Search results for: neural tube defects
2565 Taxonomic Classification for Living Organisms Using Convolutional Neural Networks
Authors: Saed Khawaldeh, Mohamed Elsharnouby, Alaa Eddin Alchalabi, Usama Pervaiz, Tajwar Aleef, Vu Hoang Minh
Abstract:
Taxonomic classification has a wide-range of applications such as finding out more about the evolutionary history of organisms that can be done by making a comparison between species living now and species that lived in the past. This comparison can be made using different kinds of extracted species’ data which include DNA sequences. Compared to the estimated number of the organisms that nature harbours, humanity does not have a thorough comprehension of which specific species they all belong to, in spite of the significant development of science and scientific knowledge over many years. One of the methods that can be applied to extract information out of the study of organisms in this regard is to use the DNA sequence of a living organism as a marker, thus making it available to classify it into a taxonomy. The classification of living organisms can be done in many machine learning techniques including Neural Networks (NNs). In this study, DNA sequences classification is performed using Convolutional Neural Networks (CNNs) which is a special type of NNs.Keywords: deep networks, convolutional neural networks, taxonomic classification, DNA sequences classification
Procedia PDF Downloads 4282564 Radiation Hardness Materials Article Review
Authors: S. Abou El-Azm, U. Kruchonak, M. Gostkin, A. Guskov, A. Zhemchugov
Abstract:
Semiconductor detectors are widely used in nuclear physics and high-energy physics experiments. The application of semiconductor detectors could be limited by their ultimate radiation resistance. The increase of radiation defects concentration leads to significant degradation of the working parameters of semiconductor detectors. The investigation of radiation defects properties in order to enhance the radiation hardness of semiconductor detectors is an important task for the successful implementation of a number of nuclear physics experiments; we presented some information about radiation hardness materials like diamond, sapphire and CdTe. Also, the results of measurements I-V characteristics, charge collection efficiency and its dependence on the bias voltage for different doses of high resistivity (GaAs: Cr) and Si at LINAC-200 accelerator and reactor IBR-2 are presented.Keywords: semiconductor detectors, radiation hardness, GaAs, Si, CCE, I-V, C-V
Procedia PDF Downloads 992563 Age Related Changes in the Neural Substrates of Emotion Regulation: Mechanisms, Consequences, and Interventions
Authors: Yasaman Mohammadi
Abstract:
Emotion regulation is a complex process that allows individuals to manage and modulate their emotional responses in order to adaptively respond to environmental demands. As individuals age, emotion regulation abilities may decline, leading to an increased vulnerability to mood disorders and other negative health outcomes. Advances in neuroimaging techniques have greatly enhanced our understanding of the neural substrates underlying emotion regulation and age-related changes in these neural systems. Additionally, genetic research has identified several candidate genes that may influence age-related changes in emotion regulation. In this paper, we review recent findings from neuroimaging and genetic research on age-related changes in the neural substrates of emotion regulation, highlighting the mechanisms and consequences of these changes. We also discuss potential interventions, including cognitive and behavioral approaches, that may be effective in mitigating age-related declines in emotion regulation. We propose that a better understanding of the mechanisms underlying age-related changes in emotion regulation may lead to the development of more targeted interventions aimed at promoting healthy emotional functioning in older adults. Overall, this paper highlights the importance of studying age-related changes in emotion regulation and provides a roadmap for future research in this field.Keywords: emotion regulation, aging, neural substrates, neuroimaging, emotional functioning, healthy aging
Procedia PDF Downloads 1042562 Intelligent Prediction System for Diagnosis of Heart Attack
Authors: Oluwaponmile David Alao
Abstract:
Due to an increase in the death rate as a result of heart attack. There is need to develop a system that can be useful in the diagnosis of the disease at the medical centre. This system will help in preventing misdiagnosis that may occur from the medical practitioner or the physicians. In this research work, heart disease dataset obtained from UCI repository has been used to develop an intelligent prediction diagnosis system. The system is modeled on a feedforwad neural network and trained with back propagation neural network. A recognition rate of 86% is obtained from the testing of the network.Keywords: heart disease, artificial neural network, diagnosis, prediction system
Procedia PDF Downloads 4422561 Clustering-Based Threshold Model for Condition Rating of Concrete Bridge Decks
Authors: M. Alsharqawi, T. Zayed, S. Abu Dabous
Abstract:
To ensure safety and serviceability of bridge infrastructure, accurate condition assessment and rating methods are needed to provide basis for bridge Maintenance, Repair and Replacement (MRR) decisions. In North America, the common practices to assess condition of bridges are through visual inspection. These practices are limited to detect surface defects and external flaws. Further, the thresholds that define the severity of bridge deterioration are selected arbitrarily. The current research discusses the main deteriorations and defects identified during visual inspection and Non-Destructive Evaluation (NDE). NDE techniques are becoming popular in augmenting the visual examination during inspection to detect subsurface defects. Quality inspection data and accurate condition assessment and rating are the basis for determining appropriate MRR decisions. Thus, in this paper, a novel method for bridge condition assessment using the Quality Function Deployment (QFD) theory is utilized. The QFD model is designed to provide an integrated condition by evaluating both the surface and subsurface defects for concrete bridges. Moreover, an integrated condition rating index with four thresholds is developed based on the QFD condition assessment model and using K-means clustering technique. Twenty case studies are analyzed by applying the QFD model and implementing the developed rating index. The results from the analyzed case studies show that the proposed threshold model produces robust MRR recommendations consistent with decisions and recommendations made by bridge managers on these projects. The proposed method is expected to advance the state of the art of bridges condition assessment and rating.Keywords: concrete bridge decks, condition assessment and rating, quality function deployment, k-means clustering technique
Procedia PDF Downloads 2172560 Effect of Pristine Graphene on Developmental Toxicity in Zebrafish (Danio rerio) Embryos: Cardiovascular Defects, Apoptosis, and Globin Expression Analysis
Authors: Manjunatha Bangeppagari, Lee Sang Joon
Abstract:
Recently, graphene-related nanomaterials are receiving fast-increasing attention with augmented applications in various fields. Especially, graphene-related materials have been widely applied to the biomedical field in the past years. In the present study, we evaluated the adverse effects of pristine graphene (pG) in zebrafish (Danio rerio) embryos in various aspects, such as mortality rate, heart rate, hatching rate, cardiotoxicity, cardiovascular defect, cardiac looping, apoptosis, and globin expression. For various trace concentrations of pG (1, 5, 10, 15, 20, 25, 30, 35, 40, 45, and 50 μg/L), early life-stage parameters were observed at 24, 48, 72, and 96 hpf. As a result, pG induces significant developmental defects including yolk sac edema, pericardial edema, embryonic mortality, delayed hatching, heartbeat, several morphological defects, pericardial toxicity, and bradycardia. Moreover, the exposure to pG was found to be a potential risk factor to the cardiovascular system of zebrafish embryos. However, further study on their properties which vary according to production methods and surface functionalization is essentially required. In addition, the possible risks of pG flakes to aquatic animals, and public health should be evaluated before releasing them to the surrounding environment.Keywords: apoptosis, cardiovascular toxicity, globin expression, pristine graphene, zebrafish embryos
Procedia PDF Downloads 1282559 Isolation and Antifungal Susceptibility Pattern of Candida albicans from Endocervical and High Vaginal Swabs of Pregnant Women Attending State Specialist Hospital Gombe, Nigeria
Authors: Isa Shu’aibu, A. A. Mu’inat, F. U. Maigari, M. A. Mani
Abstract:
Candida albicans is the common cause of both oral and vaginal candidiasis in humans. This candidiasis leads to a wide range of physical, psychological and even physiological problems in humans particularly pregnant women. Samples of endocervical and high vaginal swab were collected from 200 women attending Gombe Specialist Hospital and inoculated on Saboraud Dextrose Agar (SDA) incorporated with chloramphenicol to get rid of the unwanted bacterial contaminants. Gram staining technique and germ tube test were employed for the identification, as Candida albicans is positive for both. Gram positive samples were 70% (n=140) and were further subjected to germ tube test. The remaining 30% (n=60) were found to be Gram negative. 90% (n=126) of the Gram positive ones isolated were also found to be positive for germ tube test; confirming the presence of Candida albicans. Antifungal susceptibility testing revealed that members of Imidazole (Ketoconazole, Miconazole) and those of Triazoles (Fluconazole and Itraconazole) were found to be more effective at concentrations of 20, 50 and 100 µg/disc compared to Griseofulvin (Fulcin) with only 26.00 mm zone of inhibition at 100 µg/disc concentration.Keywords: Candida albicans, candidiasis, endocervical, vaginal swab, antifungal susceptibility, imidazole, triazoles
Procedia PDF Downloads 3282558 Automatic Measurement of Garment Sizes Using Deep Learning
Authors: Maulik Parmar, Sumeet Sandhu
Abstract:
The online fashion industry experiences high product return rates. Many returns are because of size/fit mismatches -the size scale on labels can vary across brands, the size parameters may not capture all fit measurements, or the product may have manufacturing defects. Warehouse quality check of garment sizes can be semi-automated to improve speed and accuracy. This paper presents an approach for automatically measuring garment sizes from a single image of the garment -using Deep Learning to learn garment keypoints. The paper focuses on the waist size measurement of jeans and can be easily extended to other garment types and measurements. Experimental results show that this approach can greatly improve the speed and accuracy of today’s manual measurement process.Keywords: convolutional neural networks, deep learning, distortion, garment measurements, image warping, keypoints
Procedia PDF Downloads 2912557 Simulation of Improving the Efficiency of a Fire-Tube Steam Boiler
Authors: Roudane Mohamed
Abstract:
In this study we are interested in improving the efficiency of a steam boiler to 4.5T/h and minimize fume discharge temperature by the addition of a heat exchanger against the current in the energy system, the output of the boiler. The mathematical approach to the problem is based on the use of heat transfer by convection and conduction equations. These equations have been chosen because of their extensive use in a wide range of application. A software and developed for solving the equations governing these phenomena and the estimation of the thermal characteristics of boiler through the study of the thermal characteristics of the heat exchanger by both LMTD and NUT methods. Subsequently, an analysis of the thermal performance of the steam boiler by studying the influence of different operating parameters on heat flux densities, temperatures, exchanged power and performance was carried out. The study showed that the behavior of the boiler is largely influenced. In the first regime (P = 3.5 bar), the boiler efficiency has improved significantly from 93.03 to 99.43 at the rate of 6.47% and 4.5%. For maximum speed, the change is less important, it is of the order of 1.06%. The results obtained in this study of great interest to industrial utilities equipped with smoke tube boilers for the preheating air temperature intervene to calculate the actual temperature of the gas so the heat exchanged will be increased and minimize temperature smoke discharge. On the other hand, this work could be used as a model of computation in the design process.Keywords: numerical simulation, efficiency, fire tube, heat exchanger, convection and conduction
Procedia PDF Downloads 2142556 Optimization of Surface Roughness in Additive Manufacturing Processes via Taguchi Methodology
Authors: Anjian Chen, Joseph C. Chen
Abstract:
This paper studies a case where the targeted surface roughness of fused deposition modeling (FDM) additive manufacturing process is improved. The process is designing to reduce or eliminate the defects and improve the process capability index Cp and Cpk for an FDM additive manufacturing process. The baseline Cp is 0.274 and Cpk is 0.654. This research utilizes the Taguchi methodology, to eliminate defects and improve the process. The Taguchi method is used to optimize the additive manufacturing process and printing parameters that affect the targeted surface roughness of FDM additive manufacturing. The Taguchi L9 orthogonal array is used to organize the parameters' (four controllable parameters and one non-controllable parameter) effectiveness on the FDM additive manufacturing process. The four controllable parameters are nozzle temperature [°C], layer thickness [mm], nozzle speed [mm/s], and extruder speed [%]. The non-controllable parameter is the environmental temperature [°C]. After the optimization of the parameters, a confirmation print was printed to prove that the results can reduce the amount of defects and improve the process capability index Cp from 0.274 to 1.605 and the Cpk from 0.654 to 1.233 for the FDM additive manufacturing process. The final results confirmed that the Taguchi methodology is sufficient to improve the surface roughness of FDM additive manufacturing process.Keywords: additive manufacturing, fused deposition modeling, surface roughness, six-sigma, Taguchi method, 3D printing
Procedia PDF Downloads 3772555 Hot Corrosion Susceptibility of Uncoated Boiler Tubes during High Vanadium Containing Fuel Oil Operation in Boiler Applications
Authors: Nicole Laws, William L. Roberts, Saumitra Saxena, Krishnamurthy Anand, Sreenivasa Gubba, Ziad Dawood, Aiping Chen
Abstract:
Boiler-fired power plants that operate steam turbines in Saudi Arabia use vanadium-containing fuel oil. In a super- or sub-critical steam cycle, the skin temperature of boiler tube metal can reach close to 600-1000°C depending on the location of the tubes. At high temperatures, corrosion by the sodium-vanadium-oxygen-sulfur eutectic can become a significant risk. The experimental work utilized a state-of-the-art high-temperature, high-pressure burner rig at KAUST, King Abdullah University of Science and Technology. To establish corrosion rates of different boiler tubes and materials, SA 213 T12, SA 213 T22, SA 213 T91, and Inconel 600, were used under various corrosive media, including vanadium to sulfur levels and vanadium to sodium ratios. The results obtained from the experiments establish a corrosion rate map for the materials involved and layout an empirical framework to rank the life of boiler tube materials under different operating conditions. Safe windows of operation are proposed for burning liquid fuels under varying vanadium, sodium, and sulfur levels before corrosion rates become a matter of significance under high-temperature conditionsKeywords: boiler tube life, hot corrosion, steam boilers, vanadium in fuel oil
Procedia PDF Downloads 2212554 A Case Study of Deep Learning for Disease Detection in Crops
Authors: Felipe A. Guth, Shane Ward, Kevin McDonnell
Abstract:
In the precision agriculture area, one of the main tasks is the automated detection of diseases in crops. Machine Learning algorithms have been studied in recent decades for such tasks in view of their potential for improving economic outcomes that automated disease detection may attain over crop fields. The latest generation of deep learning convolution neural networks has presented significant results in the area of image classification. In this way, this work has tested the implementation of an architecture of deep learning convolution neural network for the detection of diseases in different types of crops. A data augmentation strategy was used to meet the requirements of the algorithm implemented with a deep learning framework. Two test scenarios were deployed. The first scenario implemented a neural network under images extracted from a controlled environment while the second one took images both from the field and the controlled environment. The results evaluated the generalisation capacity of the neural networks in relation to the two types of images presented. Results yielded a general classification accuracy of 59% in scenario 1 and 96% in scenario 2.Keywords: convolutional neural networks, deep learning, disease detection, precision agriculture
Procedia PDF Downloads 2472553 Photovoltaic Maximum Power-Point Tracking Using Artificial Neural Network
Authors: Abdelazziz Aouiche, El Moundher Aouiche, Mouhamed Salah Soudani
Abstract:
Renewable energy sources now significantly contribute to the replacement of traditional fossil fuel energy sources. One of the most potent types of renewable energy that has developed quickly in recent years is photovoltaic energy. We all know that solar energy, which is sustainable and non-depleting, is the best knowledge form of energy that we have at our disposal. Due to changing weather conditions, the primary drawback of conventional solar PV cells is their inability to track their maximum power point. In this study, we apply artificial neural networks (ANN) to automatically track and measure the maximum power point (MPP) of solar panels. In MATLAB, the complete system is simulated, and the results are adjusted for the external environment. The results are better performance than traditional MPPT methods and the results demonstrate the advantages of using neural networks in solar PV systems.Keywords: modeling, photovoltaic panel, artificial neural networks, maximum power point tracking
Procedia PDF Downloads 782552 Collaboration between Dietician and Occupational Therapist, Promotes Independent Functional Eating in Tube Weaning Process of Mechanical Ventilated Patients
Authors: Inbal Zuriely, Yonit Weiss, Hilla Zaharoni, Hadas Lewkowicz, Tatiana Vander, Tarif Bader
Abstract:
early active movement, along with adjusting optimal nutrition, prevents aggravation of muscle degeneracy and functional decline. Eating is a basic activity of daily life, which reflects the patient's independence. When eating and feeding are experienced successfully, they lead to a sense of pleasure and satisfaction. However, when they are experienced as a difficulty, they might evoke feelings of helplessness and frustration. This stresses the essential process of gradual weaning off the enteral feeding tube. the work describes the collaboration of a dietitian, determining the nutritional needs of patients undergoing enteral tube weaning as part of the rehabilitation process, with the suited treatment of an occupational therapist. Occupational therapy intervention regarding eating capabilities focuses on improving the required motor and cognitive components, along with environmental adjustments and aids, imparting eating strategies and training to patients and their families. The project was conducted in the long-term, ventilated patients’ department at the Herzfeld Rehabilitation Geriatric Medical Center on patients undergoing enteral tube weaning with the staff’s assistance. Establishing continuous collaboration between the dietician and the occupational therapist, starting from the beginning of the feeding-tube weaning process: 1.The dietician updates the occupational therapist about the start of the process and the approved diet. 2.The occupational therapist performs cognitive, motor, and functional assessments and treatments regarding the patient’s eating capabilities and recommends the required adjustments for independent eating according to the FIM (Functional Independence Measure) scale. 3.The occupational therapist closely follows up on the patient’s degree of independence in eating and provides a repeated update to the dietician. 4.The dietician accordingly guides the ward staff on whether and how to feed the patient or allow independent eating. The project aimed to promote patients toward independent feeding, which leads to a sense of empowerment, enjoyment of the eating experience, and progress of functional ability, along with performing active movements that will motivate mobilization. From the beginning of 2022, 26 patients participated in the project. 79% of all patients who started the weaning process from tube feeding achieved different levels of independence in feeding (independence levels ranged from supervision (FIM-5) to complete independence (FIM-7). The integration of occupational therapy and dietary treatment is based on a patient-centered approach while considering the patient’s personal needs, preferences, and goals. This interdisciplinary partnership is essential for meeting the complex needs of prolonged mechanically ventilated patients and promotes independent functioning and quality of life.Keywords: dietary, mechanical ventilation, occupational therapy, tube feeding weaning
Procedia PDF Downloads 712551 Local Image Features Emerging from Brain Inspired Multi-Layer Neural Network
Authors: Hui Wei, Zheng Dong
Abstract:
Object recognition has long been a challenging task in computer vision. Yet the human brain, with the ability to rapidly and accurately recognize visual stimuli, manages this task effortlessly. In the past decades, advances in neuroscience have revealed some neural mechanisms underlying visual processing. In this paper, we present a novel model inspired by the visual pathway in primate brains. This multi-layer neural network model imitates the hierarchical convergent processing mechanism in the visual pathway. We show that local image features generated by this model exhibit robust discrimination and even better generalization ability compared with some existing image descriptors. We also demonstrate the application of this model in an object recognition task on image data sets. The result provides strong support for the potential of this model.Keywords: biological model, feature extraction, multi-layer neural network, object recognition
Procedia PDF Downloads 5352550 Design and Fabrication of a Parabolic trough Collector and Experimental Investigation of Direct Steam Production in Tehran
Authors: M. Bidi, H. Akhbari, S. Eslami, A. Bakhtiari
Abstract:
Due to the high potential of solar energy utilization in Iran, development of related technologies is of great necessity. Linear parabolic collectors are among the most common and most efficient means to harness the solar energy. The main goal of this paper is design and construction of a parabolic trough collector to produce hot water and steam in Tehran. To provide precise and practical plans, 3D models of the collector under consideration were developed using Solidworks software. This collector was designed in a way that the tilt angle can be adjusted manually. To increase concentraion ratio, a small diameter absorber tube is selected and to enhance solar absorbtion, a shape of U-tube is used. One of the outstanding properties of this collector is its simple design and use of low cost metal and plastic materials in its manufacturing procedure. The collector under consideration was installed in Shahid Beheshti University of Tehran and the values of solar irradiation, ambient temperature, wind speed and collector steam production rate were measured in different days and hours of July. Results revealed that a 1×2 m parabolic trough collector located in Tehran is able to produce steam by the rate of 300ml/s under the condition of atmospheric pressure and without using a vacuum cover over the absorber tube.Keywords: desalination, parabolic trough collector, direct steam production, solar water heater, design and construction
Procedia PDF Downloads 3052549 Predicting Durability of Self Compacting Concrete Using Artificial Neural Network
Authors: R. Boudjelthia
Abstract:
The aim of this study is to determine the influence of mix composition of concrete as the content of water and cement, water–binder ratio, and the replacement of fly ash on the durability of self compacting concrete (SCC) by using artificial neural networks (ANNs). To achieve this, an ANNs model is developed to predict the durability of self compacting concrete which is expressed in terms of chloride ions permeability in accordance with ASTM C1202-97 or AASHTO T277. Database gathered from the literature for the training and testing the model. A sensitivity analysis was also conducted using the trained and tested ANN model to investigate the effect of fly ash on the durability of SCC. The results indicate that the developed model is reliable and accurate. the durability of SCC expressed in terms of total charge passed over a 6-h period can be significantly improved by using at least 25% fly ash as replacement of cement. This study show that artificial neural network have strong potentialas a feasible tool for predicting accurately the durability of SCC containing fly ash.Keywords: artificial neural networks, durability, chloride ions permeability, self compacting concrete
Procedia PDF Downloads 3702548 Combining the Deep Neural Network with the K-Means for Traffic Accident Prediction
Authors: Celso L. Fernando, Toshio Yoshii, Takahiro Tsubota
Abstract:
Understanding the causes of a road accident and predicting their occurrence is key to preventing deaths and serious injuries from road accident events. Traditional statistical methods such as the Poisson and the Logistics regressions have been used to find the association of the traffic environmental factors with the accident occurred; recently, an artificial neural network, ANN, a computational technique that learns from historical data to make a more accurate prediction, has emerged. Although the ability to make accurate predictions, the ANN has difficulty dealing with highly unbalanced attribute patterns distribution in the training dataset; in such circumstances, the ANN treats the minority group as noise. However, in the real world data, the minority group is often the group of interest; e.g., in the road traffic accident data, the events of the accident are the group of interest. This study proposes a combination of the k-means with the ANN to improve the predictive ability of the neural network model by alleviating the effect of the unbalanced distribution of the attribute patterns in the training dataset. The results show that the proposed method improves the ability of the neural network to make a prediction on a highly unbalanced distributed attribute patterns dataset; however, on an even distributed attribute patterns dataset, the proposed method performs almost like a standard neural network.Keywords: accident risks estimation, artificial neural network, deep learning, k-mean, road safety
Procedia PDF Downloads 1552547 Neural Network in Fixed Time for Collision Detection between Two Convex Polyhedra
Authors: M. Khouil, N. Saber, M. Mestari
Abstract:
In this paper, a different architecture of a collision detection neural network (DCNN) is developed. This network, which has been particularly reviewed, has enabled us to solve with a new approach the problem of collision detection between two convex polyhedra in a fixed time (O (1) time). We used two types of neurons, linear and threshold logic, which simplified the actual implementation of all the networks proposed. The study of the collision detection is divided into two sections, the collision between a point and a polyhedron and then the collision between two convex polyhedra. The aim of this research is to determine through the AMAXNET network a mini maximum point in a fixed time, which allows us to detect the presence of a potential collision.Keywords: collision identification, fixed time, convex polyhedra, neural network, AMAXNET
Procedia PDF Downloads 4182546 Numerical Investigation of AL₂O₃ Nanoparticle Effect on a Boiling Forced Swirl Flow Field
Authors: Ataollah Rabiee1, Amir Hossein Kamalinia, Alireza Atf
Abstract:
One of the most important issues in the design of nuclear fusion power plants is the heat removal from the hottest region at the diverter. Various methods could be employed in order to improve the heat transfer efficiency, such as generating turbulent flow and injection of nanoparticles in the host fluid. In the current study, Water/AL₂O₃ nanofluid forced swirl flow boiling has been investigated by using a homogeneous thermophysical model within the Eulerian-Eulerian framework through a twisted tape tube, and the boiling phenomenon was modeled using the Rensselaer Polytechnic Institute (RPI) approach. In addition to comparing the results with the experimental data and their reasonable agreement, it was evidenced that higher flow mixing results in more uniform bulk temperature and lower wall temperature along the twisted tape tube. The presence of AL₂O₃ nanoparticles in the boiling flow field showed that increasing the nanoparticle concentration leads to a reduced vapor volume fraction and wall temperature. The Computational fluid dynamics (CFD) results show that the average heat transfer coefficient in the tube increases both by increasing the nanoparticle concentration and the insertion of twisted tape, which significantly affects the thermal field of the boiling flow.Keywords: nanoparticle, boiling, CFD, two phase flow, alumina, ITER
Procedia PDF Downloads 1202545 Makhraj Recognition Using Convolutional Neural Network
Authors: Zan Azma Nasruddin, Irwan Mazlin, Nor Aziah Daud, Fauziah Redzuan, Fariza Hanis Abdul Razak
Abstract:
This paper focuses on a machine learning that learn the correct pronunciation of Makhraj Huroofs. Usually, people need to find an expert to pronounce the Huroof accurately. In this study, the researchers have developed a system that is able to learn the selected Huroofs which are ha, tsa, zho, and dza using the Convolutional Neural Network. The researchers present the chosen type of the CNN architecture to make the system that is able to learn the data (Huroofs) as quick as possible and produces high accuracy during the prediction. The researchers have experimented the system to measure the accuracy and the cross entropy in the training process.Keywords: convolutional neural network, Makhraj recognition, speech recognition, signal processing, tensorflow
Procedia PDF Downloads 3282544 Deep Learning Based, End-to-End Metaphor Detection in Greek with Recurrent and Convolutional Neural Networks
Authors: Konstantinos Perifanos, Eirini Florou, Dionysis Goutsos
Abstract:
This paper presents and benchmarks a number of end-to-end Deep Learning based models for metaphor detection in Greek. We combine Convolutional Neural Networks and Recurrent Neural Networks with representation learning to bear on the metaphor detection problem for the Greek language. The models presented achieve exceptional accuracy scores, significantly improving the previous state-of-the-art results, which had already achieved accuracy 0.82. Furthermore, no special preprocessing, feature engineering or linguistic knowledge is used in this work. The methods presented achieve accuracy of 0.92 and F-score 0.92 with Convolutional Neural Networks (CNNs) and bidirectional Long Short Term Memory networks (LSTMs). Comparable results of 0.91 accuracy and 0.91 F-score are also achieved with bidirectional Gated Recurrent Units (GRUs) and Convolutional Recurrent Neural Nets (CRNNs). The models are trained and evaluated only on the basis of training tuples, the related sentences and their labels. The outcome is a state-of-the-art collection of metaphor detection models, trained on limited labelled resources, which can be extended to other languages and similar tasks.Keywords: metaphor detection, deep learning, representation learning, embeddings
Procedia PDF Downloads 1442543 Combination of Artificial Neural Network Model and Geographic Information System for Prediction Water Quality
Authors: Sirilak Areerachakul
Abstract:
Water quality has initiated serious management efforts in many countries. Artificial Neural Network (ANN) models are developed as forecasting tools in predicting water quality trend based on historical data. This study endeavors to automatically classify water quality. The water quality classes are evaluated using 6 factor indices. These factors are pH value (pH), Dissolved Oxygen (DO), Biochemical Oxygen Demand (BOD), Nitrate Nitrogen (NO3N), Ammonia Nitrogen (NH3N) and Total Coliform (T-Coliform). The methodology involves applying data mining techniques using multilayer perceptron (MLP) neural network models. The data consisted of 11 sites of Saen Saep canal in Bangkok, Thailand. The data is obtained from the Department of Drainage and Sewerage Bangkok Metropolitan Administration during 2007-2011. The results of multilayer perceptron neural network exhibit a high accuracy multilayer perception rate at 94.23% in classifying the water quality of Saen Saep canal in Bangkok. Subsequently, this encouraging result could be combined with GIS data improves the classification accuracy significantly.Keywords: artificial neural network, geographic information system, water quality, computer science
Procedia PDF Downloads 3342542 Analytical Study of Data Mining Techniques for Software Quality Assurance
Authors: Mariam Bibi, Rubab Mehboob, Mehreen Sirshar
Abstract:
Satisfying the customer requirements is the ultimate goal of producing or developing any product. The quality of the product is decided on the bases of the level of customer satisfaction. There are different techniques which have been reported during the survey which enhance the quality of the product through software defect prediction and by locating the missing software requirements. Some mining techniques were proposed to assess the individual performance indicators in collaborative environment to reduce errors at individual level. The basic intention is to produce a product with zero or few defects thereby producing a best product quality wise. In the analysis of survey the techniques like Genetic algorithm, artificial neural network, classification and clustering techniques and decision tree are studied. After analysis it has been discovered that these techniques contributed much to the improvement and enhancement of the quality of the product.Keywords: data mining, defect prediction, missing requirements, software quality
Procedia PDF Downloads 4602541 Research of Interaction between Layers of Compressed Composite Columns
Authors: Daumantas Zidanavicius
Abstract:
In order to investigate the bond between concrete and steel in the circular steel tube column filled with concrete, the 7 series of specimens were tested with the same geometrical parameters but different concrete properties. Two types of specimens were chosen. For the first type, the expansive additives to the concrete mixture were taken to increase internal forces. And for the second type, mechanical components were used. All 7 series of the short columns were modeled by FEM and tested experimentally. In the work, big attention was taken to the bond-slip models between steel and concrete. Results show that additives to concrete let increase the bond strength up to two times and the mechanical anchorage –up to 6 times compared to control specimens without additives and anchorage.Keywords: concrete filled steel tube, push-out test, bond slip relationship, bond stress distribution
Procedia PDF Downloads 1212540 Characterization of Sintered Fe-Cr-Mn Powder Mixtures Containing Intermetallics
Authors: A. Yonetken, A. Erol, M. Cakmakkaya
Abstract:
Intermetallic materials are among advanced technology materials that have outstanding mechanical and physical properties for high temperature applications. Especially creep resistance, low density and high hardness properties stand out in such intermetallics. The microstructure, mechanical properties of %88Ni-%10Cr and %2Mn powders were investigated using specimens produced by tube furnace sintering at 900-1300°C temperature. A composite consisting of ternary additions, a metallic phase, Fe ,Cr and Mn have been prepared under Ar shroud and then tube furnace sintered. XRD, SEM (Scanning Electron Microscope), were investigated to characterize the properties of the specimens. Experimental results carried out for composition %88Ni-%10Cr and %2Mn at 1300°C suggest that the best properties as 138,80HV and 6,269/cm3 density were obtained at 1300°C.Keywords: composite, high temperature, intermetallic, sintering
Procedia PDF Downloads 4032539 Evaluation of the Improve Vacuum Blood Collection Tube for Laboratory Tests
Authors: Yoon Kyung Song, Seung Won Han, Sang Hyun Hwang, Do Hoon Lee
Abstract:
Laboratory tests is a significant part for the diagnosis, prognosis, treatment of diseases. Blood collection is a simple process, but can be a potential cause of pre-analytical errors. Vacuum blood collection tubes used to collect and store the blood specimens is necessary for accurate test results. The purpose of this study was to validate Improve serum separator tube(SST) (Guanzhou Improve Medical Instruments Co., Ltd, China) for routine clinical chemistry laboratory testing. Blood specimens were collected from 100 volunteers in three different serum vacuum tubes (Greiner SST , Becton Dickinson SST , Improve SST). The specimens were evaluated for 16 routine chemistry tests using TBA-200FR NEO (Toshiba Medical Co. JAPAN). The results were statistically analyzed by paired t-test and Bland-Altman plot. For stability test, the initial results for each tube were compared with results of 72 hours preserved specimens. Their clinical availability was evaluated by biological Variation of Ricos data bank. Paired t-test analysis revealed that AST, ALT, K, Cl showed statistically same results but calcium (CA), phosphorus(PHOS), glucose(GLU), BUN, uric acid(UA), cholesterol(CHOL), total protein(TP), albumin(ALB), total bilirubin(TB), ALP, creatinine(CRE), sodium(NA) were different(P < 0.05) between Improve SST and Greiner SST. Also, CA, PHOS, TP, TB, AST, ALT, NA, K, Cl showed statistically the same results but GLU, BUN, UA, CHOL, ALB, ALP, CRE were different between Improve SST and Becton Dickinson SST. All statistically different cases were clinically acceptable by biological Variation of Ricos data bank. Improve SST tubes showed satisfactory results compared with Greiner SST and Becton Dickinson SST. We concluded that the tubes are acceptable for routine clinical chemistry laboratory testing.Keywords: blood collection, Guanzhou Improve, SST, vacuum tube
Procedia PDF Downloads 2362538 Prediction of Rolling Forces and Real Exit Thickness of Strips in the Cold Rolling by Using Artificial Neural Networks
Authors: M. Heydari Vini
Abstract:
There is a complicated relation between effective input parameters of cold rolling and output rolling force and exit thickness of strips.in many mathematical models, the effect of some rolling parameters have been ignored and the outputs have not a desirable accuracy. In the other hand, there is a special relation among input thickness of strips,the width of the strips,rolling speeds,mandrill tensions and the required exit thickness of strips with rolling force and the real exit thickness of the rolled strip. First of all, in this paper the effective parameters of cold rolling process modeled using an artificial neural network according to the optimum network achieved by using a written program in MATLAB,it has been shown that the prediction of rolling stand parameters with different properties and new dimensions attained from prior rolled strips by an artificial neural network is applicable.Keywords: cold rolling, artificial neural networks, rolling force, real rolled thickness of strips
Procedia PDF Downloads 4972537 Separation of Composites for Recycling: Measurement of Electrostatic Charge of Carbon and Glass Fiber Particles
Authors: J. Thirunavukkarasu, M. Poulet, T. Turner, S. Pickering
Abstract:
Composite waste from manufacturing can consist of different fiber materials, including blends of different fiber. Commercially, the recycling of composite waste is currently limited to carbon fiber waste and recycling glass fiber waste is currently not economically viable due to the low cost of virgin glass fiber and the reduced mechanical properties of the recovered fibers. For this reason, the recycling of hybrid fiber materials, where carbon fiber is combined with a proportion of glass fiber, cannot be processed economically. Therefore, a separation method is required to remove the glass fiber materials during the recycling process. An electrostatic separation method is chosen for this work because of the significant difference between carbon and glass fiber electrical properties. In this study, an experimental rig has been developed to measure the electrostatic charge achievable as the materials are passed through a tube. A range of particle lengths (80-100 µm, 6 mm and 12 mm), surface state conditions (0%SA, 2%SA and 6%SA), and several tube wall materials have been studied. A polytetrafluoroethylene (PTFE) tube and recycled without sizing agent was identified as the most suitable parameters for the electrical separation method. It was also found that shorter fiber lengths helped to encourage particle flow and attain higher charge values. These findings can be used to develop a separation process to enable the cost-effective recycling of hybrid fiber composite waste.Keywords: electrostatic charging, hybrid fiber composites, recycling, short fiber composites
Procedia PDF Downloads 1212536 Effect of Weld Build-up on the Mechanical Performance of Railway Wheels
Authors: Abdullah Kaymakci, Daniel M. Madyira, Hilda Moseme
Abstract:
Repairing railway wheels by weld build-up is one of the technological solutions that have been applied in the past. However, the effects of this process on the material properties are not well established. The effects of the weld build-up on the mechanical properties of the wheel material in comparison to the required mechanical properties for proper service performance were investigated in this study. A turning process was used to remove the worn surface from the railway wheel. During this process 5mm thickness was removed to ensure that, if there was any weld build-up done in the previous years, it was removed. This was followed by welding a round bar on the sides of the wheel to provide build-up guide. There were two welding processes performed, namely submerged arc welding (SAW) and gas metal arc welding (GMAW). Submerged arc welding (SAW) was used to build up weld on one rim while the other rim was just left with metal arc welding of the round bar at the edges. Both processes produced hardness values that were lower than that of the parent material of 195 HV as the GMAW welds had an average of 184 HV and SAW had an average of 194 HV. Whilst a number of defects were noted on the GMAW welds at both macro and micro levels, SAW welds had less defects and they were all micro defects. All the microstructures were ferritic but with differences in grain sizes. Furthermore, in the SAW weld build up, the grains of the weld build-up appeared to be elongated which was a result of the cooling rate. Using GMAW instead of SAW would result in improved wear and fatigue performance.Keywords: submerged arc welding, gas metal arc welding, railway wheel, microstructure, micro hardness
Procedia PDF Downloads 300