Search results for: explicit algorithm

Authors: Oscar E. Cariceo, Claudia V. Casal

Abstract:

Machine learning offers a set of techniques to promote social work interventions and can lead to support decisions of practitioners in order to predict new behaviors based on data produced by the organizations, services agencies, users, clients or individuals. Machine learning techniques include a set of generalizable algorithms that are data-driven, which means that rules and solutions are derived by examining data, based on the patterns that are present within any data set. In other words, the goal of machine learning is teaching computers through 'examples', by training data to test specifics hypothesis and predict what would be a certain outcome, based on a current scenario and improve that experience. Machine learning can be classified into two general categories depending on the nature of the problem that this technique needs to tackle. First, supervised learning involves a dataset that is already known in terms of their output. Supervising learning problems are categorized, into regression problems, which involve a prediction from quantitative variables, using a continuous function; and classification problems, which seek predict results from discrete qualitative variables. For social work research, machine learning generates predictions as a key element to improving social interventions on complex social issues by providing better inference from data and establishing more precise estimated effects, for example in services that seek to improve their outcomes. This paper exposes the results of a classification algorithm to predict cyberbullying among adolescents. Data were retrieved from the National Polyvictimization Survey conducted by the government of Chile in 2017. A logistic regression model was created to predict if an adolescent would experience cyberbullying based on the interaction and behavior of gender, age, grade, type of school, and self-esteem sentiments. The model can predict with an accuracy of 59.8% if an adolescent will suffer cyberbullying. These results can help to promote programs to avoid cyberbullying at schools and improve evidence based practice.

Keywords: cyberbullying, evidence based practice, machine learning, social work research

Procedia PDF Downloads 170

Authors: Kathryn Rooney, Kaitlyn Eddy, Evan Landers, Weihui Li

Abstract:

The international mortality rate for neonates and infants has been declining at a disproportionally low rate when compared to the overall decline in child mortality in recent decades. A significant portion of infant deaths could be prevented with the implementation of low-cost and easy to use physiological monitoring devices, by enabling early identification of symptoms before they progress into life-threatening illnesses. The oral diagnostic device discussed in this paper serves to continuously monitor the key vital signs of body temperature, respiratory rate, heart rate, and oxygen saturation. The device mimics an infant pacifier, designed to be easily tolerated by infants as well as orthodontically inert. The fundamental measurements are gathered via thermistors and a pulse oximeter, each encapsulated in medical-grade silicone and wired internally to a microcontroller chip. The chip then translates the raw measurements into physiological values via an internal algorithm, before outputting the data to a liquid crystal display screen and an Android application. Additionally, a biological sample collection chamber is incorporated into the internal portion of the device. The movement within the oral chamber created by sucking on the pacifier-like device pushes saliva through a small check valve in the distal end, where it is accumulated and stored. The collection chamber can be easily removed, making the sample readily available to be tested for various diseases and analytes. With the vital sign monitoring and sample collection offered by this device, abnormal fluctuations in physiological parameters can be identified and appropriate medical care can be sought. This device enables preventative diagnosis for infants who may otherwise have gone undiagnosed, due to the inaccessibility of healthcare that plagues vast numbers of underprivileged populations.

Keywords: neonate mortality, infant mortality, low-cost diagnostics, vital signs, saliva testing, preventative care

Procedia PDF Downloads 154

Authors: Kana Matsuyanagi

Abstract:

Anorexia Nervosa (AN) is a psychiatric disorder characterized by a relentless pursuit of thinness and strict restriction of food. The current therapeutic approaches for AN predominantly revolve around outpatient psychotherapies, which create significant financial barriers for the majority of affected patients, hindering their access to treatment. Nonetheless, AN exhibit one of the highest mortality and relapse rates among psychological disorders, underscoring the urgent need to provide patients with an affordable self-treatment tool, enabling those unable to access conventional medical intervention to address their condition autonomously. To this end, a neurofeedback software, termed RelaxNeuron, was developed with the objective of providing an economical and portable means to aid individuals in self-managing AN. Electroencephalography (EEG) was chosen as the preferred modality for RelaxNeuron, as it aligns with the study's goal of supplying a cost-effective and convenient solution for addressing AN. The primary aim of the software is to ameliorate the negative emotional responses towards food stimuli and the accompanying aberrant eye-tracking patterns observed in AN patient, ultimately alleviating the profound fear towards food an elemental symptom and, conceivably, the fundamental etiology of AN. The core functionality of RelaxNeuron hinges on the acquisition and analysis of EEG signals, alongside an electrocardiogram (ECG) signal, to infer the user's emotional state while viewing dynamic food-related imagery on the screen. Moreover, the software quantifies the user's performance in accurately tracking the moving food image. Subsequently, these two parameters undergo further processing in the subsequent algorithm, informing the delivery of either negative or positive feedback to the user. Preliminary test results have exhibited promising outcomes, suggesting the potential advantages of employing RelaxNeuron in the treatment of AN, as evidenced by its capacity to enhance emotional regulation and attentional processing through repetitive and persistent therapeutic interventions.

Keywords: Anorexia Nervosa, fear conditioning, neurofeedback, BCI

Procedia PDF Downloads 48

Authors: Xiaowei Zhang, Min Xu, Saeid Habibi, Fengjun Yan, Ryan Ahmed

Abstract:

Recently, Electric Vehicles (EVs) have received extensive consideration since they offer a more sustainable and greener transportation alternative compared to fossil-fuel propelled vehicles. Lithium-Ion (Li-ion) batteries are increasingly being deployed in EVs because of their high energy density, high cell-level voltage, and low rate of self-discharge. Since Li-ion batteries represent the most expensive component in the EV powertrain, accurate monitoring and control strategies must be executed to ensure their prolonged lifespan. The Battery Management System (BMS) has to accurately estimate parameters such as the battery State-of-Charge (SOC), State-of-Health (SOH), and Remaining Useful Life (RUL). In order for the BMS to estimate these parameters, an accurate and control-oriented battery model has to work collaboratively with a robust state and parameter estimation strategy. Since battery physical parameters, such as the internal resistance and diffusion coefficient change depending on the battery state-of-life (SOL), the BMS has to be adaptive to accommodate for this change. In this paper, an extensive battery aging study has been conducted over 12-months period on 5.4 Ah, 3.7 V Lithium polymer cells. Instead of using fixed charging/discharging aging cycles at fixed C-rate, a set of real-world driving scenarios have been used to age the cells. The test has been interrupted every 5% capacity degradation by a set of reference performance tests to assess the battery degradation and track model parameters. As battery ages, the combined model parameters are optimized and tracked in an offline mode over the entire batteries lifespan. Based on the optimized model, a state and parameter estimation strategy based on the Extended Kalman Filter (EKF) and the relatively new Smooth Variable Structure Filter (SVSF) have been applied to estimate the SOC at various states of life.

Keywords: lithium-ion batteries, genetic algorithm optimization, battery aging test, parameter identification

Procedia PDF Downloads 270

Authors: A. Kachmazova, A. Shadiev, Y. Teterin, P. Yartcev

Abstract:

Introduction: Biliary calculi disease (LCS) still occupies the leading position among urgent diseases of the abdominal cavity, manifesting itself from asymptomatic course to life-threatening states. Nowadays arsenal of diagnostic methods for choledocholithiasis is quite wide: ultrasound, hepatobiliscintigraphy (HBSG), magnetic resonance imaging (MRI), endoscopic retrograde cholangiography (ERCP). Among them, transabdominal ultrasound (TA ultrasound) is the most accessible and routine diagnostic method. Nowadays ERCG is the "gold" standard in diagnosis and one-stage treatment of biliary tract obstruction. However, transpapillary techniques are accompanied by serious postoperative complications (postmanipulative pancreatitis (3-5%), endoscopic papillosphincterotomy bleeding (2%), cholangitis (1%)), the lethality being 0.4%. GBSG and MRI are also quite informative methods in the diagnosis of choledocholithiasis. Small size of concrements, their localization in intrapancreatic and retroduodenal part of common bile duct significantly reduces informativity of all diagnostic methods described above, that demands additional studying of this problem. Materials and Methods: 890 patients with the diagnosis of cholelithiasis (calculous cholecystitis) were admitted to the Sklifosovsky Scientific Research Institute of Hospital Medicine in the period from August, 2020 to June, 2021. Of them 115 people with mechanical jaundice caused by concrements in bile ducts. Results: Final EUS diagnosis was made in all patients (100,0%). In all patients in whom choledocholithiasis diagnosis was revealed or confirmed after EUS, ERCP was performed urgently (within two days from the moment of its detection) as the X-ray operation room was provided; it confirmed the presence of concrements. All stones were removed by lithoextraction using Dormia basket. The postoperative period in these patients had no complications. Conclusions: EUS is the most informative and safe diagnostic method, which allows to detect choledocholithiasis in patients with discrepancies between clinical-laboratory and instrumental methods of diagnosis in shortest time, that in its turn will help to decide promptly on the further tactics of patient treatment. We consider it reasonable to include EUS in the diagnostic algorithm for choledocholithiasis. Disclosure: Nothing to disclose.

Keywords: endoscopic ultrasonography, choledocholithiasis, common bile duct, concrement, ERCP

Procedia PDF Downloads 88

Authors: Ravi Ande, Mousumi Hazari

Abstract:

One of the common geophysical techniques for mapping subsurface geo-electrical structures, extensive hydro-geological research, and engineering and environmental geophysics applications is the use of time domain electromagnetic (TDEM)/transient electromagnetic (TEM) soundings. A large transmitter loop for energising the ground and a small receiver loop or magnetometer for recording the transient voltage or magnetic field in the air or on the surface of the earth, with the receiver at the center of the loop or at any random point inside or outside the source loop, make up a large loop TEM system. In general, one can acquire data using one of the configurations with a large loop source, namely, with the receiver at the center point of the loop (central loop method), at an arbitrary in-loop point (in-loop method), coincident with the transmitter loop (coincidence-loop method), and at an arbitrary offset loop point (offset-loop method), respectively. Because of the mathematical simplicity associated with the expressions of EM fields, as compared to the in-loop and offset-loop systems, the central loop system (for ground surveys) and coincident loop system (for ground as well as airborne surveys) have been developed and used extensively for the exploration of mineral and geothermal resources, for mapping contaminated groundwater caused by hazardous waste and thickness of permafrost layer. Because a proper analytical expression for the TEM response over the layered earth model for the large loop TEM system does not exist, the forward problem used in this inversion scheme is first formulated in the frequency domain and then it is transformed in the time domain using Fourier cosine or sine transforms. Using the EMLCLLER algorithm, the forward computation is initially carried out in the frequency domain. As a result, the EMLCLLER modified the forward calculation scheme in NLSTCI to compute frequency domain answers before converting them to the time domain using Fourier Cosine and/or Sine transforms.

Keywords: time domain electromagnetic (TDEM), TEM system, geoelectrical sounding structure, Fourier cosine

Procedia PDF Downloads 95

Authors: Neha Devi, P. K. Joshi

Abstract:

Fire fuel map is one of the most critical factors for planning and managing the fire hazard and risk. One of the most significant forms of global disturbance, impacting community dynamics, biogeochemical cycles and local and regional climate across a wide range of ecosystems ranging from boreal forests to tropical rainforest is wildfire Assessment of fire danger is a function of forest type, fuelwood stock volume, moisture content, degree of senescence and fire management strategy adopted in the ground. Remote sensing has potential of reduction the uncertainty in mapping fuels. Hyperspectral remote sensing is emerging to be a very promising technology for wildfire fuels characterization. Fine spectral information also facilitates mapping of biophysical and chemical information that is directly related to the quality of forest fire fuels including above ground live biomass, canopy moisture, etc. We used Hyperion imagery acquired in February, 2016 and analysed four fuel characteristics using Hyperion sensor data on-board EO-1 satellite, acquired over the Shiwalik Himalayas covering the area of Champawat, Uttarakhand state. The main objective of this study was to present an overview of methodologies for mapping fuel properties using hyperspectral remote sensing data. Fuel characteristics analysed include fuel biomass, fuel moisture, and fuel condition and fuel type. Fuel moisture and fuel biomass were assessed through the expression of the liquid water bands. Fuel condition and type was assessed using green vegetation, non-photosynthetic vegetation and soil as Endmember for spectral mixture analysis. Linear Spectral Unmixing, a partial spectral unmixing algorithm, was used to identify the spectral abundance of green vegetation, non-photosynthetic vegetation and soil.

Keywords: forest fire fuel, Hyperion, hyperspectral, linear spectral unmixing, spectral mixture analysis

Procedia PDF Downloads 166

Authors: Nathenal Thomas

Abstract:

In the food chain and in many other agricultural products, corn, also known as maize, which goes by the scientific name Zea mays subsp, is a widely produced agricultural product. Corn has the highest adaptability. It comes in many different types, is employed in many different industrial processes, and is more adaptable to different agro-climatic situations. In Ethiopia, maize is among the most widely grown crop. Small-scale corn farming may be a household's only source of food in developing nations like Ethiopia. The aforementioned data demonstrates that the country's requirement for this crop is excessively high, and conversely, the crop's productivity is very low for a variety of reasons. The most damaging disease that greatly contributes to this imbalance between the crop's supply and demand is the corn disease. The failure to diagnose diseases in maize plant until they are too late is one of the most important factors influencing crop output in Ethiopia. This study will aid in the early detection of such diseases and support farmers during the cultivation process, directly affecting the amount of maize produced. The diseases in maize plants, such as northern leaf blight and cercospora leaf spot, have distinct symptoms that are visible. This study aims to detect the most frequent and degrading maize diseases using the most efficiently used subset of machine learning technology, deep learning so, called Image Processing. Deep learning uses networks that can be trained from unlabeled data without supervision (unsupervised). It is a feature that simulates the exercises the human brain goes through when digesting data. Its applications include speech recognition, language translation, object classification, and decision-making. Convolutional Neural Network (CNN) for Image Processing, also known as convent, is a deep learning class that is widely used for image classification, image detection, face recognition, and other problems. it will also use this algorithm as the state-of-the-art for my research to detect maize diseases by photographing maize leaves using a mobile phone.

Keywords: CNN, zea mays subsp, leaf blight, cercospora leaf spot

Procedia PDF Downloads 75

Authors: Samar Swaid

Abstract:

Today, corporates are moving toward the adoption of Design-Thinking techniques to develop products and services, putting their consumer as the heart of the development process. One of the leading companies in Design-Thinking, IDEO (Innovation, Design, Engineering Organization), defines Design-Thinking as an approach to problem-solving that relies on a set of multi-layered skills, processes, and mindsets that help people generate novel solutions to problems. Design thinking may result in new ideas, narratives, objects or systems. It is about redesigning systems, organizations, infrastructures, processes, and solutions in an innovative fashion based on the users' feedback. Tim Brown, president and CEO of IDEO, sees design thinking as a human-centered approach that draws from the designer's toolkit to integrate people's needs, innovative technologies, and business requirements. The application of design thinking has been witnessed to be the road to developing innovative applications, interactive systems, scientific software, healthcare application, and even to utilizing Design-Thinking to re-think business operations, as in the case of Airbnb. Recently, there has been a movement to apply design thinking to machine learning and artificial intelligence to ensure creating the "wow" effect on consumers. The Association of Computing Machinery task force on Data Science program states that" Data scientists should be able to implement and understand algorithms for data collection and analysis. They should understand the time and space considerations of algorithms. They should follow good design principles developing software, understanding the importance of those principles for testability and maintainability" However, this definition hides the user behind the machine who works on data preparation, algorithm selection and model interpretation. Thus, the Data Science program includes design thinking to ensure meeting the user demands, generating more usable machine learning tools, and developing ways of framing computational thinking. Here, describe the fundamentals of Design-Thinking and teaching modules for data science programs.

Keywords: data science, design thinking, AI, currculum, transformation

Procedia PDF Downloads 84

Authors: Shohreh Ghasemi

Abstract:

Introduction: Managing oral and maxillofacial trauma is a multifaceted challenge, as it can have life-threatening consequences and significant functional and aesthetic impact. Navigation techniques have been introduced to improve surgical precision to meet this challenge. A machine learning algorithm was also developed to support clinical decision-making regarding treating oral and maxillofacial trauma. Given these advances, this systematic meta-analysis aims to assess the efficacy of navigational techniques in treating oral and maxillofacial trauma and explore the impact of machine learning on their management. Methods: A detailed and comprehensive analysis of studies published between January 2010 and September 2021 was conducted through a systematic meta-analysis. This included performing a thorough search of Web of Science, Embase, and PubMed databases to identify studies evaluating the efficacy of navigational techniques and the impact of machine learning in managing oral and maxillofacial trauma. Studies that did not meet established entry criteria were excluded. In addition, the overall quality of studies included was evaluated using Cochrane risk of bias tool and the Newcastle-Ottawa scale. Results: Total of 12 studies, including 869 patients with oral and maxillofacial trauma, met the inclusion criteria. An analysis of studies revealed that navigation techniques effectively improve surgical accuracy and minimize the risk of complications. Additionally, machine learning algorithms have proven effective in predicting treatment outcomes and identifying patients at high risk for complications. Conclusion: The introduction of navigational technology has great potential to improve surgical precision in oral and maxillofacial trauma treatment. Furthermore, developing machine learning algorithms offers opportunities to improve clinical decision-making and patient outcomes. Still, further studies are necessary to corroborate these results and establish the optimal use of these technologies in managing oral and maxillofacial trauma

Keywords: trauma, machine learning, navigation, maxillofacial, management

Procedia PDF Downloads 60

Authors: Benjamin K. Ghansah, Richard K. Appoh, Iliya Nababa, Eric K. Forkuo

Abstract:

The Nasia River is an important source of water for domestic and agricultural purposes to the inhabitants of its catchment. Major farming activities takes place within the floodplain of the river and its network of tributaries. The actual inundation extent of the river system is; however, unknown. Reasons for this lack of information include financial constraints and inadequate human resources as flood modelling is becoming increasingly complex by the day. Knowledge of the inundation extent will help in the assessment of risk posed by the annual flooding of the river, and help in the planning of flood recession agricultural activities. This study used a simple terrain based algorithm, Height Above Nearest Drainage (HAND), to delineate the floodplain of the Nasia River and its tributaries. The HAND model is a drainage normalized digital elevation model, which has its height reference based on the local drainage systems rather than the average mean sea level (AMSL). The underlying principle guiding the development of the HAND model is that hillslope flow paths behave differently when the reference gradient is to the local drainage network as compared to the seaward gradient. The new terrain model of the catchment was created using the NASA’s SRTM Digital Elevation Model (DEM) 30m as the only data input. Contours (HAND Contour) were then generated from the normalized DEM. Based on field flood inundation survey, historical information of flooding of the area as well as satellite images, a HAND Contour of 2m was found to best correlates with the flood inundation extent of the river and its tributaries. A percentage accuracy of 75% was obtained when the surface area created by the 2m contour was compared with surface area of the floodplain computed from a satellite image captured during the peak flooding season in September 2016. It was estimated that the flooding of the Nasia River and its tributaries created a floodplain area of 1011 km².

Keywords: digital elevation model, floodplain, HAND contour, inundation extent, Nasia River

Procedia PDF Downloads 459

Authors: Insaf Ajili, Malik Mallem, Jean-Yves Didier

Abstract:

Human motion recognition has been extensively increased in recent years due to its importance in a wide range of applications, such as human-computer interaction, intelligent surveillance, augmented reality, content-based video compression and retrieval, etc. However, it is still regarded as a challenging task especially in realistic scenarios. It can be seen as a general machine learning problem which requires an effective human motion representation and an efficient learning method. In this work, we introduce a descriptor based on Laban Movement Analysis technique, a formal and universal language for human movement, to capture both quantitative and qualitative aspects of movement. We use Discrete Hidden Markov Model (DHMM) for training and classification motions. We improve the classification algorithm by proposing two DHMMs for each motion class to process the motion sequence in two different directions, forward and backward. Such modification allows avoiding the misclassification that can happen when recognizing similar motions. Two experiments are conducted. In the first one, we evaluate our method on a public dataset, the Microsoft Research Cambridge-12 Kinect gesture data set (MSRC-12) which is a widely used dataset for evaluating action/gesture recognition methods. In the second experiment, we build a dataset composed of 10 gestures(Introduce yourself, waving, Dance, move, turn left, turn right, stop, sit down, increase velocity, decrease velocity) performed by 20 persons. The evaluation of the system includes testing the efficiency of our descriptor vector based on LMA with basic DHMM method and comparing the recognition results of the modified DHMM with the original one. Experiment results demonstrate that our method outperforms most of existing methods that used the MSRC-12 dataset, and a near perfect classification rate in our dataset.

Keywords: human motion recognition, motion representation, Laban Movement Analysis, Discrete Hidden Markov Model

Procedia PDF Downloads 212

Authors: María Dolores Caro, Eugenio M. Fedriani, Ángel F. Tenorio

Abstract:

The transportation of dangerous goods by lorries throughout Europe must be done by using the roads conforming the European Road Transport Network. In this network, there are several parking areas where lorry drivers can park to rest according to the regulations. According to the "European Agreement concerning the International Carriage of Dangerous Goods by Road", parking areas where lorries transporting dangerous goods can park to rest, must follow several security stipulations to keep safe the rest of road users. At this respect, these lorries must be parked in adapted areas with strict and permanent surveillance measures. Moreover, drivers must satisfy several restrictions about resting and driving time. Under these facts, one may expect that there exist enough parking areas for the transport of this type of goods in order to obey the regulations prescribed by the European Union and its member countries. However, the already-existing parking areas are not sufficient to cover all the stops required by drivers transporting dangerous goods. Our main goal is, starting from the already-existing parking areas and the loading-and-unloading location, to provide an optimal answer to the following question: how many additional parking areas must be built and where must they be located to assure that lorry drivers can transport dangerous goods following all the stipulations about security and safety for their stops? The sense of the word “optimal” is due to the fact that we give a global solution for the location of parking areas throughout the whole European Road Transport Network, adjusting the number of additional areas to be as lower as possible. To do so, we have modeled the problem using graph theory since we are working with a road network. As nodes, we have considered the locations of each already-existing parking area, each loading-and-unloading area each road bifurcation. Each road connecting two nodes is considered as an edge in the graph whose weight corresponds to the distance between both nodes in the edge. By applying a new efficient algorithm, we have found the additional nodes for the network representing the new parking areas adapted for dangerous goods, under the fact that the distance between two parking areas must be less than or equal to 400 km.

Keywords: trans-european transport network, dangerous goods, parking areas, graph-based modeling

Procedia PDF Downloads 283

Authors: Sungho Kim, Jaechoul Shin, Yujin Baek, Nakseok Kim, Kyungnam Kim, Shinhaeng Jo

Abstract:

The climate change and increase in heavy traffic have been accelerating damages that cause the problems such as pothole on asphalt pavement. Pothole causes traffic accidents, vehicle damages, road casualties and traffic congestion. A quick and efficient maintenance method is needed because pothole is caused by stripping and accelerates pavement distress. In this study, we propose a rapid and systematic pothole management by developing a pothole automated repairing equipment including a volume measurement system of pothole. Three kinds of cold mix asphalt mixture were investigated to select repair materials. The materials were evaluated for satisfaction with quality standard and applicability to automated equipment. The volume measurement system of potholes was composed of multi-sensor that are combined with laser sensor and ultrasonic sensor and installed in front and side of the automated repair equipment. An algorithm was proposed to calculate the amount of repair material according to the measured pothole volume, and the system for releasing the correct amount of material was developed. Field test results showed that the loss of repair material amount could be reduced from approximately 20% to 6% per one point of pothole. Pothole rapid automated repair equipment will contribute to improvement on quality and efficient and economical maintenance by not only reducing materials and resources but also calculating appropriate materials. Through field application, it is possible to improve the accuracy of pothole volume measurement, to correct the calculation of material amount, and to manage the pothole data of roads, thereby enabling more efficient pavement maintenance management. Acknowledgment: The author would like to thank the MOLIT(Ministry of Land, Infrastructure, and Transport). This work was carried out through the project funded by the MOLIT. The project name is 'development of 20mm grade for road surface detecting roadway condition and rapid detection automation system for removal of pothole'.

Keywords: automated equipment, management, multi-beam sensor, pothole

Procedia PDF Downloads 225

Authors: Dewi Retno Sari Saputro, Purnami Widyaningsih, Hendrika Handayani

Abstract:

Extreme data on an observation can occur due to unusual circumstances in the observation. The data can provide important information that can’t be provided by other data so that its existence needs to be further investigated. The method for obtaining extreme data is one of them using maxima block method. The distribution of extreme data sets taken with the maxima block method is called the distribution of extreme values. Distribution of extreme values is Gumbel distribution with two parameters. The parameter estimation of Gumbel distribution with maximum likelihood method (ML) is difficult to determine its exact value so that it is necessary to solve the approach. The purpose of this study was to determine the parameter estimation of Gumbel distribution with quasi-Newton BFGS method. The quasi-Newton BFGS method is a numerical method used for nonlinear function optimization without constraint so that the method can be used for parameter estimation from Gumbel distribution whose distribution function is in the form of exponential doubel function. The quasi-New BFGS method is a development of the Newton method. The Newton method uses the second derivative to calculate the parameter value changes on each iteration. Newton's method is then modified with the addition of a step length to provide a guarantee of convergence when the second derivative requires complex calculations. In the quasi-Newton BFGS method, Newton's method is modified by updating both derivatives on each iteration. The parameter estimation of the Gumbel distribution by a numerical approach using the quasi-Newton BFGS method is done by calculating the parameter values that make the distribution function maximum. In this method, we need gradient vector and hessian matrix. This research is a theory research and application by studying several journals and textbooks. The results of this study obtained the quasi-Newton BFGS algorithm and estimation of Gumbel distribution parameters. The estimation method is then applied to daily rainfall data in Purworejo District to estimate the distribution parameters. This indicates that the high rainfall that occurred in Purworejo District decreased its intensity and the range of rainfall that occurred decreased.

Keywords: parameter estimation, Gumbel distribution, maximum likelihood, broyden fletcher goldfarb shanno (BFGS)quasi newton

Procedia PDF Downloads 328

Authors: Xiaobin Liang, Wei Liang, Laibin Zhang, Xiaoyan Guo

Abstract:

Pipelines pass through coal mined gobs inevitably in the mining area, the stability of which has great influence on the safety of pipelines. After extensive literature study and field research, it was found that there are a few risk assessment methods for coal mined gob pipelines, and there is a lack of data on the gob sites. Therefore, the fuzzy comprehensive evaluation method is widely used based on expert opinions. However, the subjective opinions or lack of experience of individual experts may lead to inaccurate evaluation results. Hence the accuracy of the results needs to be further improved. This paper presents a comprehensive approach to achieve this purpose by combining bow-tie model and cloud inference. The specific evaluation process is as follows: First, a bow-tie model composed of a fault tree and an event tree is established to graphically illustrate the probability and consequence indicators of pipeline failure. Second, the interval estimation method can be scored in the form of intervals to improve the accuracy of the results, and the censored mean algorithm is used to remove the maximum and minimum values of the score to improve the stability of the results. The golden section method is used to determine the weight of the indicators and reduce the subjectivity of index weights. Third, the failure probability and failure consequence scores of the pipeline are converted into three numerical features by using cloud inference. The cloud inference can better describe the ambiguity and volatility of the results which can better describe the volatility of the risk level. Finally, the cloud drop graphs of failure probability and failure consequences can be expressed, which intuitively and accurately illustrate the ambiguity and randomness of the results. A case study of a coal mine gob pipeline carrying natural gas has been investigated to validate the utility of the proposed method. The evaluation results of this case show that the probability of failure of the pipeline is very low, the consequences of failure are more serious, which is consistent with the reality.

Keywords: bow-tie model, natural gas pipeline, coal mine gob, cloud inference

Procedia PDF Downloads 253

Authors: Thomas Monahan, Nicolas Gorius, Thanh Nguyen

Abstract:

Exoplanet atmospheric parameters retrieval is a complex, computationally intensive, inverse modeling problem in which an exoplanet’s atmospheric composition is extracted from an observed spectrum. Traditional Bayesian sampling methods require extensive time and computation, involving algorithms that compare large numbers of known atmospheric models to the input spectral data. Runtimes are directly proportional to the number of parameters under consideration. These increased power and runtime requirements are difficult to accommodate in space missions where model size, speed, and power consumption are of particular importance. The use of traditional Bayesian sampling methods, therefore, compromise model complexity or sampling accuracy. The Atmospheric Retrievals conditional Generative Adversarial Network (ARcGAN) is a deep convolutional generative adversarial network that improves on the previous model’s speed and accuracy. We demonstrate the efficacy of artificial intelligence to quickly and reliably predict atmospheric parameters and present it as a viable alternative to slow and computationally heavy Bayesian methods. In addition to its broad applicability across instruments and planetary types, ARcGAN has been designed to function on low power application-specific integrated circuits. The application of edge computing to atmospheric retrievals allows for real or near-real-time quantification of atmospheric constituents at the instrument level. Additionally, edge computing provides both high-performance and power-efficient computing for AI applications, both of which are critical for space missions. With the edge computing chip implementation, ArcGAN serves as a strong basis for the development of a similar machine-learning algorithm to reduce the downlinked data volume from the Compact Ultraviolet to Visible Imaging Spectrometer (CUVIS) onboard the DAVINCI mission to Venus.

Keywords: deep learning, generative adversarial network, edge computing, atmospheric parameters retrieval

Procedia PDF Downloads 173

Authors: Bartosz Kedra, Robert Malkowski

Abstract:

This paper provides description and presentation of laboratory test unit built basing on 150 kVA power frequency converter and Simulink RealTime platform. Assumptions, based on criteria which load and generator types may be simulated using discussed device, are presented, as well as control algorithm structure. As laboratory setup contains transformer with thyristor controlled tap changer, a wider scope of setup capabilities is presented. Information about used communication interface, data maintenance, and storage solution as well as used Simulink real-time features is presented. List and description of all measurements are provided. Potential of laboratory setup modifications is evaluated. For purposes of Rapid Control Prototyping, a dedicated environment was used Simulink RealTime. Therefore, load model Functional Unit Controller is based on a PC computer with I/O cards and Simulink RealTime software. Simulink RealTime was used to create real-time applications directly from Simulink models. In the next step, applications were loaded on a target computer connected to physical devices that provided opportunity to perform Hardware in the Loop (HIL) tests, as well as the mentioned Rapid Control Prototyping process. With Simulink RealTime, Simulink models were extended with I/O cards driver blocks that made automatic generation of real-time applications and performing interactive or automated runs on a dedicated target computer equipped with a real-time kernel, multicore CPU, and I/O cards possible. Results of performed laboratory tests are presented. Different load configurations are described and experimental results are presented. This includes simulation of under frequency load shedding, frequency and voltage dependent characteristics of groups of load units, time characteristics of group of different load units in a chosen area and arbitrary active and reactive power regulation basing on defined schedule.

Keywords: MATLAB, power converter, Simulink Real-Time, thyristor-controlled tap changer

Procedia PDF Downloads 326

Authors: Shaikah Alsubayae, Gianluigi Casse, Carlos Chavez, Jon Taylor, Alan Taylor, Mohammad Alsulimane

Abstract:

Achieving precise radiotherapy through carbon therapy necessitates the accurate monitoring of radiation dose distribution within the patient's body. This process is pivotal for targeted tumor treatment, minimizing harm to healthy tissues, and enhancing overall treatment effectiveness while reducing the risk of side effects. In our investigation, we adopted a methodological approach to monitor secondary proton doses in carbon therapy using Monte Carlo (MC) simulations. Initially, Geant4 simulations were employed to extract the initial positions of secondary particles generated during interactions between carbon ions and water, including protons, gamma rays, alpha particles, neutrons, and tritons. Subsequently, we explored the relationship between the carbon ion beam and these secondary particles. Interaction vertex imaging (IVI) proves valuable for monitoring dose distribution during carbon therapy, providing information about secondary particle locations and abundances, particularly protons. The IVI method relies on charged particles produced during ion fragmentation to gather range information by reconstructing particle trajectories back to their point of origin, known as the vertex. In the context of carbon ion therapy, our simulation results indicated a strong correlation between some secondary particles and the range of carbon ions. However, challenges arose due to the unique elongated geometry of the target, hindering the straightforward transmission of forward-generated protons. Consequently, the limited protons that did emerge predominantly originated from points close to the target entrance. Fragment (protons) trajectories were approximated as straight lines, and a beam back-projection algorithm, utilizing interaction positions recorded in Si detectors, was developed to reconstruct vertices. The analysis revealed a correlation between the reconstructed and actual positions.

Keywords: radiotherapy, carbon therapy, monitor secondary proton doses, interaction vertex imaging

Procedia PDF Downloads 80

Authors: Joy Cao, Min Zhou

Abstract:

Purpose: Acute Type A aortic dissection is a well-known cause of extremely high mortality rate. A highly accurate and cost-effective non-invasive predictor is critically needed so that the patient can be treated at earlier stage. Although various CFD approaches have been tried to establish some prediction frameworks, they are sensitive to uncertainty in both image segmentation and boundary conditions. Tedious pre-processing and demanding calibration procedures requirement further compound the issue, thus hampering their clinical applicability. Using the latest physics informed deep learning methods to establish an accurate and cost-effective predictor framework are amongst the main goals for a better Type A aortic dissection treatment. Methods: Via training a novel physics-informed deep residual network, with non-invasive 4D MRI displacement vectors as inputs, the trained model can cost-effectively calculate all these biomarkers: aortic blood pressure, WSS, and OSI, which are used to predict potential type A aortic dissection to avoid the high mortality events down the road. Results: The proposed deep learning method has been successfully trained and tested with both synthetic 3D aneurysm dataset and a clinical dataset in the aortic dissection context using Google colab environment. In both cases, the model has generated aortic blood pressure, WSS, and OSI results matching the expected patient’s health status. Conclusion: The proposed novel physics-informed deep residual network shows great potential to create a cost-effective, non-invasive predictor framework. Additional physics-based de-noising algorithm will be added to make the model more robust to clinical data noises. Further studies will be conducted in collaboration with big institutions such as Cleveland Clinic with more clinical samples to further improve the model’s clinical applicability.

Keywords: type-a aortic dissection, deep residual networks, blood flow modeling, data-driven modeling, non-invasive diagnostics, deep learning, artificial intelligence.

Procedia PDF Downloads 92

Authors: Javier Muro, Anja Linstadter, Florian Manner, Lisa Schwarz, Stephan Wollauer, Paul Magdon, Gohar Ghazaryan, Olena Dubovyk

Abstract:

Monitoring the trade-off between biomass production and biodiversity in grasslands is critical to evaluate the effects of management practices across environmental gradients. New generations of remote sensing sensors and machine learning approaches can model grasslands’ characteristics with varying accuracies. However, studies often fail to cover a sufficiently broad range of environmental conditions, and evidence suggests that prediction models might be case specific. In this study, biomass production and biodiversity indices (species richness and Fishers’ α) are modeled in 150 grassland plots for three sites across Germany. These sites represent a North-South gradient and are characterized by distinct soil types, topographic properties, climatic conditions, and management intensities. Predictors used are derived from Sentinel-1 & 2 and a set of topoedaphic variables. The transferability of the models is tested by training and validating at different sites. The performance of feed-forward deep neural networks (DNN) is compared to a random forest algorithm. While biomass predictions across gradients and sites were acceptable (r2 0.5), predictions of biodiversity indices were poor (r2 0.14). DNN showed higher generalization capacity than random forest when predicting biomass across gradients and sites (relative root mean squared error of 0.5 for DNN vs. 0.85 for random forest). DNN also achieved high performance when using the Sentinel-2 surface reflectance data rather than different combinations of spectral indices, Sentinel-1 data, or topoedaphic variables, simplifying dimensionality. This study demonstrates the necessity of training biomass and biodiversity models using a broad range of environmental conditions and ensuring spatial independence to have realistic and transferable models where plot level information can be upscaled to landscape scale.

Keywords: ecosystem services, grassland management, machine learning, remote sensing

Procedia PDF Downloads 220

Authors: Tigabu Dagne Akal

Abstract:

While advances in computer and communications technology have made the network ubiquitous, they have also rendered networked systems vulnerable to malicious attacks devised from a distance. These attacks or intrusions start with attackers infiltrating a network through a vulnerable host and then launching further attacks on the local network or Intranet. Nowadays, system administrators and network professionals can attempt to prevent such attacks by developing intrusion detection tools and systems using data mining technology. In this study, the experiments were conducted following the Knowledge Discovery in Database Process Model. The Knowledge Discovery in Database Process Model starts from selection of the datasets. The dataset used in this study has been taken from Massachusetts Institute of Technology Lincoln Laboratory. After taking the data, it has been pre-processed. The major pre-processing activities include fill in missed values, remove outliers; resolve inconsistencies, integration of data that contains both labelled and unlabelled datasets, dimensionality reduction, size reduction and data transformation activity like discretization tasks were done for this study. A total of 21,533 intrusion records are used for training the models. For validating the performance of the selected model a separate 3,397 records are used as a testing set. For building a predictive model for intrusion detection J48 decision tree and the Naïve Bayes algorithms have been tested as a classification approach for both with and without feature selection approaches. The model that was created using 10-fold cross validation using the J48 decision tree algorithm with the default parameter values showed the best classification accuracy. The model has a prediction accuracy of 96.11% on the training datasets and 93.2% on the test dataset to classify the new instances as normal, DOS, U2R, R2L and probe classes. The findings of this study have shown that the data mining methods generates interesting rules that are crucial for intrusion detection and prevention in the networking industry. Future research directions are forwarded to come up an applicable system in the area of the study.

Keywords: intrusion detection, data mining, computer science, data mining

Procedia PDF Downloads 299

Authors: Mostafa Zandi, Ramin Mansouri

Abstract:

Spillways are one of the most important hydraulic structures of dams that provide the stability of the dam and downstream areas at the time of flood. Morning-Glory spillway is one of the common spillways for discharging the overflow water behind dams, these kinds of spillways are constructed in dams with small reservoirs. In this research, the hydraulic flow characteristics of a morning-glory spillways are investigated with CFD model. Two dimensional unsteady RANS equations were solved numerically using Finite Volume Method. The PISO scheme was applied for the velocity-pressure coupling. The mostly used two-equation turbulence models, k- and k-, were chosen to model Reynolds shear stress term. The power law scheme was used for discretization of momentum, k , and  equations. The VOF method (geometrically reconstruction algorithm) was adopted for interface simulation. The results show that the fine computational grid, the input speed condition for the flow input boundary, and the output pressure for the boundaries that are in contact with the air provide the best possible results. Also, the standard wall function is chosen for the effect of the wall function, and the turbulent model k -ε (Standard) has the most consistent results with experimental results. When the jet is getting closer to end of basin, the computational results increase with the numerical results of their differences. The lower profile of the water jet has less sensitivity to the hydraulic jet profile than the hydraulic jet profile. In the pressure test, it was also found that the results show that the numerical values of the pressure in the lower landing number differ greatly in experimental results. The characteristics of the complex flows over a Morning-Glory spillway were studied numerically using a RANS solver. Grid study showed that numerical results of a 57512-node grid had the best agreement with the experimental values. The desired downstream channel length was preferred to be 1.5 meter, and the standard k-ε turbulence model produced the best results in Morning-Glory spillway. The numerical free-surface profiles followed the theoretical equations very well.

Keywords: morning-glory spillway, CFD model, hydraulic characteristics, wall function

Procedia PDF Downloads 79

Authors: Evgeny V. Blagin, Aleksandr I. Dovgjallo, Dmitry A. Uglanov

Abstract:

This article deals with research of the working process in the thermocompressor which operates on cryogenic working fluid. Thermocompressor is device suited for the conversation of heat energy directly to the potential energy of pressure. Suggested thermocompressor is suited for operation during liquid natural gas (LNG) re-gasification and is placed after evaporator. Such application of thermocompressor allows using of the LNG cold energy for rising of working fluid pressure, which then can be used for electricity generation or another purpose. Thermocompressor consists of two chambers divided by the regenerative heat exchanger. Calculation algorithm for unsteady calculation of thermocompressor working process was suggested. The results of this investigation are to change of thermocompressor’s chambers temperature and pressure during the working cycle. These distributions help to find out the parameters, which significantly influence thermocompressor efficiency. These parameters include regenerative heat exchanger coefficient of the performance (COP) dead volume of the chambers, working frequency of the thermocompressor etc. Exergy analysis was performed to estimate thermocompressor efficiency. Cryogenic thermocompressor operated on nitrogen working fluid was chosen as a prototype. Calculation of the temperature and pressure change was performed with taking into account heat fluxes through regenerator and thermocompressor walls. Temperature of the cold chamber significantly differs from the results of steady calculation, which is caused by friction of the working fluid in regenerator and heat fluxes from the hot chamber. The rise of the cold chamber temperature leads to decreasing of thermocompressor delivery volume. Temperature of hot chamber differs negligibly because losses due to heat fluxes to a cold chamber are compensated by the friction of the working fluid in the regenerator. Optimal working frequency was selected. Main results of the investigation: -theoretical confirmation of thermocompressor operation capability on the cryogenic working fluid; -optimal working frequency was found; -value of the cold chamber temperature differs from the starting value much more than the temperature of the hot chamber; -main parameters which influence thermocompressor performance are regenerative heat exchanger COP and heat fluxes through regenerator and thermocompressor walls.

Keywords: cold energy, liquid natural gas, thermocompressor, regenerative heat exchanger

Procedia PDF Downloads 585

Authors: Evren Isen

Abstract:

In grid-connected renewable energy systems, input power is controlled by AC/DC converter or/and DC/DC converter depending on output voltage of input source. The power is injected to DC-link, and DC-link voltage is regulated by inverter controlling the grid current. Inverter performance is considerable in grid-connected renewable energy systems to meet the utility standards. In this paper, modelling and simulation of hysteresis current controlled single-phase grid-connected inverter that is utilized in renewable energy systems, such as wind and solar systems, are presented. 2 kW single-phase grid-connected inverter is simulated in Simulink and modeled in Matlab-m-file. The grid current synchronization is obtained by phase locked loop (PLL) technique in dq synchronous rotating frame. Although dq-PLL can be easily implemented in three-phase systems, there is difficulty to generate β component of grid voltage in single-phase system because single-phase grid voltage exists. Inverse-Park PLL with low-pass filter is used to generate β component for grid angle determination. As grid current is controlled by constant bandwidth hysteresis current control (HCC) technique, average switching frequency and variation of switching frequency in a fundamental period are considered. 3.56% total harmonic distortion value of grid current is achieved with 0.5 A bandwidth. Average value of switching frequency and total harmonic distortion curves for different hysteresis bandwidth are obtained from model in m-file. Average switching frequency is 25.6 kHz while switching frequency varies between 14 kHz-38 kHz in a fundamental period. The average and maximum frequency difference should be considered for selection of solid state switching device, and designing driver circuit. Steady-state and dynamic response performances of the inverter depending on the input power are presented with waveforms. The control algorithm regulates the DC-link voltage by adjusting the output power.

Keywords: grid-connected inverter, hysteresis current control, inverter modelling, single-phase inverter

Procedia PDF Downloads 480

Authors: Rezvan Ravanfar Haghighi, V. C. Vani, Suresh Perumal, Sabyasachi Chatterjee, Pratik Kumar

Abstract:

X-ray attenuation coefficient [µ(E)] of any substance, for energy (E), is a sum of the contributions from the Compton scattering [ μCom(E)] and photoelectric effect [µPh(E)]. In terms of the, electron density (ρe) and the effective atomic number (Zeff) we have µCom(E) is proportional to [(ρe)fKN(E)] while µPh(E) is proportional to [(ρeZeffx)/Ey] with fKN(E) being the Klein-Nishina formula, with x and y being the exponents for photoelectric effect. By taking the sample's HU at two different excitation voltages (V=V1, V2) of the CT machine, we can solve for X=ρe, Y=ρeZeffx from these two independent equations, as is attempted in DECT inversion. Since µCom(E) and µPh(E) are both energy dependent, the coefficients of inversion are also dependent on (a) the source spectrum S(E,V) and (b) the detector efficiency D(E) of the CT machine. In the present paper we tabulate these coefficients of inversion for different practical manifestations of S(E,V) and D(E). The HU(V) values from the CT follow: <µ(V)>=<µw(V)>[1+HU(V)/1000] where the subscript 'w' refers to water and the averaging process <….> accounts for the source spectrum S(E,V) and the detector efficiency D(E). Linearity of μ(E) with respect to X and Y implies that (a) <µ(V)> is a linear combination of X and Y and (b) for inversion, X and Y can be written as linear combinations of two independent observations <µ(V1)>, <µ(V2)> with V1≠V2. These coefficients of inversion would naturally depend upon S(E, V) and D(E). We numerically investigate this dependence for some practical cases, by taking V = 100 , 140 kVp, as are used for cardiological investigations. The S(E,V) are generated by using the Boone-Seibert source spectrum, being superposed on aluminium filters of different thickness lAl with 7mm≤lAl≤12mm and the D(E) is considered to be that of a typical Si[Li] solid state and GdOS scintilator detector. In the values of X and Y, found by using the calculated inversion coefficients, errors are below 2% for data with solutions of glycerol, sucrose and glucose. For low Zeff materials like propionic acid, Zeffx is overestimated by 20% with X being within1%. For high Zeffx materials like KOH the value of Zeffx is underestimated by 22% while the error in X is + 15%. These imply that the source may have additional filtering than the aluminium filter specified by the manufacturer. Also it is found that the difference in the values of the inversion coefficients for the two types of detectors is negligible. The type of the detector does not affect on the DECT inversion algorithm to find the unknown chemical characteristic of the scanned materials. The effect of the source should be considered as an important factor to calculate the coefficients of inversion.

Keywords: attenuation coefficient, computed tomography, photoelectric effect, source spectrum

Procedia PDF Downloads 403

Authors: Berfin Yildiz

Abstract:

These days, increasing global warming effects, limited amount of energy resources, etc., necessitates the awareness that must be present in every profession group. The architecture and construction sectors are responsible for both the embodied and operational energy of the materials. This responsibility has led designers to seek alternative solutions for energy-efficient material selection. The choice of energy-efficient material requires consideration of the entire life cycle, including the building's production, use, and disposal energy. The aim of this study is to investigate the method of material selection of external thermal insulation composite systems (ETICS). Embodied and in-use energy values of material alternatives were used for the evaluation in this study. The operational energy is calculated according to the u-value calculation method defined in the TS 825 (Thermal Insulation Requirements) standard for Turkey, and the embodied energy is calculated based on the manufacturer's Energy Performance Declaration (EPD). ETICS consists of a wall, adhesive, insulation, lining, mechanical, mesh, and exterior finishing materials. In this study, lining, mechanical, and mesh materials were ignored because EPD documents could not be obtained. The material selection problem is designed as a hypothetical volume area (5x5x3m) and defined as a multi-objective discrete optimization problem for external thermal insulation composite systems. Defining the problem as a discrete optimization problem is important in order to choose between materials of various thicknesses and sizes. Since production and use energy values, which are determined as optimization objectives in the study, are often conflicting values, material selection is defined as a multi-objective optimization problem, and it is aimed to obtain many solution alternatives by using Hypervolume (HypE) algorithm. The enrollment process started with 100 individuals and continued for 50 generations. According to the obtained results, it was observed that autoclaved aerated concrete and Ponce block as wall material, glass wool, as insulation material gave better results.

Keywords: embodied energy, multi-objective discrete optimization, performative design, thermal insulation

Procedia PDF Downloads 146

Authors: Naser Kazemi Eilaki, Carolyn Ahmer, Ilona Heldal, Bjarne Christian Hagen

Abstract:

Older people and people with disabilities are recognized as at-risk groups when it comes to egress and travel from hazard zone to safe places. One's disability can negatively influence her or his escape time, and this becomes even more important when people from this target group live alone. This research deals with the fire safety of mentioned people's buildings by means of probabilistic methods. For this purpose, fire safety is addressed by modeling the egress of our target group from a hazardous zone to a safe zone. A common type of detached house with a prevalent plan has been chosen for safety analysis, and a limit state function has been developed according to the time-line evacuation model, which is based on a two-zone and smoke development model. An analytical computer model (B-Risk) is used to consider smoke development. Since most of the involved parameters in the fire development model pose uncertainty, an appropriate probability distribution function has been considered for each one of the variables with indeterministic nature. To achieve safety and reliability for the at-risk groups, the fire safety index method has been chosen to define the probability of failure (causalities) and safety index (beta index). An improved harmony search meta-heuristic optimization algorithm has been used to define the beta index. Sensitivity analysis has been done to define the most important and effective parameters for the fire safety of the at-risk group. Results showed an area of openings and intervals to egress exits are more important in buildings, and the safety of people would improve with increasing dimensions of occupant space (building). Fire growth is more critical compared to other parameters in the home without a detector and fire distinguishing system, but in a home equipped with these facilities, it is less important. Type of disabilities has a great effect on the safety level of people who live in the same home layout, and people with visual impairment encounter more risk of capturing compared to visual and movement disabilities.

Keywords: fire safety, at-risk groups, zone model, egress time, uncertainty

Procedia PDF Downloads 105

Authors: Khadija Refouh

Abstract:

Culture bound-expressions have been a bottleneck for Natural Language Processing (NLP) and comprehension, especially in the case of machine translation (MT). In the last decade, the field of machine translation has greatly advanced. Neural machine translation NMT has recently achieved considerable development in the quality of translation that outperformed previous traditional translation systems in many language pairs. Neural machine translation NMT is an Artificial Intelligence AI and deep neural networks applied to language processing. Despite this development, there remain some serious challenges that face neural machine translation NMT when translating culture bounded-expressions, especially for low resources language pairs such as Arabic-English and Arabic-French, which is not the case with well-established language pairs such as English-French. Machine translation of opaque idioms from English into French are likely to be more accurate than translating them from English into Arabic. For example, Google Translate Application translated the sentence “What a bad weather! It runs cats and dogs.” to “يا له من طقس سيء! تمطر القطط والكلاب” into the target language Arabic which is an inaccurate literal translation. The translation of the same sentence into the target language French was “Quel mauvais temps! Il pleut des cordes.” where Google Translate Application used the accurate French corresponding idioms. This paper aims to perform NMT experiments towards better translation of opaque idioms using high quality clean multilingual corpus. This Corpus will be collected analytically from human generated idiom translation. AutoML translation, a Google Neural Machine Translation Platform, is used as a custom translation model to improve the translation of opaque idioms. The automatic evaluation of the custom model will be compared to the Google NMT using Bilingual Evaluation Understudy Score BLEU. BLEU is an algorithm for evaluating the quality of text which has been machine-translated from one natural language to another. Human evaluation is integrated to test the reliability of the Blue Score. The researcher will examine syntactical, lexical, and semantic features using Halliday's functional theory.

Keywords: multilingual corpora, natural language processing (NLP), neural machine translation (NMT), opaque idioms

Procedia PDF Downloads 152

Authors: Asnakew Mulualem Tegegne, Tarun Kumar Lohani, Abunu Atlabachew Eshete

Abstract:

Groundwater potential delineation is essential for efficient water resource utilization and long-term development. The scarcity of potable and irrigation water has become a critical issue due to natural and anthropogenic activities in meeting the demands of human survival and productivity. With these constraints, groundwater resources are now being used extensively in Ethiopia. Therefore, an innovative convolutional neural network (CNN) is successfully applied in the Gunabay watershed to delineate groundwater potential based on the selected major influencing factors. Groundwater recharge, lithology, drainage density, lineament density, transmissivity, and geomorphology were selected as major influencing factors during the groundwater potential of the study area. For dataset training, 70% of samples were selected and 30% were used for serving out of the total 128 samples. The spatial distribution of groundwater potential has been classified into five groups: very low (10.72%), low (25.67%), moderate (31.62%), high (19.93%), and very high (12.06%). The area obtains high rainfall but has a very low amount of recharge due to a lack of proper soil and water conservation structures. The major outcome of the study showed that moderate and low potential is dominant. Geodetoctor results revealed that the magnitude influences on groundwater potential have been ranked as transmissivity (0.48), recharge (0.26), lineament density (0.26), lithology (0.13), drainage density (0.12), and geomorphology (0.06). The model results showed that using a convolutional neural network (CNN), groundwater potentiality can be delineated with higher predictive capability and accuracy. CNN-based AUC validation platform showed that 81.58% and 86.84% were accrued from the accuracy of training and testing values, respectively. Based on the findings, the local government can receive technical assistance for groundwater exploration and sustainable water resource development in the Gunabay watershed. Finally, the use of a detector-based deep learning algorithm can provide a new platform for industrial sectors, groundwater experts, scholars, and decision-makers.

Keywords: CNN, geodetector, groundwater influencing factors, Groundwater potential, Gunabay watershed

Procedia PDF Downloads 25