Search results for: point preprocessing

Authors: Abdulfetah Shobole, Arif Karakas, Ugur Savas Selamogullari, Mustafa Baysal

Abstract:

The concern of reducing emissions of Co2 from the fossil fuel generating units and using renewable energy sources increased in our world. Due this fact the integration ratio of wind farms to grid reached 20-30% in some part of our world. With increased integration of large MW scaled wind farms to the electric grid, the stability of the electrical system is a great concern. Thus, operators of power systems usually deman the wind turbine generators to obey the same rules as other traditional kinds of generation, such as thermal and hydro, i.e. not affect the grid stability. FACTS devices such as SVC or STATCOM are mostly installed close to the connection point of the wind farm to the grid in order to increase the stability especially during faulty conditions. In this paper wind farm with DFIG turbine type and STATCOM are dynamically modeled and simulated under three phase short circuit fault condition. The dynamic modeling is done by DigSILENT PowerFactory for the wind farm, STATCOM and the network. The simulation results show improvement of system stability near to the connection point of the STATCOM.

Keywords: DFIG wind turbine, statcom, dynamic modeling, digsilent

Procedia PDF Downloads 712

Authors: Danielle Shackley, Yetunde Folajimi

Abstract:

As more people turn to the internet seeking health-related information, there is more risk of finding false, inaccurate, or dangerous information. Sentiment analysis is a natural language processing technique that assigns polarity scores to text, ranging from positive, neutral, and negative. In this research, we evaluate the weight of a sentiment analysis feature added to fake health news classification models. The dataset consists of existing reliably labeled health article headlines that were supplemented with health information collected about COVID-19 from social media sources. We started with data preprocessing and tested out various vectorization methods such as Count and TFIDF vectorization. We implemented 3 Naive Bayes classifier models, including Bernoulli, Multinomial, and Complement. To test the weight of the sentiment analysis feature on the dataset, we created benchmark Naive Bayes classification models without sentiment analysis, and those same models were reproduced, and the feature was added. We evaluated using the precision and accuracy scores. The Bernoulli initial model performed with 90% precision and 75.2% accuracy, while the model supplemented with sentiment labels performed with 90.4% precision and stayed constant at 75.2% accuracy. Our results show that the addition of sentiment analysis did not improve model precision by a wide margin; while there was no evidence of improvement in accuracy, we had a 1.9% improvement margin of the precision score with the Complement model. Future expansion of this work could include replicating the experiment process and substituting the Naive Bayes for a deep learning neural network model.

Keywords: sentiment analysis, Naive Bayes model, natural language processing, topic analysis, fake health news classification model

Procedia PDF Downloads 97

Authors: Natascha C. D'Amico, Enzo Grossi, Giovanni Valbusa, Ala Malasevschi, Gianpiero Cardone, Sergio Papa

Abstract:

Purpose: To characterize, through a radiomic approach, the nature of areas classified PI-RADS (Prostate Imaging Reporting and Data System) 3/5, recognized in multiparametric prostate magnetic resonance with T2-weighted (T2w), diffusion and perfusion sequences with paramagnetic contrast. Methods and Materials: 24 cases undergoing multiparametric prostate MR and biopsy were admitted to this pilot study. Clinical outcome of the PI-RADS 3/5 was found through biopsy, finding 8 malignant tumours. The analysed images were acquired with a Philips achieva 1.5T machine with a CE- T2-weighted sequence in the axial plane. Semi-automatic tumour segmentation was carried out on MR images using 3DSlicer image analysis software. 45 shape-based, intensity-based and texture-based features were extracted and represented the input for preprocessing. An evolutionary algorithm (a TWIST system based on KNN algorithm) was used to subdivide the dataset into training and testing set and select features yielding the maximal amount of information. After this pre-processing 20 input variables were selected and different machine learning systems were used to develop a predictive model based on a training testing crossover procedure. Results: The best machine learning system (three-layers feed-forward neural network) obtained a global accuracy of 90% ( 80 % sensitivity and 100% specificity ) with a ROC of 0.82. Conclusion: Machine learning systems coupled with radiomics show a promising potential in distinguishing benign from malign tumours in PI-RADS 3/5 areas.

Keywords: machine learning, MR prostate, PI-Rads 3, radiomics

Procedia PDF Downloads 188

Authors: Yujiang Wu

Abstract:

As electrical machine (e-machine) power density re-querulents become more stringent in vehicle electrification, mounting a temperature sensor for e-machine stator windings becomes increasingly difficult. This can lead to higher manufacturing costs, complicated harnesses, and reduced reliability. In this paper, we propose a deep-learning method for predicting electric machine winding temperature, which can either replace the sensor entirely or serve as a backup to the existing sensor. We compare the performance of our method, the stateful long short-term memory networks (LSTM) with truncated backpropagation through time (TBTT), with that of linear regression, as well as stateless LSTM with/without residual connection. Our results demonstrate the strength of combining stateful LSTM and TBTT in tackling nonlinear time series prediction problems with long sequence lengths. Additionally, in industrial applications, high-temperature region prediction accuracy is more important because winding temperature sensing is typically used for derating machine power when the temperature is high. To evaluate the performance of our algorithm, we developed a temperature-stratified MSE. We propose a simple but effective data preprocessing trick to improve the high-temperature region prediction accuracy. Our experimental results demonstrate the effectiveness of our proposed method in accurately predicting winding temperature, particularly in high-temperature regions, while also reducing manufacturing costs and improving reliability.

Keywords: deep learning, electrical machine, functional safety, long short-term memory networks (LSTM), thermal management, time series prediction

Procedia PDF Downloads 99

Authors: İsmail İnce, Mustafa Fener, Sair Kahraman

Abstract:

The uniaxial compressive strength (UCS) of rocks is an important input parameter for the design of rock engineering project. Compressive strength can be determined in the laboratory using the uniaxial compressive strength (UCS) test. Although the test is relatively simple, the method is time consuming and expensive. Therefore many researchers have tried to assess the uniaxial compressive strength values of rocks via relatively simple and indirect tests (e.g. point load strength test, Schmidt Hammer hardness rebound test, P-wave velocity test, etc.). Pyroclastic rocks are widely exposed in the various regions of the world. Cappadocia region located in the Central Anatolia is one of the most spectacular cite of these regions. It is important to determine the mechanical behaviour of the pyroclastic rocks due to their ease of carving, heat insulation properties and building some civil engineering constructions in them. The purpose of this study is to estimate a widely varying uniaxial strength of pyroclastic rocks from Cappadocia region by means of point load strength, porosity, dry density and saturated density tests utilizing gene expression programming.

Keywords: pyroclastic rocks, uniaxial compressive strength, gene expression programming (GEP, Cappadocia region

Procedia PDF Downloads 341

Authors: Asma Hanif, A. I. K. Butt, Shabir Ahmad, Rahim Ud Din, Mustafa Inc

Abstract:

This paper is devoted to a study of the fuzzy fractional mathematical model reviewing the transmission dynamics of the infectious disease Covid-19. The proposed dynamical model consists of susceptible, exposed, symptomatic, asymptomatic, quarantine, hospitalized and recovered compartments. In this study, we deal with the fuzzy fractional model defined in Caputo’s sense. We show the positivity of state variables that all the state variables that represent different compartments of the model are positive. Using Gronwall inequality, we show that the solution of the model is bounded. Using the notion of the next-generation matrix, we find the basic reproduction number of the model. We demonstrate the local and global stability of the equilibrium point by using the concept of Castillo-Chavez and Lyapunov theory with the Lasalle invariant principle, respectively. We present the results that reveal the existence and uniqueness of the solution of the considered model through the fixed point theorem of Schauder and Banach. Using the fuzzy hybrid Laplace method, we acquire the approximate solution of the proposed model. The results are graphically presented via MATLAB-17.

Keywords: Caputo fractional derivative, existence and uniqueness, gronwall inequality, Lyapunov theory

Procedia PDF Downloads 106

Authors: E. Yazıcı, H. Sundu, E. Veli Veliev

Abstract:

In order to understand the nature of strong interactions and QCD vacuum, investigation of the meson coupling constants have an important role. The knowledge on the temperature dependence of the form factors is very important for the interpretation of heavy-ion collision experiments. Also, more accurate determination of these coupling constants plays a crucial role in understanding of the hadronic decays. With the increasing of CM energies of the experiments, researches on meson interactions have become one of the more interesting problems of hadronic physics. In this study, we analyze the temperature dependence of the strong form factor of the BcBcJ/ψ vertex using the three point QCD sum rules method. Here, we assume that with replacing the vacuum condensates and also the continuum threshold by their thermal version, the sum rules for the observables remain valid. In calculations, we take into account the additional operators, which appear in the Wilson expansion at finite temperature. We also investigated the momentum dependence of the form factor at T = 0, fit it into an analytic function, and extrapolate into the deep time-like region in order to obtain a strong coupling constant of the vertex. Our results are consistent with the results existing in the literature.

Keywords: QCD sum rules, thermal QCD, heavy mesons, strong coupling constants

Procedia PDF Downloads 189

Authors: M. Abir Hossain, M. Shahjada Tarafder

Abstract:

This paper deals with the analysis of potential flow past two-dimensional body by discretizing the body into panels where the Laplace equation was applied to each panel. The Laplace equation was solved at each panel by applying the boundary conditions. The boundary condition was applied at each panel to mathematically formulate the problem and then convert the problem into a computer-solvable problem. Kutta condition was applied at both the leading and trailing edges to see whether the condition is satisfied or not. Another approach that is applied for the analysis is Vortex Lattice Method (VLM). A vortex ring is considered at each control point. Using the Biot-Savart Law the strength at each control point is calculated and hence the pressure differentials are measured. For the comparison of the analytic result with the experimental result, different NACA section hydrofoil is used. The analytic result of NACA 0012 and NACA 0015 are compared with the experimental result of Abbott and Doenhoff and found significant conformity with the achieved result.

Keywords: Kutta condition, Law of Biot-Savart, pressure differentials, potential flow, vortex lattice method

Procedia PDF Downloads 190

Authors: Rahul Paul, Peter Mctaggart, Luke Skinner

Abstract:

Maintaining public safety and network reliability are the core objectives of all electricity distributors globally. For many electricity distributors, managing vegetation clearances from their above ground assets (poles and conductors) is the most important and costly risk mitigation control employed to meet these objectives. Light Detection And Ranging (LiDAR) is widely used by utilities as a cost-effective method to inspect their spatially-distributed assets at scale, often captured using high powered LiDAR scanners attached to fixed wing or rotary aircraft. The resulting 3D point cloud model is used by these utilities to perform engineering grade measurements that guide the prioritisation of vegetation cutting programs. Advances in computer vision and machine-learning approaches are increasingly applied to increase automation and reduce inspection costs and time; however, real-world LiDAR capture variables (e.g., aircraft speed and height) create complexity, noise, and missing data, reducing the effectiveness of these approaches. This paper proposes a method for identifying each conductor from LiDAR data via clustering methods that can precisely reconstruct conductors in complex real-world configurations in the presence of high levels of noise. It proposes 3D catenary models for individual clusters fitted to the captured LiDAR data points using a least square method. An iterative learning process is used to identify potential conductor models between pole pairs. The proposed method identifies the optimum parameters of the catenary function and then fits the LiDAR points to reconstruct the conductors.

Keywords: point cloud, LİDAR data, machine learning, computer vision, catenary curve, vegetation management, utility industry

Procedia PDF Downloads 99

Authors: Rahma Al Maawali, Hameed Sulaiman

Abstract:

Air pollution both from point and non-point sources is difficult to control once released in to the atmosphere. There is no engineering method known available to ameliorate the dispersed pollutants. The only suitable approach is the ecological method of constructing green belts in and around the pollution sources. Air pollution in Muscat, Oman is a serious concern due to ever increasing vehicles on roads. Identifying the air pollution tolerance levels of species is important for implementing pollution control strategies in the urban areas of Muscat. Hence, in the present study, Air Pollution Tolerance Index (APTI) for ten avenue tree species was evaluated by analyzing four bio-chemical parameters, plus their Anticipated Performance Index (API) in field conditions. Based on the two indices, Ficus benghalensis was the most suitable one with the highest performance score. Conocarpus erectuse, Phoenix dactylifera, and Pithcellobium dulce were found to be good performers and are recommended for extensive planting. Azadirachta indica which is preferred for its dense canopy is qualified in the moderate category. The rest of the tree species expressed lower API score of less than 51, hence cannot be considered as suitable species for pollution mitigation plantation projects.

Keywords: air pollution tolerance index (APTI), avenue tree species, bio-chemical parameters, muscat

Procedia PDF Downloads 284

Authors: Alejandro Molina-Villegas, Silvia Fernández-Sabido, Eduardo Mendoza-Vargas, Fátima Miranda-Pestaña

Abstract:

The automatic detection of indigenous languages ​​in digital texts is essential to promote their inclusion in digital media. Underrepresented languages, such as Maya, are often excluded from language detection tools like Google’s language-detection library, LANGDETECT. This study addresses these limitations by developing a hybrid language detection solution that accurately distinguishes Maya (YUA) from Spanish (ES). Two strategies are employed: the first focuses on creating a profile for the Maya language within the LANGDETECT library, while the second involves training a Naive Bayes classification model with two categories, YUA and ES. The process includes comprehensive data preprocessing steps, such as cleaning, normalization, tokenization, and n-gram counting, applied to text samples collected from various sources, including articles from La Jornada Maya, a major newspaper in Mexico and the only media outlet that includes a Maya section. After the training phase, a portion of the data is used to create the YUA profile within LANGDETECT, which achieves an accuracy rate above 95% in identifying the Maya language during testing. Additionally, the Naive Bayes classifier, trained and tested on the same database, achieves an accuracy close to 98% in distinguishing between Maya and Spanish, with further validation through F1 score, recall, and logarithmic scoring, without signs of overfitting. This strategy, which combines the LANGDETECT profile with a Naive Bayes model, highlights an adaptable framework that can be extended to other underrepresented languages in future research. This fills a gap in Natural Language Processing and supports the preservation and revitalization of these languages.

Keywords: indigenous languages, language detection, Maya language, Naive Bayes classifier, natural language processing, low-resource languages

Procedia PDF Downloads 16

Authors: Ksenia Siadkowska, Zbigniew Czyz, Lukasz Grabowski

Abstract:

The paper presents the research results of the construction of an injector with a modified injection nozzle. The injector is designed for a prototype aircraft opposed-piston diesel engine with an assumed starting power of 100 kW. The injector has been subjected to optical tests carried out in a constant volume chamber with the use of a camera allowing to record images at the frequency of 5400 fps and at the resolution of 1024x1024. The measurements were based on a Mie scattering technique with global lighting. Seven repetitions were made for a specific measurement point. The measuring point was selected on the basis of the analysis of engine operating conditions. The analysis focused on the average range of the spray and its distribution. As a result of the conducted research, the range of the fuel spray was defined for the determined parameters of injection. The obtained results were used to verify and optimize the combustion process in the designed opposed-piston two-stroke diesel engine. Acknowledgment: This work has been realized in the cooperation with The Construction Office of WSK 'PZL-KALISZ' S.A.' and is part of Grant Agreement No. POIR.01.02.00-00-0002/15 financed by the Polish National Centre for Research and Development.

Keywords: diesel engine, opposed-piston, aircraft, fuel injector

Procedia PDF Downloads 128

Authors: Constanza A. Barriga, Rafael Bernardi, Amokrane Berdja, Christian D. Guzman

Abstract:

Most image restoration methods in astronomy rely upon probabilistic tools that infer the best solution for a deconvolution problem. They achieve good performances when the point spread function (PSF) is spatially invariable in the image plane. However, this latter condition is not always satisfied with real optical systems. PSF angular variations cannot be evaluated directly from the observations, neither be corrected at a pixel resolution. We have developed a method for the restoration of images affected by static and anisotropic aberrations using deep neural networks that can be directly applied to sky images. The network is trained using simulated sky images corresponding to the T-80 telescope optical system, an 80 cm survey imager at Cerro Tololo (Chile), which are synthesized using a Zernike polynomial representation of the optical system. Once trained, the network can be used directly on sky images, outputting a corrected version of the image, which has a constant and known PSF across its field-of-view. The method was tested with the T-80 telescope, achieving better results than with PSF deconvolution techniques. We present the method and results on this telescope.

Keywords: aberrations, deep neural networks, image restoration, variable point spread function, wide field images

Procedia PDF Downloads 134

Authors: Daniel C. Bonzo

Abstract:

Practical considerations lead to the use of unit of analysis within subjects, e.g., bleeding episodes or treatment-related adverse events, in rare disease settings. This is coupled with data augmentation techniques such as extrapolation to enlarge the subject base. In general, one can think about extrapolation of data as extending information and conclusions from one estimand to another estimand. This approach induces hierarchichal clustered data with varying cluster sizes. Extrapolation of clinical trial data is being accepted increasingly by regulatory agencies as a means of generating data in diverse situations during drug development process. Under certain circumstances, data can be extrapolated to a different population, a different but related indication, and different but similar product. We consider here the problem of estimation (point and interval) using a mixed-models approach under an extrapolation. It is proposed that estimators (point and interval) be constructed using weighting schemes for the clusters, e.g., equally weighted and with weights proportional to cluster size. Simulated data generated under varying scenarios are then used to evaluate the performance of this approach. In conclusion, the evaluation result showed that the approach is a useful means for improving statistical inference in rare disease settings and thus aids not only signal detection but risk-benefit evaluation as well.

Keywords: clustered data, estimand, extrapolation, mixed model

Procedia PDF Downloads 136

Authors: Fatemeh Parhizkar, Mojtaba Yamani, Abdolla Behboodi, Masoomeh Hashemi

Abstract:

The mangrove forests are natural and valuable gifts that exist in some parts of the world, including Iran. Regarding the threats faced by these forests and the declining area of them all over the world, as well as in Iran, it is very necessary to manage and monitor them. The current study aimed to investigate the changes in mangrove forests and the relationship between these changes and the marine hydrodynamics and coastal morphology in the area between qeshm island and the west coast of the Hormozgan province (i.e. the coastline between Mehran river and Bandar-e Pol port) in the 49-year period. After preprocessing and classifying satellite images using the SVM, MLC, and ANN classifiers and evaluating the accuracy of the maps, the SVM approach with the highest accuracy (the Kappa coefficient of 0.97 and overall accuracy of 98) was selected for preparing the classification map of all images. The results indicate that from 1972 to 1987, the area of these forests have had experienced a declining trend, and in the next years, their expansion was initiated. These forests include the mangrove forests of Khurkhuran wetland, Muriz Deraz Estuary, Haft Baram Estuary, the mangrove forest in the south of the Laft Port, and the mangrove forests between the Tabl Pier, Maleki Village, and Gevarzin Village. The marine hydrodynamic and geomorphological characteristics of the region, such as average intertidal zone, sediment data, the freshwater inlet of Mehran river, wave stability and calmness, topography and slope, as well as mangrove conservation projects make the further expansion of mangrove forests in this area possible. By providing significant and up-to-date information on the development and decline of mangrove forests in different parts of the coast, this study can significantly contribute to taking measures for the conservation and restoration of mangrove forests.

Keywords: mangrove forests, marine hydrodynamics, coastal morphology, west of strait of Hormuz, Iran

Procedia PDF Downloads 96

Authors: Hadjer Sadoune, Liza Lamini, Scherazade Krim, Amel Djouadi, Rachida Rihani

Abstract:

Deep neural networks are highly regarded for their accuracy in predicting intricate fermentation processes. Their ability to learn from a large amount of datasets through artificial intelligence makes them particularly effective models. The primary obstacle in improving the performance of these models is to carefully choose the suitable hyperparameters, including the neural network architecture (number of hidden layers and hidden units), activation function, optimizer, learning rate, and other relevant factors. This study predicts biogas production from real wastewater treatment plant data using a sophisticated approach: hybrid Bayesian optimization with a tree-structured Parzen estimator (BO-TPE) for an optimised deep neural network (DNN) model. The plant utilizes an Upflow Anaerobic Sludge Blanket (UASB) digester that treats industrial wastewater from soft drinks and breweries. The digester has a working volume of 1574 m3 and a total volume of 1914 m3. Its internal diameter and height were 19 and 7.14 m, respectively. The data preprocessing was conducted with meticulous attention to preserving data quality while avoiding data reduction. Three normalization techniques were applied to the pre-processed data (MinMaxScaler, RobustScaler and StandardScaler) and compared with the Non-Normalized data. The RobustScaler approach has strong predictive ability for estimating the volume of biogas produced. The highest predicted biogas volume was 2236.105 Nm³/d, with coefficient of determination (R2), mean absolute error (MAE), and root mean square error (RMSE) values of 0.712, 164.610, and 223.429, respectively.

Keywords: anaerobic digestion, biogas production, deep neural network, hybrid bo-tpe, hyperparameters tuning

Procedia PDF Downloads 38

Authors: Leizhang Wang, Baocang Wang

Abstract:

General Sieve Kernel (G6K) is considered as currently the fastest algorithm for the shortest vector problem (SVP) and record holder of open SVP challenge. We study the lattice basis quality improvement effects of the Workout proposed in G6K, which is composed of a series of pumps to solve SVP. Firstly, we use a low-dimensional pump output basis to propose a predictor to predict the quality of high-dimensional Pumps output basis. Both theoretical analysis and experimental tests are performed to illustrate that it is more computationally expensive to solve the LWE problems by using a G6K default SVP solving strategy (Workout) than these lattice reduction algorithms (e.g. BKZ 2.0, Progressive BKZ, Pump, and Jump BKZ) with sieving as their SVP oracle. Secondly, the default Workout in G6K is optimized to achieve a stronger reduction and lower computational cost. Thirdly, we combine the optimized Workout and the Pump output basis quality predictor to further reduce the computational cost by optimizing LWE instances selection strategy. In fact, we can solve the TU LWE challenge (n = 65, q = 4225, = 0:005) 13.6 times faster than the G6K default Workout. Fourthly, we consider a combined two-stage (Preprocessing by BKZ- and a big Pump) LWE solving strategy. Both stages use dimension for free technology to give new theoretical security estimations of several LWE-based cryptographic schemes. The security estimations show that the securities of these schemes with the conservative Newhope’s core-SVP model are somewhat overestimated. In addition, in the case of LAC scheme, LWE instances selection strategy can be optimized to further improve the LWE-solving efficiency even by 15% and 57%. Finally, some experiments are implemented to examine the effects of our strategies on the Normal Form LWE problems, and the results demonstrate that the combined strategy is four times faster than that of Newhope.

Keywords: LWE, G6K, pump estimator, LWE instances selection strategy, dimension for free

Procedia PDF Downloads 60

Authors: Alemi Asefa Wordofa

Abstract:

The textile industry is among the biggest industries in the world, producing a wide variety of products. Industry plays an important role in the world economy as well as in our daily lives. In Ethiopia, this has also been aided by the country’s impressive economic growth over the years. However, Textile industries consume large amounts of water and produce colored wastewater, which results in polluting the environment. In this study, the efficiency of the electrocoagulation treatment process using Iron electrodes to treat textile wastewater containing Reactive black everzol was studied. The effects of parameters such as voltage, time of reaction, and inter-electrode distance on Chemical oxygen demand (COD) and dye removal efficiency were investigated. In addition, electrical energy consumption at optimum conditions has been investigated. The results showed that COD and dye removals were 90.76% and 97.66%, respectively, at the optimum point of input voltage of 14v, inter-electrode distance of 7.24mm, and 47.86min electrolysis time. Energy consumption at the optimum point is also 2.9*10-3. It can be concluded that the electrocoagulation process by the iron electrode is a very efficient and clean process for COD and reactive black removal from wastewater.

Keywords: iron electrode, electrocoagulation, chemical oxygen demand, wastewater

Procedia PDF Downloads 66

Authors: Nkechinyere Joy Olawuyi, Babajide Samuel Afolabi, Bola Ibitoye

Abstract:

This study collected a preprocessed dataset of chest radiographs and formulated a deep neural network model for detecting abnormalities. It also evaluated the performance of the formulated model and implemented a prototype of the formulated model. This was with the view to developing a deep neural network model to automatically classify abnormalities in chest radiographs. In order to achieve the overall purpose of this research, a large set of chest x-ray images were sourced for and collected from the CheXpert dataset, which is an online repository of annotated chest radiographs compiled by the Machine Learning Research Group, Stanford University. The chest radiographs were preprocessed into a format that can be fed into a deep neural network. The preprocessing techniques used were standardization and normalization. The classification problem was formulated as a multi-label binary classification model, which used convolutional neural network architecture to make a decision on whether an abnormality was present or not in the chest radiographs. The classification model was evaluated using specificity, sensitivity, and Area Under Curve (AUC) score as the parameter. A prototype of the classification model was implemented using Keras Open source deep learning framework in Python Programming Language. The AUC ROC curve of the model was able to classify Atelestasis, Support devices, Pleural effusion, Pneumonia, A normal CXR (no finding), Pneumothorax, and Consolidation. However, Lung opacity and Cardiomegaly had a probability of less than 0.5 and thus were classified as absent. Precision, recall, and F1 score values were 0.78; this implies that the number of False Positive and False Negative is the same, revealing some measure of label imbalance in the dataset. The study concluded that the developed model is sufficient to classify abnormalities present in chest radiographs into present or absent.

Keywords: transfer learning, convolutional neural network, radiograph, classification, multi-label

Procedia PDF Downloads 129

Authors: Moise Alin Ionuț Cornel

Abstract:

In a pilot lesson of prevention of consumption drugs in a classroom of teenager`s where the school want them to know how to manage their thoughts and emotions to protect themself an to be strong in an possible environment of drugs consumption. At this classroom was applied the RAIN(Recognize, Accept, Investigation,Non-identify) spiritual method and the balance model from positive and transcultural psychotherapy (PPT) in a manner of a game play for them to understand the methods in an individual experience. The balance model from PPT with his 4 parts and used in 3 ways, and the RAIN spiritual method was used to see how the teenager`s can bring clarity about theirs individual self and how they spend the time and energy in the daily life. The 3 ways of how they can used this model was explained like a analogy with the 3 periods of the SAKURA (Japanese cherry) flourish (kaika, mankai and chiru). The teenager`s received a new perspective and in the same time new tools from the spiritual point of view combined with the psychotherapeutic point of view to manage their thoughts, emotions, time and energy in the form of a psychoeducational game to be able to prevent the use of drugs.

Keywords: addiction, drugs consumption prevention education, psychotherapy, Self, Spirituality, teenagers

Procedia PDF Downloads 70

Authors: S. Pramanik

Abstract:

Since the early ages, the Hindu temples have been interpreted through various Vedic philosophies. These temples are visited by pilgrims which demonstrate the rituals and religious belief of communities, reflecting a variety of actions and behaviors. Darsana— a direct seeing, is a part of the pilgrimage activity. During the process of Darsana, a devotee is prepared for entry in the temple to realize the cognizing Truth culminating in visualizing the idol of God, placed at the Garbhagriha (sanctum sanctorum). For this, the pilgrim must pass through a sequential arrangement of spaces. During the process of progress, the pilgrims visualize the spaces differently from various points of views. The viewpoints create a variety of spatial patterns in the minds of pilgrims coherent to the Hindu philosophies. The space organization and its order are perceived by various techniques of spatial analysis. A temple, as examples of Kalinga stylistic variations, has been chosen for the study. This paper intends to demonstrate some visual patterns generated during the process of Darsana (visibility) and its accessibility by Point Isovist Studies and Visibility Graph Analysis from the entrance (Simha Dwara) to The Sanctum sanctorum (Garbhagriha).

Keywords: Hindu temple architecture, point isovist, space syntax analysis, visibility graph analysis

Procedia PDF Downloads 120

Authors: Barry D. Kyle, Jessica Boyd, Robin Pickersgill, Nicole Squires, Cynthia Balion

Abstract:

Background-Aim: Fentanyl is a highly-potent synthetic μ-opioid receptor agonist used for exceptional pain management. Its main metabolite, norfentanyl, is typically present in urine at significantly high concentrations (i.e. ~20%) representing an effective targeting molecule for immunoassay detection. Here, we evaluated the NCS^TM One Step Fentanyl Test Device© and the BTNX Rapid Response^TM Single Drug Test Strip© point of care (POC) test strips targeting norfentanyl (20 ng/ml) and fentanyl (100 ng/ml) molecules for potential risperidone interference. Methods: POC tests calibrated against norfentanyl (20 ng/ml) used [immunochromatographic] lateral flow devices to provide qualitative results within five minutes of urine sample contact. Results were recorded as negative if lines appeared in the test and control regions according to manufacturer’s instructions. Positive results were recorded if no line appeared in the test region (i.e., control line only visible). Pooled patient urine (n=20), that screened negative for drugs of abuse (using NCS One Step Multi-Line Screen) and fentanyl (using BTNX Rapid Response Strip) was used for spiking studies. Urine was spiked with risperidone alone and with combinations of fentanyl, norfentanyl and/or risperidone to evaluate cross-reactivity in each test device. Results: A positive screen result was obtained when 8,000 ng/mL of risperidone was spiked into drug free urine using the NCS test device. Positive screen results were also obtained in spiked urine samples containing fentanyl and norfentanyl combinations below the cut-off concentrations when 4000 ng/mL risperidone was present using the NCS testing device. There were no screen positive test results using the BTNX test strip with up to 8,000 ng/mL alone or in combination with concentrations of fentanyl and norfentanyl below the cut-off. Both devices screened positive when either fentanyl or norfentanyl exceeded the cut-off threshold in the absence and presence of risperidone. Conclusion: We report that urine samples containing risperidone may give a false positive result using the NCS One Step Fentanyl Test Device.

Keywords: fentanyl, interferences, point of care test, Risperidone

Procedia PDF Downloads 274

Authors: Sharif Muddsair, Eisels Martin, Giesbrecht Eugenie

Abstract:

With development of society increase the demand for the movement of people also increases gradually. The various modes of the transport in different extent which expat impacts, which depends on mainly technical-operating conditions. The up-to-date telematics systems provide the transport industry a revolutionary. Appropriate use of these systems can help to substantially improve the efficiency. Vehicle monitoring and fleet tracking are among services used for improving efficiency and effectiveness of utility vehicle. There are many telematics systems which may contribute to eco-driving. Generally, they can be grouped according to their role in driving cycle. • Before driving - eco-route selection, • While driving – Advanced driver assistance, • After driving – remote analysis. Our point of interest is regulated in third point [after driving – remote analysis]. TS [Telematics-system] make it possible to record driving patterns in real time and analysis the data later on, So that driver- classification-specific hints [fast driver, slow driver, aggressive driver…)] are given to imitate eco-friendly driving style. Together with growing number of vehicle and development of information technology, telematics become an ‘active’ research subject in IT and the car industry. Telematics has gone a long way from providing navigation solution/assisting the driver to become an integral part of the vehicle. Today’s telematics ensure safety, comfort and become convenience of the driver.

Keywords: internet of things, iot, connected vehicle, cv, ts, telematics services, ml, machine learning

Procedia PDF Downloads 306

Authors: Ma Cecilia Siva

Abstract:

This study introduces a Bidirectional Encoder Representations from Transformers (BERT)-based machine learning model aimed at improving educational counseling by automating the process of recommending academic strands for students. The framework is designed to streamline and enhance the strand selection process by analyzing students' profiles and suggesting suitable academic paths based on their interests, strengths, and goals. Data was gathered from a sample of 200 grade 10 students, which included personal essays and survey responses relevant to strand alignment. After thorough preprocessing, the text data was tokenized, label-encoded, and input into a fine-tuned BERT model set up for multi-label classification. The model was optimized for balanced accuracy and computational efficiency, featuring a multi-category classification layer with sigmoid activation for independent strand predictions. Performance metrics showed an F1 score of 88%, indicating a well-balanced model with precision at 80% and recall at 100%, demonstrating its effectiveness in providing reliable recommendations while reducing irrelevant strand suggestions. To facilitate practical use, the final deployment phase created a recommendation framework that processes new student data through the trained model and generates personalized academic strand suggestions. This automated recommendation system presents a scalable solution for academic guidance, potentially enhancing student satisfaction and alignment with educational objectives. The study's findings indicate that expanding the data set, integrating additional features, and refining the model iteratively could improve the framework's accuracy and broaden its applicability in various educational contexts.

Keywords: tokenized, sigmoid activation, transformer, multi category classification

Procedia PDF Downloads 9

Authors: Katarzyna Niewiadomska

Abstract:

Many technology startups fail to achieve a worthwhile return on investment for their funders, founders, and employees. Failures in product development, to-market strategy, sales, and delivery are commonly recognized. Founder failures are not as obvious and harder to identify. This paper explores six critical failure points that entrepreneurs and innovators are susceptible to and aims to link their emotional intelligence and behavioral profile to the points at which they experienced self-perceived failure. A model of six failure points from the perspective of the technology entrepreneur ranging from pre-startup to maturity is provided. By analyzing emotional and behavioral profile data from entrepreneurs and recording in-person accounts, certain key emotional and behavioral clusters contributing to each failure point are determined, and several underlying factors are defined and discussed. Recommendations that support entrepreneurs and innovators stalling at each failure point are given. This work can enable stakeholders to evaluate founder emotional and behavioral profiles and to take risk-mitigating action, either through coaching or through more robust team creation, to avoid founder-related company failure. The paper will be of interest to investors funding startups, executives leading them and mentors supporting them.

Keywords: behavior, emotional intelligence, entrepreneur, failure

Procedia PDF Downloads 229

Authors: Kehabtimer Shiferaw Kotiso, Getachew Hailemariam, Abiy Seifu Estifanos

Abstract:

Introduction: Despite the highest share of low birth weight (LBW) for neonatal mortality and morbidity, predicting births with LBW for better intervention preparation is challenging. This study aims to predict LBW using a dataset encompassing 53,637 birth cohorts collected from 36 primary hospitals across seven regions in Ethiopia from February 2022 to June 2024. Methods: We identified ten explanatory variables related to maternal and neonatal characteristics, including maternal education, age, residence, history of miscarriage or abortion, history of preterm birth, type of pregnancy, number of livebirths, number of stillbirths, antenatal care frequency, and sex of the fetus to predict LBW. Using WEKA 3.8.2, we developed and compared seven machine learning algorithms. Data preprocessing included handling missing values, outlier detection, and ensuring data integrity in birth weight records. Model performance was evaluated through metrics such as accuracy, precision, recall, F1-score, and area under the Receiver Operating Characteristic curve (ROC AUC) using 10-fold cross-validation. Results: The results demonstrated that the decision tree, J48, logistic regression, and gradient boosted trees model achieved the highest accuracy (94.5% to 94.6%) with a precision of 93.1% to 93.3%, F1-score of 92.7% to 93.1%, and ROC AUC of 71.8% to 76.6%. Conclusion: This study demonstrates the effectiveness of machine learning models in predicting LBW. The high accuracy and recall rates achieved indicate that these models can serve as valuable tools for healthcare policymakers and providers in identifying at-risk newborns and implementing timely interventions to achieve the sustainable developmental goal (SDG) related to neonatal mortality.

Keywords: low birth weight, machine learning, classification, neonatal mortality, Ethiopia

Procedia PDF Downloads 22

Authors: Emmy Pratiwi, Ketut B. Artana, A. A. B. Dinariyana

Abstract:

Madura Strait is considered as one of the busiest shipping channels in Indonesia. High vessel traffic density in Madura Strait gives serious threat due to navigational safety in this area, i.e. ship collision. This study is necessary as an attempt to enhance the safety of marine traffic. Fuzzy inference system (FIS) is proposed to calculate risk collision of ships. Collision risk is evaluated based on ship domain, Distance to Closest Point of Approach (DCPA), and Time to Closest Point of Approach (TCPA). Data were collected by utilizing Automatic Identification System (AIS). This study considers several ships’ domain models to give the characteristic of marine traffic in the waterways. Each encounter in the ship domain is analyzed to obtain the level of collision risk. Risk level of ships, as the result in this study, can be used as guidance to avoid the accident, providing brief description about safety traffic in Madura Strait and improving the navigational safety in the area.

Keywords: automatic identification system, collision risk, DCPA, fuzzy inference system, TCPA

Procedia PDF Downloads 550

Authors: Reyhan Tekin Sitrava

Abstract:

Teachers should have robust and comprehensive content knowledge for effective mathematics teaching. It was explained that content knowledge includes knowing the facts, truths, and concepts; explaining the reasons behind these facts, truths and concepts, and making relationship between the concepts and other disciplines. By virtue of its importance, it will be significant to explore teachers and prospective teachers’ content knowledge related to variety of topics in mathematics. From this point of view, the purpose of this study was to investigate prospective mathematics teachers’ content knowledge. Particularly, it was aimed to reveal the prospective teachers’ knowledge regarding the definition of limit and derivate. To achieve the purpose and to get in-depth understanding, a qualitative case study method was used. The data was collected from 34 prospective mathematics teachers through a questionnaire containing 2 questions. The first question required the prospective teachers to define the limit and the second one required to define the derivative. The data was analyzed using content analysis method. Based on the analysis of the data, although half of the prospective teachers (50%) could write the definition of the limit, nine prospective teachers (26.5%) could not define limit. However, eight prospective teachers’ definition was regarded as partially correct. On the other hand, twenty-seven prospective teachers (79.5%) could define derivative, but seven of them (20.5%) defined it partially. According to the findings, most of the prospective teachers have robust content knowledge on limit and derivative. This result is important because definitions have a virtual role in learning and teaching of mathematics. More specifically, definition is starting point to understand the meaning of a concept. From this point of view, prospective teachers should know the definitions of the concepts to be able to teach them correctly to the students. In addition, they should have knowledge about the relationship between limit and derivative so that they can explain these concepts conceptually. Otherwise, students may memorize the rules of calculating the derivative and the limit. In conclusion, the present study showed that most of the prospective mathematics teachers had enough knowledge about the definition of derivative and limit. However, the rest of them should learn their definition conceptually. The examples of correct, partially correct, and incorrect definition of both concepts will be presented and discussed based on participants’ statements. This study has some implications for instructors. Instructors should be careful about whether students learn the definition of these concepts or not. In order to this, the instructors may give prospective teachers opportunities to discuss the definition of these concepts and the relationship between the concepts.

Keywords: content knowledge, derivative, limit, prospective mathematics teachers

Procedia PDF Downloads 221

Authors: Mansour N. Jadid

Abstract:

This paper describes the implementation of a GIS to provide decision support for successfully monitoring the movements and storage of materials, hence ensuring that finished products travel from the point of origin to the destination construction site through the supply-chain management (SCM) system. This system ensures the efficient operation of suppliers, manufacturers, and distributors by determining the shortest path from the point of origin to the final destination to reduce construction costs, minimize time, and enhance productivity. These systems are essential to the construction industry because they reduce costs and save time, thereby improve productivity and effectiveness. This study describes a typical supply-chain model and a geographical information system (GIS)-based SCM that focuses on implementing an electronic document management system, which maps the application framework to integrate geodetic support with the supply-chain system. This process provides guidance for locating the nearest suppliers to fill the information needs of project members in different locations. Moreover, this study illustrates the use of a GIS-based SCM as a collaborative tool in innovative methods for implementing Web mapping services, as well as aspects of their integration by generating an interactive GIS for the construction industry platform.

Keywords: construction, coordinate, engineering, GIS, management, map

Procedia PDF Downloads 303

Authors: Ali M. Babalghaith, Hamad A. Alsoliman, Abdulrahman S. Al-Suhaibani

Abstract:

Flexible pavement made with neat asphalt binder is not enough to resist heavy traffic loads as well as harsh environmental condition found in Riyadh region. Therefore, there is a need to modify asphalt binder with polymers to satisfy such conditions. There are several types of polymers that are used to modify asphalt binder. The objective of this paper is to compare the rheological properties of six polymer modified asphalt binders (Lucolast7010, Anglomak2144, Paveflex140, SBS KTR401, EE-2 and Crumb rubber) obtained from asphalt manufacturer plants. The rheological properties of polymer modified asphalt binders were tested using conventional tests such as penetration, softening point and viscosity; and SHRP tests such as dynamic shear rheometer and bending beam rheometer. The results have indicated that the polymer modified asphalt binders have lower penetration and higher softening point than neat asphalt indicating an improvement in stiffness of asphalt binder, and as a result, more resistant to rutting. Moreover, the dynamic shear rheometer results have shown that all modifiers used in this study improved the binder properties and satisfied the Superpave specifications except SBS KTR401 which failed to satisfy the rutting parameter (G*/sinδ).

Keywords: polymer modified asphalt, rheological properties, SBS, crumb rubber, EE-2

Procedia PDF Downloads 290