Search results for: loss model

Authors: Anthony D. Rhodes, Manan Goel

Abstract:

We provide a high fidelity deep learning algorithm (HyperSeg) for interactive video segmentation tasks using a dense convolutional network with context-aware skip connections and compressed, 'hypercolumn' image features combined with a convolutional tessellation procedure. In order to maintain high output fidelity, our model crucially processes and renders all image features in high resolution, without utilizing downsampling or pooling procedures. We maintain this consistent, high grade fidelity efficiently in our model chiefly through two means: (1) we use a statistically-principled, tensor decomposition procedure to modulate the number of hypercolumn features and (2) we render these features in their native resolution using a convolutional tessellation technique. For improved pixel-level segmentation results, we introduce a boundary loss function; for improved temporal coherence in video data, we include temporal image information in our model. Through experiments, we demonstrate the improved accuracy of our model against baseline models for interactive segmentation tasks using high resolution video data. We also introduce a benchmark video segmentation dataset, the VFX Segmentation Dataset, which contains over 27,046 high resolution video frames, including green screen and various composited scenes with corresponding, hand-crafted, pixel-level segmentations. Our work presents a improves state of the art segmentation fidelity with high resolution data and can be used across a broad range of application domains, including VFX pipelines and medical imaging disciplines.

Keywords: computer vision, object segmentation, interactive segmentation, model compression

Procedia PDF Downloads 93

Authors: Pavle Dakić, Dimitrije Kotur, Zoran Stojanović

Abstract:

This paper presents the results of the study in which the excitation system fault of synchronous generator is simulated. In a case of excitation system fault (loss of field), distance relay is used to prevent further damage. Loss-of-field relay calculates complex impedance using measured voltage and current at the generator terminals. In order to obtain phasors from sampled measured values, discrete Fourier transform is used. All simulations are conducted using Matlab and Simulink software package. The analysis is conducted on the two machine system which supplies equivalent load. While simulating loss of excitation on one generator in different conditions (at idle operation, weakly loaded, and fully loaded), diagrams of active power, reactive power, and measured impedance are analyzed and monitored. Moreover, in the simulations, the effect of generator load on relay tripping time is investigated. In conclusion, the performed tests confirm that the fault in the excitation system can be detected by measuring the impedance.

Keywords: loss-of-excitation, synchronous generator, distance protection, Fourier transformation

Procedia PDF Downloads 299

Authors: Madiha Liaqat, Rehan Ahmed Khan, Shahid Kamal

Abstract:

Multiple imputation with delta adjustment is a versatile and transparent technique for addressing univariate missing data in the presence of various missing mechanisms. This approach allows for the exploration of sensitivity to the missing-at-random (MAR) assumption. In this review, we outline the delta-adjustment procedure and illustrate its application for assessing the sensitivity to deviations from the MAR assumption. By examining diverse missingness scenarios and conducting sensitivity analyses, we gain valuable insights into the implications of missing data on our analyses, enhancing the reliability of our study's conclusions. In our study, we focused on assessing logPSA, a continuous biomarker in incomplete prostate cancer data, to examine the robustness of conclusions against plausible departures from the MAR assumption. We introduced several approaches for conducting sensitivity analyses, illustrating their application within the pattern mixture model (PMM) under the delta adjustment framework. This proposed approach effectively handles missing data, particularly loss to follow-up.

Keywords: loss to follow-up, incomplete response, multiple imputation, sensitivity analysis, prostate cancer

Procedia PDF Downloads 52

Authors: Xinyan Zhang, Zhipeng Tan, Shan Fan

Abstract:

The first layer of defense against data loss is the backup data. This paper implements an agent-based network backup system used the backup, server-storage and server-backup agent these tripartite construction, and we realize the snapshot and hierarchical index in the NSBS. It realizes the control command and data flow separation, balances the system load, thereby improving the efficiency of the system backup and recovery. The test results show the agent-based network backup system can effectively improve the task-based concurrency, reasonably allocate network bandwidth, the system backup performance loss costs smaller and improves data recovery efficiency by 20%.

Keywords: agent, network backup system, three architecture model, NSBS

Procedia PDF Downloads 427

Authors: Atul Dev, Pankaj Jha

Abstract:

Dr. Genichi Taguchi looked at quality in a broader term and gave an excellent definition of quality in terms of loss to society. However the scope of this definition is limited to the losses imparted by a poor quality product to the customer only and are considered during the useful life of the product and further in a certain situation this loss can even be zero. In this paper, it has been proposed that the scope of quality of a product shall be further enhanced by considering the losses imparted by a poor quality product to society at large, due to associated environmental and safety related factors, over the complete life cycle of the product. Moreover, though these losses can be further minimized with the use of techno-safety interventions, the net losses to society however can never be made zero. This paper proposes an entirely new approach towards defining product quality and is based on Taguchi’s definition of quality.

Keywords: existing concept, goal post philosophy, life cycle, proposed concept, quality loss function

Procedia PDF Downloads 272

Authors: Jonathan Gong

Abstract:

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

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

Procedia PDF Downloads 93

Authors: M. J. Kang, Y. N. Jo, H. H. Yoo

Abstract:

Pendulum tests were used to identify a stretch reflex and diagnose spasticity. Some researches tried to make a mathematical model to simulate the motions. Thighs are subject to compressive forces due to gravity during a pendulum test. Therefore, it affects knee trajectories. However, the most studies on the pendulum tests did not consider that conditions. We used Kelvin-Voight model as compression model of skin and muscles. In this study, we investigated viscoelastic behaviors of skin and muscles using gelatin blocks from experiments of the vibration of the compliantly supported beam. Then we calculated a dynamic stiffness and loss factors from the experiment and estimated a damping coefficient of the model. We also did pendulum tests of human lower limbs to validate the stiffness and damping coefficient of a skin model. To simulate the pendulum motion, we derive equations of motion. We used stretch reflex activation model to estimate muscle forces induced by the stretch reflex. To validate the results, we compared the activation with electromyography signals during experiments. The compression behavior of skin and muscles in this study can be applied to analyze sitting posture as wee as developing surgical techniques.

Keywords: Kelvin-Voight model, pendulum test, skin and muscles under compression, stretch reflex

Procedia PDF Downloads 417

Authors: Mubarek Alpkiray, Tan Nguyen, Arild Saasen

Abstract:

Geothermal drilling operations contain numerous challenges that are encountered to increase the well cost and nonproductive time. Fluid loss is one of the most undesirable troublesome that can cause well abandonment in geothermal drilling. Lost circulation can be seen due to natural fractures, high mud weight, and extremely high formation temperatures. This challenge may cause wellbore stability problems and lead to expensive drilling operations. Wellbore stability is the main domain that should be considered to mitigate or prevent fluid loss into the formation. This paper describes the causes of fluid loss in the Pamukoren geothermal field in Turkey. A geomechanics approach integration and assessment is applied to help the understanding of fluid loss problems. In geothermal drillings, geomechanics is primarily based on rock properties, in-situ stress characterization, the temperature of the rock, determination of stresses around the wellbore, and rock failure criteria. Since a high-temperature difference between the wellbore wall and drilling fluid is presented, temperature distribution through the wellbore is estimated and implemented to the wellbore stability approach. This study reviewed geothermal drilling data to analyze temperature estimation along the wellbore, the cause of fluid loss and stored electric capacity of the reservoir. Our observation demonstrates the geomechanical approach's significant role in understanding safe drilling operations on high-temperature wells. Fluid loss is encountered due to thermal stress effects around the borehole. This paper provides a wellbore stability analysis for a geothermal drilling operation to discuss the causes of lost circulation resulting in nonproductive time and cost.

Keywords: geothermal wells, drilling, wellbore stresses, drilling fluid loss, thermal stress

Procedia PDF Downloads 153

Authors: Julie A. LaRose

Abstract:

Native American youth, ages 10-24, have the highest rate of suicide in the United States. The hopelessness experienced by the native American youth is linked to psychosocial reasons more than biological or intrapsychic reasons. Two significant social determinants of health that diminish their hope include historical trauma and cultural loss. Intergenerational grief is caused by historical trauma from hundreds of years of colonization, broken treaties, and forced migration, leading to land, resources, and sovereignty loss. Forced acculturation through boarding schools that native children were required to attend led to the loss of traditions and culture. The result is hopelessness. This paper reviewed peer-reviewed research literature, government reports, non-government organizations reports, and video and written publications by Native Americans. Building hope through healing historical trauma and embracing cultural traditions may reduce suicide rates among Native American youth.

Keywords: culture loss, historical trauma, Native American, suicide, suicide rates

Procedia PDF Downloads 93

Authors: Ajay Agrawal, Pravin Shah, Shailaja Chhetri, Pappu Rijal

Abstract:

Background and Objectives: Postpartum hemorrhage (PPH) is a common and occasionally life-threatening complication of labour. Cesarean section (CS) is associated with more blood loss than vaginal delivery. There is a trend for increasing CS rates in both developed and developing countries. This could increase the risk of morbidity and mortality, especially among anemic women. The objective of this study was to evaluate the effect of preoperative administration of Intravenous Tranexamic Acid (TA) on blood loss during and after elective CS delivery. Materials and Methods: It is a prospective, randomized controlled study. 160 eligible pregnant women of 37 or more POG planned for CS were randomized into two groups either to receive 10ml(1gm) of tranexamic acid intravenously or 10ml of normal saline. Blood loss was measured during and for 24 hours after operation. Results: The mean estimated blood loss was significantly lower in women treated with TA compared with women in the placebo group (392.13 ml ± 10.06 versus 498.69 ml ± 15.87, respectively; p < 0.001). The mean difference in pre-operative and post-operative hemoglobin levels was statistically significant in the tranexamic acid group than in the control group (0.31 ± 0.18 versus 0.79 ± 0.23, respectively; p < 0.001). Conclusion: Pre-operative use of tranexamic acid is associated with reduced blood loss during and after elective cesarean section. In a developing country like ours where PPH is a major threat to the life of the mothers, it seems to be a promising option.

Keywords: blood loss, cesarean section, postpartum hemorrhage, tranexamic acid

Procedia PDF Downloads 244

Authors: Yongjian Du, Jinhua Sun, Kim M. Liew, Huahua Xiao

Abstract:

Optimal allocation of emergency resources before a disaster is of great importance for emergency response. In reality, the pre-protection for a single critical node where accidents may occur is common. In this study, a model is developed to determine location and inventory decisions of multiple emergency resources among a set of candidate stations to minimize the total cost based on the constraints of budgetary and capacity. The total cost includes the economic accident loss which is accorded with probability distribution of time and the warehousing cost of resources which is increasing over time. A ratio is set to measure the degree of a storage station only serving the target node that becomes larger with the decrease of the distance between them. For the application of linear program, it is assumed that the length of travel time to the accident scene of emergency resources has a linear relationship with the economic accident loss. A computational experiment is conducted to illustrate how the proposed model works, and the results indicate its effectiveness and practicability.

Keywords: emergency response, integer linear program, multiple emergency resources, pre-allocation decisions, single potential accident node

Procedia PDF Downloads 125

Authors: Nana Saralidze, Nino Sharashenidze, Zurab Kevanishvili

Abstract:

Hidden hearing loss may occur in humans exposed to prolonged high-level sound. It is the loss of ability to hear high-level background noise while having normal hearing in quiet. We compared the hearing of people who regularly listen 3 hours and more to personal music players and those who do not. Forty participants aged 18-30 years were divided into two groups: regular users of music players and people who had never used them. And the third group – elders aged 50-55 years, had 15 participants. Pure-tone audiometry (125-16000 Hz), auditory brainstem response (ABR) (70dB SPL), and ability to identify speech in noise (4-talker babble with a 65-dB signal-to-noise ratio at 80 dB) were measured in all participants. All participants had normal pure-tone audiometry (all thresholds < 25 dB HL). A significant difference between groups was observed in that regular users of personal audio systems correctly identified 53% of words, whereas the non-users identified 74% and the elder group – 63%. This contributes evidence supporting the presence of a hidden hearing loss in humans and demonstrates that speech-in-noise audiometry is an effective method and can be considered as the GOLD standard for detecting hidden hearing loss.

Keywords: mp3 player, hidden hearing loss, speech audiometry, pure tone audiometry

Procedia PDF Downloads 36

Authors: Sung-Won Seo, Jang-Young Choi

Abstract:

The rare earth magnets used in synchronous generators offer many advantages, including high efficiency, greatly reduced the size, and weight. The permanent magnet linear synchronous generator (PMLSG) allows for direct drive without the need for a mechanical device. Therefore, the PMLSG is well suited to translational applications, such as wave energy converters and free piston energy converters. This manuscript compares the effects of different magnetization patterns on the characteristics of double-sided PMLSGs in slotless stator structures. The Halbach array has a higher flux density in air-gap than the Vertical array, and the advantages of its performance and efficiency are widely known. To verify the advantage of Halbach array, we apply a finite element method (FEM) and analytical method. In general, a FEM and an analytical method are used in the electromagnetic analysis for determining model characteristics, and the FEM is preferable to magnetic field analysis. However, the FEM is often slow and inflexible. On the other hand, the analytical method requires little time and produces accurate analysis of the magnetic field. Therefore, the flux density in air-gap and the Back-EMF can be obtained by FEM. In addition, the results from the analytical method correspond well with the FEM results. The model of the Halbach array reveals less copper loss than the model of the Vertical array, because of the Halbach array’s high output power density. The model of the Vertical array is lower core loss than the model of Halbach array, because of the lower flux density in air-gap. Therefore, the current density in the Vertical model is higher for identical power output. The completed manuscript will include the magnetic field characteristics and structural features of both models, comparing various results, and specific comparative analysis will be presented for the determination of the best model for application in a wave energy converting system.

Keywords: wave energy converter, permanent magnet linear synchronous generator, finite element method, analytical method

Procedia PDF Downloads 264

Authors: Zatil Afifah Omar, Siti Nur Izati Azmi, Kathi Swaran, Navin Kumar

Abstract:

Lost circulation has always been one of the greatest problems faced by drilling companies during drilling operations due to excessive drilling Fluids losses. Loss of circulation leads to Huge cost and non-productive time. The objective of this study is to evaluate the sealing efficiency of a proprietary blend of synthetic rubber as loss circulation material in comparison with a conventional product such as calcium carbonate, graphite, cellulosic, and nutshells. Sand Bed Tester with a different proprietary blend of synthetic rubber compositions has been used to determine the effectiveness of the LCM in preventing drilling fluids losses in a lab scale. Test results show the proprietary blend of synthetic rubber have good bridging properties and sealing Off fractures of various sizes. The finish product is environmentally friendly with lower production lead time and lower production cost compared to current conventional loss circulation materials used in current drilling operations.

Keywords: loss circulation materials, drilling operation, sealing efficiency, LCM

Procedia PDF Downloads 154

Authors: Hassan Eshkiki, Benjamin Mora

Abstract:

The Neighbor Migrating Generator is a simple and efficient approach to finding the closest potential neighbor(s) with a different label for a given instance and so without the need to calibrate any kernel settings at all. This allows determining and explaining the most important features that will influence an AI model. It can be used to either migrate a specific sample to the class decision boundary of the original model within a close neighborhood of that sample or identify global features that can help localising neighbor classes. The proposed technique works by minimizing a loss function that is divided into two components which are independently weighted according to three parameters α, β, and ω, α being self-adjusting. Results show that this approach is superior to past techniques when detecting the smallest changes in the feature space and may also point out issues in models like over-fitting.

Keywords: explainable AI, EX AI, feature importance, counterfactual explanations

Procedia PDF Downloads 115

Authors: Fei Gao, Xinyang Dong, Yisu Ge, Shufang Lu, Libo Weng

Abstract:

Vehicle color recognition plays an important role in traffic accident investigation. However, due to the influence of illumination, weather, and noise, vehicle color recognition still faces challenges. In this paper, a vehicle color classification network based on spatial cluster loss and channel attention mechanism (SCNet) is proposed for vehicle color recognition. A channel attention module is applied to extract the features of vehicle color representative regions and reduce the weight of nonrepresentative color regions in the channel. The proposed loss function, called spatial clustering loss (SC-loss), consists of two channel-specific components, such as a concentration component and a diversity component. The concentration component forces all feature channels belonging to the same class to be concentrated through the channel cluster. The diversity components impose additional constraints on the channels through the mean distance coefficient, making them mutually exclusive in spatial dimensions. In the comparison experiments, the proposed method can achieve state-of-the-art performance on the public datasets, VCD, and VeRi, which are 96.1% and 96.2%, respectively. In addition, the ablation experiment further proves that SC-loss can effectively improve the accuracy of vehicle color recognition.

Keywords: feature extraction, convolutional neural networks, intelligent transportation, vehicle color recognition

Procedia PDF Downloads 139

Authors: Abdullah Eqal Al Mazrooei

Abstract:

In this work, a new nonlinear model will be introduced. The model is in the state-space form. The nonlinearity of this model is in the state equation where the state vector is multiplied by its self. This technique makes our model generalizes many famous models as Lotka-Volterra model and Lorenz model which have many applications in the real life. We will apply our new model to estimate the wind speed by using a new nonlinear estimator which suitable to work with our model.

Keywords: nonlinear systems, state-space model, Kronecker product, nonlinear estimator

Procedia PDF Downloads 652

Authors: Mpaphi Major

Abstract:

Soil erosion is becoming an important aspect of land degradation. Therefore it is of great consideration to note any factor that may escalate the rate of soil erosion in our arable land. There exist 3 main driving forces in soil erosion which are rainfall, wind and land use of which in this project only rainfall and land use will be looked at. With the increase in world population at an alarming rate, the demand for food production is expected to increase which will in turn lead to more land being converted from forests to agricultural use of which very few of it are now fertile. In our country Botswana, the rate of crop production is decreasing due to the wearing away of the fertile top soil and poor arable land management. As a result, some studies on the rate of soil loss and farm management practices should be conducted so that best soil and water conservation practices should be employed and hence reduce the risk of soil loss and increase the rate of crop production and yield. The Soil loss estimation model for Southern Africa (SLEMSA) will be used to estimate the rate of soil loss in some selected arable farms within the Palapye watershed and some field observations will be made to determine the management practices used and their impact on the arable land. Upon observations it have been found that many arable fields have been exposed to soil erosion, of which the affected parts are no longer suitable for any crop production unless the land areas are modified. Improper land practices such as ploughing along the slope and land cultivation practices were observed. As a result farmers need to be educated on best conservation practices that can be used to manage their arable land hence reduced risk of soil erosion and improved crop production.

Keywords: soil and water conservation, soil erosion, SLEMSA, land degradation

Procedia PDF Downloads 364

Authors: Sai Chand, Ashish Dhamaniya, Satish Chandra

Abstract:

Curbside bus stops are provided on urban roads when sufficient land is not available to construct bus bays. The present study demonstrates the effect of curbside bus stops on midblock capacity of an urban arterial road. Data were collected on seven sections of 6-lane urban arterial roads in New Delhi. Three sections were selected without any side friction to estimate the base value of capacity. Remaining four sections were with curbside bus stop. Speed and volume data were collected in field and these data were used to estimate the capacity of a section. The average base midblock capacity of a 6–lane divided urban road was found to be 6314 PCU/hr which was further referred as base capacity. Effect of curbside bus stop on midblock capacity of urban road was evaluated by comparing the capacity of a section with curbside bus stop with that of the base capacity. Finally, a mathematical relation has been developed between bus frequency and capacity loss. Also a relation has been suggested between dwell time and capacity loss. The developed relations would be very useful for practising engineers to estimate capacity loss due to bus stop.

Keywords: bus frequency, bus stops, capacity loss, urban arterial

Procedia PDF Downloads 319

Authors: K. D. R. Jagath-Kumara, D. D. Dias

Abstract:

The sea waves carry thousands of GWs of power globally. Although there are a number of different approaches to harness offshore energy, they are likely to be expensive, practically challenging and vulnerable to storms. Therefore, this paper considers using the near shore waves for generating mechanical and electrical power. It introduces two new approaches, the wave manipulation and using a variable duct turbine, for intercepting very wide wave fronts and coping with the fluctuations of the wave height and the sea level, respectively. The first approach effectively allows capturing much more energy yet with a much narrower turbine rotor. The second approach allows using a rotor with a smaller radius but captures energy of higher wave fronts at higher sea levels yet preventing it from totally submerging. To illustrate the effectiveness of the approach, the paper contains a description and the simulation results of a scale model of a wave manipulator. Then, it includes the results of testing a physical model of the manipulator and a single duct, axial flow turbine, in a wave flume in the laboratory. The paper also includes comparisons of theoretical predictions, simulation results and wave flume tests with respect to the incident energy, loss in wave manipulation, minimal loss, brake torque and the angular velocity.

Keywords: near-shore sea waves, renewable energy, wave energy conversion, wave manipulation

Procedia PDF Downloads 447

Authors: Juan Huang, Hugo Ninanya

Abstract:

Oil has been used as a source of energy and supply to make materials, such as asphalt or rubber for many years. This is the reason why new technologies have been implemented through time. However, research still needs to continue increasing due to new challenges engineers face every day, just like unconventional reservoirs. Various numerical methodologies have been applied in petroleum engineering as tools in order to optimize the production of reservoirs before drilling a wellbore, although not all of these have the same efficiency when talking about studying fracture propagation. Analytical methods like those based on linear elastic fractures mechanics fail to give a reasonable prediction when simulating fracture propagation in ductile materials whereas numerical methods based on the cohesive zone method (CZM) allow to represent the elastoplastic behavior in a reservoir based on a constitutive model; therefore, predictions in terms of displacements and pressure will be more reliable. In this work, a hydro-geomechanical coupled model of horizontal wells in fractured rock was developed using ABAQUS; both extended element method and cohesive elements were used to represent predefined fractures in a model (2-D). A power law for representing the rheological behavior of fluid (shear-thinning, power index <1) through fractures and leak-off rate permeating to the matrix was considered. Results have been showed in terms of aperture and length of the fracture, pressure within fracture and fluid loss. It was showed a high infiltration rate to the matrix as power index decreases. A sensitivity analysis is conclusively performed to identify the most influential factor of fluid loss.

Keywords: fracture, hydro-geomechanical model, non-Newtonian fluid, numerical analysis, sensitivity analysis

Procedia PDF Downloads 177

Authors: Hany Elsaid Fawaz Abdallah

Abstract:

This study presents a new artificial neural network(ANN) model to predict the Nusselt Number and pressure drop for the turbulent flow in a triangular corrugated plate heat exchanger for forced air and turbulent water flow. An experimental investigation was performed to create a new dataset for the Nusselt Number and pressure drop values in the following range of dimensionless parameters: The plate corrugation angles (from 0° to 60°), the Reynolds number (from 10000 to 40000), pitch to height ratio (from 1 to 4), and Prandtl number (from 0.7 to 200). Based on the ANN performance graph, the three-layer structure with {12-8-6} hidden neurons has been chosen. The training procedure includes back-propagation with the biases and weight adjustment, the evaluation of the loss function for the training and validation dataset and feed-forward propagation of the input parameters. The linear function was used at the output layer as the activation function, while for the hidden layers, the rectified linear unit activation function was utilized. In order to accelerate the ANN training, the loss function minimization may be achieved by the adaptive moment estimation algorithm (ADAM). The ‘‘MinMax’’ normalization approach was utilized to avoid the increase in the training time due to drastic differences in the loss function gradients with respect to the values of weights. Since the test dataset is not being used for the ANN training, a cross-validation technique is applied to the ANN network using the new data. Such procedure was repeated until loss function convergence was achieved or for 4000 epochs with a batch size of 200 points. The program code was written in Python 3.0 using open-source ANN libraries such as Scikit learn, TensorFlow and Keras libraries. The mean average percent error values of 9.4% for the Nusselt number and 8.2% for pressure drop for the ANN model have been achieved. Therefore, higher accuracy compared to the generalized correlations was achieved. The performance validation of the obtained model was based on a comparison of predicted data with the experimental results yielding excellent accuracy.

Keywords: artificial neural networks, corrugated channel, heat transfer enhancement, Nusselt number, pressure drop, generalized correlations

Procedia PDF Downloads 51

Authors: Alka Yadav, Mayank Jain, Rajan Saxena, Niraj Kumari, Narendra Krishnani, Ashok Kumar

Abstract:

Purpose: To study the mismatch repair (MMR) protein expression and its clinicopathological correlation in colorectal cancer patients in North India. Methods: A prospective study was conducted on histologically proven 52 (38 males and 14 females) patients with adenocarcinoma of colorectum. MMR protein loss was determined by using immunohistochemistry for MLH1, MSH2, PMS2 and MSH6. Results: 52 patients (38 males and 14 females) underwent resection for colorectal cancer with the median age of 52 years (16-81 years). 35% of the patients (n=18) were younger than 50 years of the age. 3 patients had associated history of malignancy in the family. 29 (56%) patients had right colon cancer, 9 (17%) left colon cancer and 14 (27%) rectal cancer. 2 patients each had synchronous and metachronous cancer. Histology revealed well-differentiated tumour in 16, moderately differentiated in 10 and poorly differentiated tumour in 26 patients. MMR protein loss was seen in 15 (29%) patients. Seven (46%) of these patients were less than 50 years of age. Combined loss of MSH2 and MSH6 was seen most commonly and it was found in 6 patients. 12 (80%) patients with MMR protein loss had tumour located proximal to the splenic flexure compared to 3 (20%) located distal to the splenic flexure. There was no difference in MMR protein loss based on patients' age, gender, degree of tumour differentiation, stage of the disease and tumour histological characteristics. Conclusions: This study revealed that there was less than 30% MMR protein loss in colorectal cancer patients. The loss was most commonly seen in right sided colon cancer than left. A larger study is further required to validate these findings.

Keywords: colorectal cancer, mismatch repair protein, immunohitochemistry, clinicopathological correlation

Procedia PDF Downloads 194

Authors: S. Olyaee, M. Seifouri, A. Nikoosohbat, M. Shams Esfand Abadi

Abstract:

Photonic Crystal Fibers (PCFs) can be used in optical communications as transmission lines. For this reason, the PCFs with low confinement loss, low chromatic dispersion, and low nonlinear effects are highly suitable transmission media. In this paper, we introduce a new design of index-guiding nanostructured photonic crystal fiber (IG-NPCF) with ultra-low chromatic dispersion, low nonlinearity effects, and low confinement loss. Relatively low dispersion is achieved in the wavelength range of 1200 to 1600nm using the proposed design. According to the new structure of nanostructured PCF presented in this study, the chromatic dispersion slope is -30(ps/km.nm) and the confinement loss reaches below 10-7 dB/km. While in the wavelength range mentioned above at the same time an effective area of more than 50.2μm2 is obtained.

Keywords: optical communication systems, nanostructured, index-guiding, dispersion, confinement loss, photonic crystal fiber

Procedia PDF Downloads 533

Authors: Adel Edwar Waheeb Louka

Abstract:

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

Keywords: artificial intelligence, convolutional neural networks, deeplearning, image processing, machine learningSarapin, intraarticular, chronic knee pain, osteoarthritisFNS, trauma, hip, neck femur fracture, minimally invasive surgery

Procedia PDF Downloads 20

Authors: J. R. Wang, H. T. Lin, Y. Chiang, H. C. Chen, C. Shih

Abstract:

Kuosheng Nuclear Power Plant (NPP) is located on the northern coast of Taiwan. Its nuclear steam supply system is a type of BWR/6 designed and built by General Electric on a twin unit concept. First, the methodology of Kuosheng NPP SPU (Stretch Power Uprate) safety analysis TRACE/SNAP model was developed in this research. Then, in order to estimate the safety of Kuosheng NPP under the more severe condition, the SBO (Station Blackout) + LOCA (Loss-of-Coolant Accident) transient analysis of Kuosheng NPP SPU TRACE/SNAP model was performed. Besides, the animation model of Kuosheng NPP was presented using the animation function of SNAP with TRACE/SNAP analysis results.

Keywords: TRACE, safety analysis, BWR/6, severe accident

Procedia PDF Downloads 672

Authors: Yuzhi Cai

Abstract:

In this paper, we discuss a Bayesian approach to quantile autoregressive (QAR) time series model estimation and forecasting. Together with a combining forecasts technique, we then predict USD to GBP currency exchange rates. Combined forecasts contain all the information captured by the fitted QAR models at different quantile levels and are therefore better than those obtained from individual models. Our results show that an unequally weighted combining method performs better than other forecasting methodology. We found that a median AR model can perform well in point forecasting when the predictive density functions are symmetric. However, in practice, using the median AR model alone may involve the loss of information about the data captured by other QAR models. We recommend that combined forecasts should be used whenever possible.

Keywords: combining forecasts, MCMC, predictive density functions, quantile forecasting, quantile modelling

Procedia PDF Downloads 228

Authors: Nazari Maryam, Gorji Saman

Abstract:

For most competitions, athletes usually engage in a process called rapid weight loss (RWL) and subsequent rapid weight gain (RWG) in the days preceding the event. Besides the perfection of performance, weight regulation mediates a self-image of being “a real athlete” which is mentally important as a part of the pre-competition preparation. This feeling enhances the focus and commitment of the athlete. There is a large body of evidence that weight loss, particularly in combat sports, results in several health benefits. However, intentional weight loss beyond normal levels might have unknown negative special effects on the immune system. As the results show, a high prevalence (50%) of RWL is happening among combat athletes. It seems that energy deprivation and intense exercise to reach RWL results in altered blood cell distribution through modification of body composition that, in turn, changes B and T-Lymphocyte and/or CD4 T-Helper response. Moreover, it may diminish IgG antibody levels and modulate IgG glycosylation after this course. On the other hand, some studies show suppression of signaling and regulation of IgE antibody and chemokine production are responsible for immunodeficiency following a period of low-energy availability. Some researchers hypothesize that severe glutamine depletion, which occurs during exercise and calorie restriction, is responsible for this immune system weakness. However, supplementation by this amino acid is not prescribed yet. Therefore, weight loss is achieved not only through chronic strategies (body fat losses) but also through acute manipulations prior to competition should be supervised by a sports nutritionist to minimize side effects on the immune system and other body systems.

Keywords: athletes, immune system, rapid weight loss, weight loss strategies

Procedia PDF Downloads 84

Authors: Imen Bouazzi

Abstract:

The IEEE-802.15.4 standard utilizes the CSMA-CA mechanism to control nodes access to the shared wireless communication medium. It is becoming the popular choice for various applications of surveillance and control used in wireless sensor network (WSN). The benefit of this standard is evaluated regarding of the packet loss probability who depends on the configuration of IEEE 802.15.4 MAC parameters and the traffic load. Our exigency is to evaluate the effects of various configurable MAC parameters on the performance of beaconless IEEE 802.15.4 networks under different traffic loads, static values of IEEE 802.15.4 MAC parameters (macMinBE, macMaxCSMABackoffs, and macMaxFrame Retries) will be evaluated. To performance analysis, we use ns-2[2] network simulator.

Keywords: WSN, packet loss, CSMA/CA, IEEE-802.15.4

Procedia PDF Downloads 301

Authors: Enyia James Diwa, Dodeye Ina Igbong, Archibong Archibong Eso

Abstract:

Gas turbine operators have been faced with the dramatic financial setback resulting from compressor fouling. In a highly deregulated power industry where there is stiffness in the market competition, has made it imperative to improvise means of reducing maintenance cost in other to yield maximum profit. Compressor fouling results from the deposition of contaminants in the presence of oil and moisture on the compressor blade or annulus surfaces, which leads to a loss in flow capacity and compressor efficiency. These combined effects reduce power output, increase heat rate and cause creep life reduction. This paper also contains a model of two gas turbine engines via Cranfield University software known as TURBOMATCH, which is simulation software for detecting engine fouling rate. The model engines are of different configurations and capacities, and are operating in two different modes of constant output power and turbine inlet temperature for a two and three stage filter system. The idea is to investigate the more economically viable filtration systems by gas turbine users based on performance only. It has been demonstrated in the results that the two spool engine is a little more beneficial compared to the single spool. This is as a result of a higher pressure ratio of the two spools as well as the deceleration of the high-pressure compressor and high-pressure turbine speed in a constant TET. Meanwhile, the inlet filtration system was properly designed and balanced with a well-timed and economical compressor washing regime/scheme to control compressor fouling. The different technologies of inlet air filtration and compressor washing are considered and an attempt at optimization with respect to the cost of a combination of both control measures are made.

Keywords: inlet filtration, pressure loss, single spool, two spool

Procedia PDF Downloads 285