Search results for: deep tendon reflexes
1325 Towards Developing A Rural South African Child Into An Engineering Graduates With Conceptual And Critical Thinking Skills
Authors: Betty Kibirige
Abstract:
Students entering the University of Zululand (UNIZULU) Science Faculty mostly come with skills that allow them to prepare for exams and pass them in order to satisfy requirements for entry into a tertiary Institution. Some students hail from deep rural schools with limited facilities, while others come from well-resourced schools. Personal experience has shown that it may take a student the whole time at a tertiary institution following the same skills as those acquired in high school as a sure means of entering the next level in their development, namely a postgraduate program. While it is apparent that at this point in human history, it is totally impossible to teach all the possible content in any one subject, many academics approach teaching and learning from the traditional point of view. It therefore became apparent to explore ways of developing a graduate that will be able to approach life with skills that allows them to navigate knowledge by applying conceptual and critical thinking skills. Recently, the Science Faculty at the University of Zululand introduced two Engineering programs. In an endeavour to approach the development of the Engineering graduate in this institution to be able to tackle problem-solving in the present-day excessive information availability, it became necessary to study and review approaches used by various academics in order to settle for a possible best approach to the challenge at hand. This paper focuses on the development of a deep rural child in a graduate with conceptual and critical thinking skills as major attributes possessed upon graduation. For this purpose, various approaches were studied. A combination of these approaches was repackaged to form an approach that may appear novel to UNIZULU and the rural child, especially for the Engineering discipline. The approach was checked by offering quiz questions to students participating in an engineering module, observing test scores in the targeted module and make comparative studies. Test results are discussed in the article. It was concluded that students’ graduate attributes could be tailored subconsciously to indeed include conceptual and critical thinking skills, but through more than one approach depending mainly on the student's high school background.Keywords: graduate attributes, conceptual skills, critical thinking skills, traditional approach
Procedia PDF Downloads 2321324 Estimating Poverty Levels from Satellite Imagery: A Comparison of Human Readers and an Artificial Intelligence Model
Authors: Ola Hall, Ibrahim Wahab, Thorsteinn Rognvaldsson, Mattias Ohlsson
Abstract:
The subfield of poverty and welfare estimation that applies machine learning tools and methods on satellite imagery is a nascent but rapidly growing one. This is in part driven by the sustainable development goal, whose overarching principle is that no region is left behind. Among other things, this requires that welfare levels can be accurately and rapidly estimated at different spatial scales and resolutions. Conventional tools of household surveys and interviews do not suffice in this regard. While they are useful for gaining a longitudinal understanding of the welfare levels of populations, they do not offer adequate spatial coverage for the accuracy that is needed, nor are their implementation sufficiently swift to gain an accurate insight into people and places. It is this void that satellite imagery fills. Previously, this was near-impossible to implement due to the sheer volume of data that needed processing. Recent advances in machine learning, especially the deep learning subtype, such as deep neural networks, have made this a rapidly growing area of scholarship. Despite their unprecedented levels of performance, such models lack transparency and explainability and thus have seen limited downstream applications as humans generally are apprehensive of techniques that are not inherently interpretable and trustworthy. While several studies have demonstrated the superhuman performance of AI models, none has directly compared the performance of such models and human readers in the domain of poverty studies. In the present study, we directly compare the performance of human readers and a DL model using different resolutions of satellite imagery to estimate the welfare levels of demographic and health survey clusters in Tanzania, using the wealth quintile ratings from the same survey as the ground truth data. The cluster-level imagery covers all 608 cluster locations, of which 428 were classified as rural. The imagery for the human readers was sourced from the Google Maps Platform at an ultra-high resolution of 0.6m per pixel at zoom level 18, while that of the machine learning model was sourced from the comparatively lower resolution Sentinel-2 10m per pixel data for the same cluster locations. Rank correlation coefficients of between 0.31 and 0.32 achieved by the human readers were much lower when compared to those attained by the machine learning model – 0.69-0.79. This superhuman performance by the model is even more significant given that it was trained on the relatively lower 10-meter resolution satellite data while the human readers estimated welfare levels from the higher 0.6m spatial resolution data from which key markers of poverty and slums – roofing and road quality – are discernible. It is important to note, however, that the human readers did not receive any training before ratings, and had this been done, their performance might have improved. The stellar performance of the model also comes with the inevitable shortfall relating to limited transparency and explainability. The findings have significant implications for attaining the objective of the current frontier of deep learning models in this domain of scholarship – eXplainable Artificial Intelligence through a collaborative rather than a comparative framework.Keywords: poverty prediction, satellite imagery, human readers, machine learning, Tanzania
Procedia PDF Downloads 911323 Experimental Study on Different Load Operation and Rapid Load-change Characteristics of Pulverized Coal Combustion with Self-preheating Technology
Authors: Hongliang Ding, Ziqu Ouyang
Abstract:
Under the basic national conditions that the energy structure is dominated by coal, it is of great significance to realize deep and flexible peak shaving of boilers in pulverized coal power plants, and maximize the consumption of renewable energy in the power grid, to ensure China's energy security and scientifically achieve the goals of carbon peak and carbon neutrality. With the promising self-preheating combustion technology, which had the potential of broad-load regulation and rapid response to load changes, this study mainly investigated the different load operation and rapid load-change characteristics of pulverized coal combustion. Four effective load-stabilization bases were proposed according to preheating temperature, coal gas composition (calorific value), combustion temperature (spatial mean temperature and mean square temperature fluctuation coefficient), and flue gas emissions (CO and NOx concentrations), on the basis of which the load-change rates were calculated to assess the load response characteristics. Due to the improvement of the physicochemical properties of pulverized coal after preheating, stable ignition and combustion conditions could be obtained even at a low load of 25%, with a combustion efficiency of over 97.5%, and NOx emission reached the lowest at 50% load, with the concentration of 50.97 mg/Nm3 (@6%O2). Additionally, the load ramp-up stage displayed higher load-change rates than the load ramp-down stage, with maximum rates of 3.30 %/min and 3.01 %/min, respectively. Furthermore, the driving force formed by high step load was conducive to the increase of load-change rate. The rates based on the preheating indicator attained the highest value of 3.30 %/min, while the rates based on the combustion indicator peaked at 2.71 %/min. In comparison, the combustion indicator accurately described the system’s combustion state and load changes, whereas the preheating indicator was easier to acquire, with a higher load-change rate, hence the appropriate evaluation strategy should depend on the actual situation. This study verified a feasible method for deep and flexible peak shaving of coal-fired power units, further providing basic data and technical supports for future engineering applications.Keywords: clean coal combustion, load-change rate, peak shaving, self-preheating
Procedia PDF Downloads 641322 Predictive Analysis of the Stock Price Market Trends with Deep Learning
Authors: Suraj Mehrotra
Abstract:
The stock market is a volatile, bustling marketplace that is a cornerstone of economics. It defines whether companies are successful or in spiral. A thorough understanding of it is important - many companies have whole divisions dedicated to analysis of both their stock and of rivaling companies. Linking the world of finance and artificial intelligence (AI), especially the stock market, has been a relatively recent development. Predicting how stocks will do considering all external factors and previous data has always been a human task. With the help of AI, however, machine learning models can help us make more complete predictions in financial trends. Taking a look at the stock market specifically, predicting the open, closing, high, and low prices for the next day is very hard to do. Machine learning makes this task a lot easier. A model that builds upon itself that takes in external factors as weights can predict trends far into the future. When used effectively, new doors can be opened up in the business and finance world, and companies can make better and more complete decisions. This paper explores the various techniques used in the prediction of stock prices, from traditional statistical methods to deep learning and neural networks based approaches, among other methods. It provides a detailed analysis of the techniques and also explores the challenges in predictive analysis. For the accuracy of the testing set, taking a look at four different models - linear regression, neural network, decision tree, and naïve Bayes - on the different stocks, Apple, Google, Tesla, Amazon, United Healthcare, Exxon Mobil, J.P. Morgan & Chase, and Johnson & Johnson, the naïve Bayes model and linear regression models worked best. For the testing set, the naïve Bayes model had the highest accuracy along with the linear regression model, followed by the neural network model and then the decision tree model. The training set had similar results except for the fact that the decision tree model was perfect with complete accuracy in its predictions, which makes sense. This means that the decision tree model likely overfitted the training set when used for the testing set.Keywords: machine learning, testing set, artificial intelligence, stock analysis
Procedia PDF Downloads 861321 Effect of Toxic Metals Exposure on Rat Behavior and Brain Morphology: Arsenic, Manganese
Authors: Tamar Bikashvili, Tamar Lordkipanidze, Ilia Lazrishvili
Abstract:
Heavy metals remain one of serious environmental problems due to their toxic effects. The effect of arsenic and manganese compounds on rat behavior and neuromorphology was studied. Wistar rats were assigned to four groups: rats in control group were given regular water, while rats in other groups drank water with final manganese concentration of 10 mg/L (group A), 20 mg/L (group B) and final arsenic concentration 68 mg/L (group C), respectively, for a month. To study exploratory and anxiety behavior and also to evaluate aggressive performance in “home cage” rats were tested in “Open Field” and to estimate learning and memory status multi-branched maze was used. Statistically significant increase of motor and oriental-searching activity in experimental groups was revealed by an open field test, which was expressed in increase of number of lines crossed, rearing and hole reflexes. Obtained results indicated the suppression of fear in rats exposed to manganese. Specifically, this was estimated by the frequency of getting to the central part of the open field. Experiments revealed that 30-day exposure to 10 mg/ml manganese did not stimulate aggressive behavior in rats, while exposure to the higher dose (20 mg/ml), 37% of initially non-aggressive animals manifested aggressive behavior. Furthermore, 25% of rats were extremely aggressive. Obtained data support the hypothesis that excess manganese in the body is one of the immediate causes of enhancement of interspecific predatory aggressive and violent behavior in rats. It was also discovered that manganese intoxication produces non-reversible severe learning disability and insignificant, reversible memory disturbances. Studies of rodents exposed to arsenic also revealed changes in the learning process. As it is known, the distribution of metal ions differs in various brain regions. The principle manganese accumulation was observed in the hippocampus and in the neocortex, while arsenic was predominantly accumulated in nucleus accumbens, striatum, and cortex. These brain regions play an important role in the regulation of emotional state and motor activity. Histopathological analyzes of brain sections illustrated two morphologically distinct altered phenotypes of neurons: (1) shrunk cells with indications of apoptosis - nucleus and cytoplasm were very difficult to be distinguished, the integrity of neuronal cytoplasm was not disturbed; and (2) swollen cells - with indications of necrosis. Pyknotic nucleus, plasma membrane disruption and cytoplasmic vacuoles were observed in swollen neurons and they were surrounded by activated gliocytes. It’s worth to mention that in the cortex the majority of damaged neurons were apoptotic while in subcortical nuclei –neurons were mainly necrotic. Ultrastructural analyses demonstrated that all cell types in the cortex and the nucleus caudatus represent destructed mitochondria, widened neurons’ vacuolar system profiles, increased number of lysosomes and degeneration of axonal endings.Keywords: arsenic, manganese, behavior, learning, neuron
Procedia PDF Downloads 3511320 Women's Religiosity as a Factor in the Persistence of Religious Traditions: Kazakhstan, the XX Century
Authors: G. Nadirova, B. Aktaulova
Abstract:
The main question of the research is- how did the Kazakhs manage to keep their religious thinking in the period of active propaganda of Soviet atheism, for seventy years of struggle against religion with the involvement of the scientific worldview as the primary means of proving the absence of the divine nature and materiality of the world? Our hypothesis is that In case of Kazakhstan the conservative female religious consciousness seems to have been a factor that helped to preserve the “everyday” religiousness of Kazakhs, which was far from deep theological contents of Islam, but able to revive in a short time after the decennia of proclaimed atheism.Keywords: woman, religious thinking, Kazakhstan, soviet ideology, rituals, family
Procedia PDF Downloads 2081319 Comparison of Extended Kalman Filter and Unscented Kalman Filter for Autonomous Orbit Determination of Lagrangian Navigation Constellation
Authors: Youtao Gao, Bingyu Jin, Tanran Zhao, Bo Xu
Abstract:
The history of satellite navigation can be dated back to the 1960s. From the U.S. Transit system and the Russian Tsikada system to the modern Global Positioning System (GPS) and the Globalnaya Navigatsionnaya Sputnikovaya Sistema (GLONASS), performance of satellite navigation has been greatly improved. Nowadays, the navigation accuracy and coverage of these existing systems have already fully fulfilled the requirement of near-Earth users, but these systems are still beyond the reach of deep space targets. Due to the renewed interest in space exploration, a novel high-precision satellite navigation system is becoming even more important. The increasing demand for such a deep space navigation system has contributed to the emergence of a variety of new constellation architectures, such as the Lunar Global Positioning System. Apart from a Walker constellation which is similar to the one adopted by GPS on Earth, a novel constellation architecture which consists of libration point satellites in the Earth-Moon system is also available to construct the lunar navigation system, which can be called accordingly, the libration point satellite navigation system. The concept of using Earth-Moon libration point satellites for lunar navigation was first proposed by Farquhar and then followed by many other researchers. Moreover, due to the special characteristics of Libration point orbits, an autonomous orbit determination technique, which is called ‘Liaison navigation’, can be adopted by the libration point satellites. Using only scalar satellite-to-satellite tracking data, both the orbits of the user and libration point satellites can be determined autonomously. In this way, the extensive Earth-based tracking measurement can be eliminated, and an autonomous satellite navigation system can be developed for future space exploration missions. The method of state estimate is an unnegligible factor which impacts on the orbit determination accuracy besides type of orbit, initial state accuracy and measurement accuracy. We apply the extended Kalman filter(EKF) and the unscented Kalman filter(UKF) to determinate the orbits of Lagrangian navigation satellites. The autonomous orbit determination errors are compared. The simulation results illustrate that UKF can improve the accuracy and z-axis convergence to some extent.Keywords: extended Kalman filter, autonomous orbit determination, unscented Kalman filter, navigation constellation
Procedia PDF Downloads 2741318 Surgical Treatment of Glaucoma – Literature and Video Review of Blebs, Tubes, and Micro-Invasive Glaucoma Surgeries (MIGS)
Authors: Ana Miguel
Abstract:
Purpose: Glaucoma is the second cause of worldwide blindness and the first cause of irreversible blindness. Trabeculectomy, the standard glaucoma surgery, has a success rate between 36.0% and 98.0% at three years and a high complication rate, leading to the development of different surgeries, micro-invasive glaucoma surgeries (MIGS). MIGS devices are diverse and have various indications, risks, and effectiveness. We intended to review MIGS’ surgical techniques, indications, contra-indications, and IOP effect. Methods: We performed a literature review of MIGS to differentiate the devices and their reported effectiveness compared to traditional surgery (tubes and blebs). We also conducted a video review of the last 1000 glaucoma surgeries of the author (including MIGS, but also trabeculectomy, deep sclerectomy, and tubes of Ahmed and Baerveldt) performed at glaucoma and advanced anterior segment fellowship in Canada and France, to describe preferred surgical techniques for each. Results: We present the videos with surgical techniques and pearls for each surgery. Glaucoma surgeries included: 1- bleb surgery (namely trabeculectomy, with releasable sutures or with slip knots, deep sclerectomy, Ahmed valve, Baerveldt tube), 2- MIGS with bleb, also known as MIBS (including XEN 45, XEN 63, and Preserflo), 3- MIGS increasing supra-choroidal flow (iStar), 4-MIGS increasing trabecular flow (iStent, gonioscopy-assisted transluminal trabeculotomy - GATT, goniotomy, excimer laser trabeculostomy -ELT), and 5-MIGS decreasing aqueous humor production (endocyclophotocoagulation, ECP). There was also needling (ab interno and ab externo) performed at the operating room and irido-zonulo-hyaloïdectomy (IZHV). Each technique had different indications and contra-indications. Conclusion: MIGS are valuable in glaucoma surgery, such as traditional surgery with trabeculectomy and tubes. All glaucoma surgery can be combined with phacoemulsification (there may be a synergistic effect on MIGS + cataract surgery). In addition, some MIGS may be combined for further intraocular pressure lowering effect (for example, iStents with goniotomy and ECP). A good surgical technique and postoperative management are fundamental to increasing success and good practice in all glaucoma surgery.Keywords: glaucoma, migs, surgery, video, review
Procedia PDF Downloads 741317 Existential Feeling in Contemporary Chinese Novels: The Case of Yan Lianke
Authors: Thuy Hanh Nguyen Thi
Abstract:
Since 1940, existentialism has penetrated into China and continued to profoundly influence contemporary Chinese literature. By the method of deep reading and text analysis, this article analyzes the existential feeling in Yan Lianke’s novels through various aspects: the Sisyphus senses, the narrative rationalization and the viewpoint of the dead. In addition to pointing out the characteristics of the existential sensation in the writer’s novels, the analysis of the article also provides an insight into the nature and depth of contemporary Chinese society.Keywords: Yan Lianke, existentialism, the existential feeling, contemporary Chinese literature
Procedia PDF Downloads 1351316 Deep Q-Network for Navigation in Gazebo Simulator
Authors: Xabier Olaz Moratinos
Abstract:
Drone navigation is critical, particularly during the initial phases, such as the initial ascension, where pilots may fail due to strong external interferences that could potentially lead to a crash. In this ongoing work, a drone has been successfully trained to perform an ascent of up to 6 meters at speeds with external disturbances pushing it up to 24 mph, with the DQN algorithm managing external forces affecting the system. It has been demonstrated that the system can control its height, position, and stability in all three axes (roll, pitch, and yaw) throughout the process. The learning process is carried out in the Gazebo simulator, which emulates interferences, while ROS is used to communicate with the agent.Keywords: machine learning, DQN, Gazebo, navigation
Procedia PDF Downloads 671315 Astronomical Object Classification
Authors: Alina Muradyan, Lina Babayan, Arsen Nanyan, Gohar Galstyan, Vigen Khachatryan
Abstract:
We present a photometric method for identifying stars, galaxies and quasars in multi-color surveys, which uses a library of ∼> 65000 color templates for comparison with observed objects. The method aims for extracting the information content of object colors in a statistically correct way, and performs a classification as well as a redshift estimation for galaxies and quasars in a unified approach based on the same probability density functions. For the redshift estimation, we employ an advanced version of the Minimum Error Variance estimator which determines the redshift error from the redshift dependent probability density function itself. The method was originally developed for the Calar Alto Deep Imaging Survey (CADIS), but is now used in a wide variety of survey projects. We checked its performance by spectroscopy of CADIS objects, where the method provides high reliability (6 errors among 151 objects with R < 24), especially for the quasar selection, and redshifts accurate within σz ≈ 0.03 for galaxies and σz ≈ 0.1 for quasars. For an optimization of future survey efforts, a few model surveys are compared, which are designed to use the same total amount of telescope time but different sets of broad-band and medium-band filters. Their performance is investigated by Monte-Carlo simulations as well as by analytic evaluation in terms of classification and redshift estimation. If photon noise were the only error source, broad-band surveys and medium-band surveys should perform equally well, as long as they provide the same spectral coverage. In practice, medium-band surveys show superior performance due to their higher tolerance for calibration errors and cosmic variance. Finally, we discuss the relevance of color calibration and derive important conclusions for the issues of library design and choice of filters. The calibration accuracy poses strong constraints on an accurate classification, which are most critical for surveys with few, broad and deeply exposed filters, but less severe for surveys with many, narrow and less deep filters.Keywords: VO, ArVO, DFBS, FITS, image processing, data analysis
Procedia PDF Downloads 631314 Efficacy of Deep Learning for Below-Canopy Reconstruction of Satellite and Aerial Sensing Point Clouds through Fractal Tree Symmetry
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 931313 Dynamic Reliability for a Complex System and Process: Application on Offshore Platform in Mozambique
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 1151312 Enhanced Multi-Scale Feature Extraction Using a DCNN by Proposing Dynamic Soft Margin SoftMax for Face Emotion Detection
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 641311 The Introduction of the Revolution Einstein’s Relative Energy Equations in Even 2n and Odd 3n Light Dimension Energy States Systems
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 3321310 Multimedia Design in Tactical Play Learning and Acquisition for Elite Gaelic Football Practitioners
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 911309 BERT-Based Chinese Coreference Resolution
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 2001308 Fatigue Analysis of Spread Mooring Line
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 3241307 ANAC-id - Facial Recognition to Detect Fraud
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 1461306 Semi-Supervised Learning for Spanish Speech Recognition Using Deep Neural Networks
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 3311305 Automatic Checkpoint System Using Face and Card Information
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 3141304 Convolutional Neural Networks Architecture Analysis for Image Captioning
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 1231303 Social Structure, Involuntary Relations and Urban Poverty
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 6691302 Experimental and FEA Study for Reduction of Damage in Sheet Metal Forming
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 4821301 Federated Learning in Healthcare
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 1291300 A Study of Various Ontology Learning Systems from Text and a Look into Future
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 5041299 Earth Flat Roofs
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 4491298 Social Media and the Future of Veganism Influence on Gender Norms
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 1041297 Insight2OSC: Using Electroencephalography (EEG) Rhythms from the Emotiv Insight for Musical Composition via Open Sound Control (OSC)
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 3111296 Detection and Classification Strabismus Using Convolutional Neural Network and Spatial Image Processing
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 77