reference in order to formulate the velocity transformation matrix. The local transformation of the generalized coordinates to the inertial frame of reference is executed by applying the Euler Angle approach. The spherical joints are articulated amongst the multibody as the kinematic joints. The hydrodynamic force, the two-strand forces, the hydrostatic force, and the mooring forces are taken into consideration as the external forces. The radiation force of the hydrodynamic force is obtained by employing the Cummins equation. The wave exciting part of the hydrodynamic force is obtained by using force response amplitude operators (RAOs) that are obtained by the commercial solver ‘OpenFOAM’. The strand force is obtained by considering the wire rope as an elastic spring. The nonlinear hydrostatic force is obtained by the pressure integration technique at each time step of the wave movement. The mooring forces are evaluated by using Faltinsen analytical approach. ‘The Runge Kutta Method’ of Fourth-Order is employed to evaluate the coupled equations of motion obtained for 18-dof multibody model. The results are correlated with the simulated Orcaflex Model. Moreover, the results from Orcaflex Model are compared with the MOSES Model from previous studies. The MBDS of single barge lifting operation from the former studies are compared with the MBDS of the established dual barge lifting operation. The dynamics of the dual barge lifting operation are found larger in magnitude as compared to the single barge lifting operation. It is noticed that the traction at the top connection point of the cable decreases with the increase in the length, and it becomes almost constant after passing through the splash zone.

Keywords: dual barge lifting operation, Y-method, multibody dynamics, shipbuilding, installation of subsea equipment, shipbuilding

Procedia PDF Downloads 196