Search results for: gradient boosting machine

Authors: Md. Armin Islam, Les Dallin, Mark Boland, W. J. Zhang

Abstract:

This paper reports a study on the optimal magnetic design of a compact quadrupole electromagnet for the Canadian Light Source (CLS 2.0). The nature of the design is to determine a quadrupole with low relative higher order harmonics and better field quality. The design problem was formulated as an optimization model, in which the objective function is the higher order harmonics (multipole errors) and the variable to be optimized is the material distribution on the pole. The higher order harmonics arose in the quadrupole due to truncating the ideal hyperbola at a certain point to make the pole. In this project, the arisen harmonics have been optimized both transversely and longitudinally by adjusting material on the poles in a controlled way. For optimization, finite element analysis (FEA) has been conducted. A better higher order harmonics amplitudes and field quality have been achieved through the optimization. On the basis of the optimized magnetic design, electrical and cooling calculation has been performed for the magnet.

Keywords: drift, electrical, and cooling calculation, integrated field, magnetic field gradient, multipole errors, quadrupole

Procedia PDF Downloads 142

Authors: Babak Forouraghi

Abstract:

A genetic circuit is a collection of interacting genes and proteins that enable individual cells to implement and perform vital biological functions such as cell division, growth, death, and signaling. In cell engineering, synthetic gene circuits are engineered networks of genes specifically designed to implement functionalities that are not evolved by nature. These engineered networks enable scientists to tackle complex problems such as engineering cells to produce therapeutics within the patient's body, altering T cells to target cancer-related antigens for treatment, improving antibody production using engineered cells, tissue engineering, and production of genetically modified plants and livestock. Construction of computational models to realize genetic circuits is an especially challenging task since it requires the discovery of flow of genetic information in complex biological systems. Building synthetic biological models is also a time-consuming process with relatively low prediction accuracy for highly complex genetic circuits. The primary goal of this study was to investigate the utility of a pre-trained bidirectional encoder transformer that can accurately predict gene expressions in genetic circuit designs. The main reason behind using transformers is their innate ability (attention mechanism) to take account of the semantic context present in long DNA chains that are heavily dependent on spatial representation of their constituent genes. Previous approaches to gene circuit design, such as CNN and RNN architectures, are unable to capture semantic dependencies in long contexts as required in most real-world applications of synthetic biology. For instance, RNN models (LSTM, GRU), although able to learn long-term dependencies, greatly suffer from vanishing gradient and low-efficiency problem when they sequentially process past states and compresses contextual information into a bottleneck with long input sequences. In other words, these architectures are not equipped with the necessary attention mechanisms to follow a long chain of genes with thousands of tokens. To address the above-mentioned limitations of previous approaches, a transformer model was built in this work as a variation to the existing DNA Bidirectional Encoder Representations from Transformers (DNABERT) model. It is shown that the proposed transformer is capable of capturing contextual information from long input sequences with attention mechanism. In a previous work on genetic circuit design, the traditional approaches to classification and regression, such as Random Forrest, Support Vector Machine, and Artificial Neural Networks, were able to achieve reasonably high R2 accuracy levels of 0.95 to 0.97. However, the transformer model utilized in this work with its attention-based mechanism, was able to achieve a perfect accuracy level of 100%. Further, it is demonstrated that the efficiency of the transformer-based gene expression classifier is not dependent on presence of large amounts of training examples, which may be difficult to compile in many real-world gene circuit designs.

Keywords: transformers, generative ai, gene expression design, classification

Procedia PDF Downloads 59

Authors: Shun-Tong Chen, Wei-Ping Huang, Hong-Ye Yang, Ming-Chieh Yeh, Chih-Wei Du

Abstract:

This study presents a novel versatile high-precision integrated micromachining system that combines contact and non-contact micromachining techniques to machine intricate micro-parts precisely. Two broad methods of micro fabrication-1) volume additive (micro co-deposition), and 2) volume subtractive (nanometric flycutting, ultrafine w-EDM (wire Electrical Discharge Machining), and micro honing) - are integrated in the developed micromachining system, and their effectiveness is verified. A multidirectional headstock that supports various machining orientations is designed to evaluate the feasibility of multifunctional micromachining. An exchangeable working-tank that allows for various machining mechanisms is also incorporated into the system. Hence, the micro tool and workpiece need not be unloaded or repositioned until all the planned tasks have been completed. By using the designed servo rotary mechanism, a nanometric flycutting approach with a concentric rotary accuracy of 5-nm is constructed and utilized with the system to machine a diffraction-grating element with a nano-metric scale V-groove array. To improve the wear resistance of the micro tool, the micro co-deposition function is used to provide a micro-abrasive coating by an electrochemical method. The construction of ultrafine w-EDM facilitates the fabrication of micro slots with a width of less than 20-µm on a hardened tool. The hardened tool can thus be employed as a micro honing-tool to hone a micro hole with an internal diameter of 200 µm on SKD-11 molded steel. Experimental results prove that intricate micro-parts can be in-situ manufactured with high-precision by the developed integrated micromachining system.

Keywords: integrated micromachining system, in-situ micromachining, nanometric flycutting, ultrafine w-EDM, micro honing

Procedia PDF Downloads 409

Authors: Hamed A. Keykha, Hadi Miri

Abstract:

This paper describes a new method of soil stabilisation, electro-biogrouting (EBM), for improvement of soft soil with low hydraulic conductivity. This method uses an applied voltage gradient across the soil to induce the ions and bacteria cells through the soil matrix, resulting in CaCO3 precipitation and an increase of the soil shear strength in the process. The EBM were used effectively with two injection methods; bacteria injection and products of bacteria injection. The bacteria cells, calcium ions and urea were moved across the soil by electromigration and electro osmotic flow respectively. The products of bacteria (CO3-2) were moved by electromigration. The results showed that the undrained shear strength of the soil increased from 6 to 65 and 70 kPa for first and second injection method respectively. The injection of carbonate solution and calcium could be effectively flowed in the clay soil compare to injection of bacteria cells. The detection of CaCO3 percentage and its corresponding water content across the specimen showed that the increase of undrained shear strength relates to the deposit of calcite crystals between soil particles.

Keywords: Sporosarcina pasteurii, electrophoresis, electromigration, electroosmosis, biocement

Procedia PDF Downloads 526

Authors: Kwaku Damoah

Abstract:

The agricultural sector is characterized by continuous transformation, driven by factors such as demographic shifts, evolving consumer preferences, climate change, and migration trends. This dynamic environment presents complex challenges for key stakeholders including farmers, governments, and investors, who must navigate these changes to achieve optimal investment returns. To effectively predict market trends and uncover promising investment opportunities, a systematic, data-driven approach is essential. This paper introduces the Structural Evolution Index (SEI), a machine learning-based methodology. SEI is specifically designed to analyse long-term trends and forecast the potential of emerging agricultural products for investment. Versatile in application, it evaluates various agricultural metrics such as production, yield, trade, land use, and consumption, providing a comprehensive view of the evolution within agricultural markets. By harnessing data from the UN Food and Agricultural Organisation (FAOSTAT), this study demonstrates the SEI's capabilities through Comparative Exploratory Analysis and evaluation of international trade in agricultural products, focusing on Malaysia and Singapore. The SEI methodology reveals intricate patterns and transitions within the agricultural sector, enabling stakeholders to strategically identify and capitalize on emerging markets. This predictive framework is a powerful tool for decision-makers, offering crucial insights that help anticipate market shifts and align investments with anticipated returns.

Keywords: agricultural investment, algorithm, comparative exploratory analytics, machine learning, market trends, predictive analytics, structural evolution index

Procedia PDF Downloads 61

Authors: Pierce Radecki, Pulkit Malik, Bharath Ramaswamy, Ben Shapiro

Abstract:

The ability to effectively design and test magnetic nanoparticles for controlled movement has been an elusive goal in the design of these particles. Magnetic nanoparticles of various characteristics have been created for use towards therapeutic effects, however the challenge of designing for controlled movement remains unmet. A step towards design in this aspect is a first principles model that captures and predicts the behaviors of particles in a magnetic field. The model is governed by four forces acting on the particles, the magnetic gradient, the dipole-dipole forces, the steric forces, and the viscous drag force. The particles are multi-core or single core, and incorporate a preferred magnetization axis. Particles exhibit behaviors, such as chaining, in simulations that are similar to those witnessed through experimentation. Currently, experimental results are being compared to the modeling results for verification of the model, through the analysis of chaining behaviors. This modeling system will be used in designing magnetic nanoparticles for specific chaining and movement behaviors.

Keywords: controlled movement, modeling, magnetic nanoparticles, nanoparticle design

Procedia PDF Downloads 303

Authors: Xingyu Gao, Qiang Wu

Abstract:

Patents play a crucial role in protecting innovation and intellectual property. Early prediction of the impact of artificial intelligence (AI) patents helps researchers and companies allocate resources and make better decisions. Understanding the key factors that influence patent impact can assist researchers in gaining a better understanding of the evolution of AI technology and innovation trends. Therefore, identifying highly impactful patents early and providing support for them holds immeasurable value in accelerating technological progress, reducing research and development costs, and mitigating market positioning risks. Despite the extensive research on AI patents, accurately predicting their early impact remains a challenge. Traditional methods often consider only single factors or simple combinations, failing to comprehensively and accurately reflect the actual impact of patents. This paper utilized the artificial intelligence patent database from the United States Patent and Trademark Office and the Len.org patent retrieval platform to obtain specific information on 35,708 AI patents. Using six machine learning models, namely Multiple Linear Regression, Random Forest Regression, XGBoost Regression, LightGBM Regression, Support Vector Machine Regression, and K-Nearest Neighbors Regression, and using early indicators of patents as features, the paper comprehensively predicted the impact of patents from three aspects: technical, social, and economic. These aspects include the technical leadership of patents, the number of citations they receive, and their shared value. The SHAP (Shapley Additive exPlanations) metric was used to explain the predictions of the best model, quantifying the contribution of each feature to the model's predictions. The experimental results on the AI patent dataset indicate that, for all three target variables, LightGBM regression shows the best predictive performance. Specifically, patent novelty has the greatest impact on predicting the technical impact of patents and has a positive effect. Additionally, the number of owners, the number of backward citations, and the number of independent claims are all crucial and have a positive influence on predicting technical impact. In predicting the social impact of patents, the number of applicants is considered the most critical input variable, but it has a negative impact on social impact. At the same time, the number of independent claims, the number of owners, and the number of backward citations are also important predictive factors, and they have a positive effect on social impact. For predicting the economic impact of patents, the number of independent claims is considered the most important factor and has a positive impact on economic impact. The number of owners, the number of sibling countries or regions, and the size of the extended patent family also have a positive influence on economic impact. The study primarily relies on data from the United States Patent and Trademark Office for artificial intelligence patents. Future research could consider more comprehensive data sources, including artificial intelligence patent data, from a global perspective. While the study takes into account various factors, there may still be other important features not considered. In the future, factors such as patent implementation and market applications may be considered as they could have an impact on the influence of patents.

Keywords: patent influence, interpretable machine learning, predictive models, SHAP

Procedia PDF Downloads 47

Authors: Gizem Eser Erdek

Abstract:

This study is research on predicting the remaining life of industrial cutting tools used in the industrial production process with deep learning methods. When the life of cutting tools decreases, they cause destruction to the raw material they are processing. This study it is aimed to predict the remaining life of the cutting tool based on the damage caused by the cutting tools to the raw material. For this, hole photos were collected from the hole-drilling machine for 8 months. Photos were labeled in 5 classes according to hole quality. In this way, the problem was transformed into a classification problem. Using the prepared data set, a model was created with convolutional neural networks, which is a deep learning method. In addition, VGGNet and ResNet architectures, which have been successful in the literature, have been tested on the data set. A hybrid model using convolutional neural networks and support vector machines is also used for comparison. When all models are compared, it has been determined that the model in which convolutional neural networks are used gives successful results of a %74 accuracy rate. In the preliminary studies, the data set was arranged to include only the best and worst classes, and the study gave ~93% accuracy when the binary classification model was applied. The results of this study showed that the remaining life of the cutting tools could be predicted by deep learning methods based on the damage to the raw material. Experiments have proven that deep learning methods can be used as an alternative for cutting tool life estimation.

Keywords: classification, convolutional neural network, deep learning, remaining life of industrial cutting tools, ResNet, support vector machine, VggNet

Procedia PDF Downloads 75

Authors: C. Fernandez-Plaza, I. Abad, E. Diaz, I. Diaz

Abstract:

Births occurring before the 37th week of gestation are considered preterm births. A threat of preterm is defined as the beginning of regular uterine contractions, dilation and cervical effacement between 23 and 36 gestation weeks. To author's best knowledge, the factors that determine the beginning of the birth are not completely defined yet. In particular, the incidence of sleep habits on preterm births is weekly studied. The aim of this study is to develop a model to predict the factors affecting premature delivery on pregnancy, based on the above potential risk factors, including those derived from sleep habits and light exposure at night (introduced as 12 variables obtained by a telephone survey using two questionnaires previously used by other authors). Thus, three groups of variables were included in the study (maternal, fetal and sleep habits). The study was approved by Research Ethics Committee of the Principado of Asturias (Spain). An observational, retrospective and descriptive study was performed with 481 births between January 1, 2015 and May 10, 2016 in the University Central Hospital of Asturias (Spain). A statistical analysis using SPSS was carried out to compare qualitative and quantitative variables between preterm and term delivery. Chi-square test qualitative variable and t-test for quantitative variables were applied. Statistically significant differences (p < 0.05) between preterm vs. term births were found for primiparity, multi-parity, kind of conception, place of residence or premature rupture of membranes and interruption during nights. In addition to the statistical analysis, machine learning methods to look for a prediction model were tested. In particular, tree based models were applied as the trade-off between performance and interpretability is especially suitable for this study. C5.0, recursive partitioning, random forest and tree bag models were analysed using caret R-package. Cross validation with 10-folds and parameter tuning to optimize the methods were applied. In addition, different noise reduction methods were applied to the initial data using NoiseFiltersR package. The best performance was obtained by C5.0 method with Accuracy 0.91, Sensitivity 0.93, Specificity 0.89 and Precision 0.91. Some well known preterm birth factors were identified: Cervix Dilation, maternal BMI, Premature rupture of membranes or nuchal translucency analysis in the first trimester. The model also identifies other new factors related to sleep habits such as light through window, bedtime on working days, usage of electronic devices before sleeping from Mondays to Fridays or change of sleeping habits reflected in the number of hours, in the depth of sleep or in the lighting of the room. IF dilation < = 2.95 AND usage of electronic devices before sleeping from Mondays to Friday = YES and change of sleeping habits = YES, then preterm is one of the predicting rules obtained by C5.0. In this work a model for predicting preterm births is developed. It is based on machine learning together with noise reduction techniques. The method maximizing the performance is the one selected. This model shows the influence of variables related to sleep habits in preterm prediction.

Keywords: machine learning, noise reduction, preterm birth, sleep habit

Procedia PDF Downloads 145

Authors: Prachi Sharma, Mukesh Kumar Rana

Abstract:

In the present study, the simple sequence repeat(SSR) markers have been used in analysis of genetic diversity of 37 genotypes of Triticum aestivum. The DNA was extracted using cTAB method. The DNA was quantified using the fluorimeter. The annealing temperatures for 27 primer pairs were standardized using gradient PCR, out of which 16 primers gave satisfactory amplification at temperature ranging from 50-62⁰ C. Out of 16 polymorphic SSR markers only 10 SSR primer pairs were used in the study generating 34 reproducible amplicons among 37 genotypes out of which 30 were polymorphic. Primer pairs Xgwm533, Xgwm 160, Xgwm 408, Xgwm 120, Xgwm 186, Xgwm 261 produced maximum percent of polymorphic bands (100%). The bands ranged on an average of 3.4 bands per primer. The genetic relationship was determined using Jaccard pair wise similarity co-efficient and UPGMA cluster analysis with NTSYS Pc.2 software. The values of similarity index range from 0-1. The similarity coefficient ranged from 0.13 to 0.97. A minimum genetic similarity (0.13) was observed between VL 804 and HPW 288, meaning they are only 13% similar. More number of available SSR markers can be useful for supporting the genetic diversity analysis in the above wheat genotypes.

Keywords: wheat, genetic diversity, microsatellite, polymorphism

Procedia PDF Downloads 607

Authors: D. P. Lawrence, T. M. M. D. Ariyarathna, W. N. K. De Silva, M. D. S. C. De Silva, Lasantha Abeysiri, Pradeep Abeygunawardhna

Abstract:

Safari traveling is one of the most famous hobbies all over the world. In Sri Lanka, 'Yala' is the second-largest national park, which is a better place to go for a safari. Many number of local and foreign travelers are coming to go for a safari in 'Yala'. But 'Yala' does not have a mobile application that is made to facilitate the traveler with some important features that the traveler wants to achieve in the safari experience. To overcome these difficulties, the proposed mobile application by adding those identified features to make travelers, guiders, and administration's works easier. The proposed safari traveling guidance mobile application is called 'SMART SAFARI' for the 'Yala' National Park in Sri Lanka. There are four facilities in this mobile application that provide for travelers as well as the guiders. As the first facility, the guider and traveler can view the created map of the park, and the guider can add temporary locations of animals and special locations on the map. This is a Geographic Information System (GIS) to capture, analyze, and display geographical data. And as the second facility is to generate optimal paths according to the travelers' requirements through the park by using machine learning techniques. In the third part, the traveler can get information about animals using an animal identification system by capturing the animal. As in the other facility, the traveler will be facilitated to add reviews and a rate and view those comments under categorized sections and pre-defined score range. With those facilities, this user-friendly mobile application provides the user to get a better experience in safari traveling, and it will probably help to develop tourism culture in Sri Lanka.

Keywords: animal identification system, geographic information system, machine learning techniques, pre defined score range

Procedia PDF Downloads 131

Authors: Jinn-Jong Sheu, Cang-Fu Liang, Cheng-Hsien Yu

Abstract:

This paper proposed the cold roll forming process and the die design methods for a 400mm by 400 mm square tube with 16 mm in thickness. The tubular blank made by cold roll forming is 508mm in diameter. The square tube roll forming process was designed considering the layout of rolls and the compression ratio distribution for each stand. The final tube corner radius and the edge straightness in the front end of the tube are to be controlled according to the tube specification. A five-stand forming design using four rolls at each stand was proposed to establish the base reference of square tube roll forming quality. Different numbers of pass and roll designs were proposed and compared to the base design in order to find the feasibility of increase pass number to improve the square tube quality. The proposed roll forming processes were simulated using FEM analysis. The thickness variations of the corner and the edge areas were examined. The maximum loads and the torques of each stand were calculated to study the power consumption of the roll forming machine. The simulation results showed the square tube thickness variations and concavity of the edge are acceptable with the JIS tube specifications for the base design. But the maximum loads and torques are very high. By changing the layout and the number of the rolls were able to obtain better tube geometry and decrease the maximum load and torque of each stand. This paper had shown the feasibility of designing the roll forming process and the layout of dies using FEM simulation. The obtained information is helpful to the roll forming machine design for a large size square tube making.

Keywords: cold roll forming, FEM analysis, roll forming die design, tube roll forming

Procedia PDF Downloads 309

Authors: Po-Ting Chen, Santhanamoorthi Nachimuthu, Jyh-Chiang Jiang

Abstract:

Classical molecular dynamics (CMD) simulations are highly efficient for material simulations but have limited accuracy. In contrast, ab initio molecular dynamics (AIMD) provides high precision by solving the Kohn–Sham equations yet requires significant computational resources, restricting the size of systems and time scales that can be simulated. To address these challenges, we employed NequIP, a machine learning model based on an E(3)-equivariant graph neural network, to accelerate molecular dynamics simulations of a 1M LiPF6 in EC/EMC (v/v 3:7) for Li battery applications. AIMD calculations were initially conducted using the Vienna Ab initio Simulation Package (VASP) to generate highly accurate atomic positions, forces, and energies. This data was then used to train the NequIP model, which efficiently learns from the provided data. NequIP achieved AIMD-level accuracy with significantly less training data. After training, NequIP was integrated into the LAMMPS software to enable molecular dynamics simulations of larger systems over longer time scales. This method overcomes the computational limitations of AIMD while improving the accuracy limitations of CMD, providing an efficient and precise computational framework. This study showcases NequIP’s applicability to electrolyte systems, particularly for simulating the dynamics of LiPF6 ionic mixtures. The results demonstrate substantial improvements in both computational efficiency and simulation accuracy, highlighting the potential of machine learning models to enhance molecular dynamics simulations.

Keywords: lithium-ion batteries, electrolyte simulation, molecular dynamics, neural network

Procedia PDF Downloads 13

Authors: David Robert Irvine

Abstract:

In the dental restoration sector, there has been a shift to using zirconia. With the ever increasing need to decrease lead times to deliver restorations faster the zirconia is machined in its pre-sintered state instead of grinding the very hard sintered state. As with all machining, there is tool wear and while investigating the tooling used to machine pre-sintered zirconia it became apparent that the wear rate is based more on material build up and abrasion than it is on plastic deformation like conventional metal machining. It also came to light that the tool material can currently not be selected based on wear resistance, as there is no data. Different works have analysed the effect of the individual wear mechanism separately using similar if not the same material. In this work, the testing method used to analyse the wear was a modified from ISO 8688:1989 to use the pre-sintered zirconia and the cutting conditions used in dental to machine it. This understanding was developed through a series of tests based in machining operations, to give the best representation of the multiple wear factors that can occur in machining of pre-sintered zirconia such as 3 body abrasion, material build up, surface welding, plastic deformation, tool vibration and thermal cracking. From the testing, it found that carbide grades with low trans-granular rupture toughness would fail due to abrasion while those with high trans-granular rupture toughness failed due to edge chipping from build up or thermal properties. The results gained can assist the development of these tools and the restorative dental process. This work was completed with the aim of assisting in the selection of tool material for future tools along with a deeper understanding of the properties that assist in abrasive wear resistance and material build up.

Keywords: abrasive wear, cemented carbide, pre-sintered zirconia, tool wear

Procedia PDF Downloads 158

Authors: Michaela Chovancova, Jakub Elcner

Abstract:

Real bronchial tree is very complicated piping system. Analysis of flow and pressure losses in this system is very difficult. Due to the complex geometry and the very small size in the lower generations is examination by CFD possible only in the central part of bronchial tree. For specify the pressure losses of lower generations is necessary to provide a mathematical equation. Determination of mathematical formulas for calculating the pressure losses in the real lungs is due to its complexity and diversity lengthy and inefficient process. For these calculations is necessary the lungs to slightly simplify (same cross-section over the length of individual generation) or use one of the models of lungs. The simplification could cause deviations from real values. The article compares the values of pressure losses obtained from CFD simulation of air flow in the central part of the real bronchial tree with the values calculated in a slightly simplified real lungs by using a mathematical relationship derived from the Bernoulli equation and continuity equation. Then, evaluate the desirability of using this formula to determine the pressure loss across the bronchial tree.

Keywords: pressure gradient, airways resistance, real geometry of bronchial tree, breathing

Procedia PDF Downloads 319

Authors: Srinivas Vangari

Abstract:

In the era of big data, ensuring the accuracy, consistency, and reliability of critical data assets is crucial for data-driven enterprises. Master Data Management (MDM) plays a crucial role in this endeavor. This paper investigates the role of Artificial Intelligence (AI) in enhancing MDM, focusing on how AI-driven solutions can automate and optimize various stages of the master data lifecycle. By integrating AI (Quantitative and Qualitative Analysis) into processes such as data creation, maintenance, enrichment, and usage, organizations can achieve significant improvements in data quality and operational efficiency. Quantitative analysis is employed to measure the impact of AI on key metrics, including data accuracy, processing speed, and error reduction. For instance, our study demonstrates an 18% improvement in data accuracy and a 75% reduction in duplicate records across multiple systems post-AI implementation. Furthermore, AI’s predictive maintenance capabilities reduced data obsolescence by 22%, as indicated by statistical analyses of data usage patterns over a 12-month period. Complementing this, a qualitative analysis delves into the specific AI-driven strategies that enhance MDM practices, such as automating data entry and validation, which resulted in a 28% decrease in manual errors. Insights from case studies highlight how AI-driven data cleansing processes reduced inconsistencies by 25% and how AI-powered enrichment strategies improved data relevance by 24%, thus boosting decision-making accuracy. The findings demonstrate that AI significantly enhances data quality and integrity, leading to improved enterprise performance through cost reduction, increased compliance, and more accurate, real-time decision-making. These insights underscore the value of AI as a critical tool in modern data management strategies, offering a competitive edge to organizations that leverage its capabilities.

Keywords: artificial intelligence, master data management, data governance, data quality

Procedia PDF Downloads 16

Authors: Yu-Jia Jian, Emily Chia-Yu Su, Hui-Ling Hsu, Jian-Jhih Chen

Abstract:

Coronary artery is the major supplier of myocardial blood flow. When fat and cholesterol are deposit in the coronary arterial wall, narrowing and stenosis of the artery occurs, which may lead to myocardial ischemia and eventually infarction. According to the World Health Organization (WHO), estimated 740 million people have died of coronary heart disease in 2015. According to Statistics from Ministry of Health and Welfare in Taiwan, heart disease (except for hypertensive diseases) ranked the second among the top 10 causes of death from 2013 to 2016, and it still shows a growing trend. According to American Heart Association (AHA), the risk factors for coronary heart disease including: age (> 65 years), sex (men to women with 2:1 ratio), obesity, diabetes, hypertension, hyperlipidemia, smoking, family history, lack of exercise and more. We have collected a dataset of 421 patients from a hospital located in northern Taiwan who received coronary computed tomography (CT) angiography. There were 300 males (71.26%) and 121 females (28.74%), with age ranging from 24 to 92 years, and a mean age of 56.3 years. Prior to coronary CT angiography, basic data of the patients, including age, gender, obesity index (BMI), diastolic blood pressure, systolic blood pressure, diabetes, hypertension, hyperlipidemia, smoking, family history of coronary heart disease and exercise habits, were collected and used as input variables. The output variable of the prediction module is the degree of coronary artery stenosis. The output variable of the prediction module is the narrow constriction of the coronary artery. In this study, the dataset was randomly divided into 80% as training set and 20% as test set. Four machine learning algorithms, including logistic regression, stepwise regression, neural network and decision tree, were incorporated to generate prediction results. We used area under curve (AUC) / accuracy (Acc.) to compare the four models, the best model is neural network, followed by stepwise logistic regression, decision tree, and logistic regression, with 0.68 / 79 %, 0.68 / 74%, 0.65 / 78%, and 0.65 / 74%, respectively. Sensitivity of neural network was 27.3%, specificity was 90.8%, stepwise Logistic regression sensitivity was 18.2%, specificity was 92.3%, decision tree sensitivity was 13.6%, specificity was 100%, logistic regression sensitivity was 27.3%, specificity 89.2%. From the result of this study, we hope to improve the accuracy by improving the module parameters or other methods in the future and we hope to solve the problem of low sensitivity by adjusting the imbalanced proportion of positive and negative data.

Keywords: decision support, computed tomography, coronary artery, machine learning

Procedia PDF Downloads 226

Authors: Lewis J. Woollin, Robert I. Davidson, Paul Watson, Philip J. Hyde

Abstract:

Introduction: In-vitro testing of arthroplasty materials is of paramount importance when ensuring that they can withstand the performance requirements encountered in-vivo. One common machine used for in-vitro testing is a pin-on-plate tribometer, an early stage screening device that generates data on the wear characteristics of arthroplasty bearing materials. These devices test vertically loaded rotating cylindrical pins acting against reciprocating plates, representing the bearing surfaces. In this study, a pin-on-plate machine has been developed that provides several improvements over current technology, thereby progressing arthroplasty bearing research. Historically, pin-on-plate tribometers have been used to investigate the performance of arthroplasty bearing materials under conditions commonly encountered during a standard gait cycle; nominal operating pressures of 2-6 MPa and an operating frequency of 1 Hz are typical. There has been increased interest in using pin-on-plate machines to test more representative in-vivo conditions, due to the drive to test 'beyond compliance', as well as their testing speed and economic advantages over hip simulators. Current pin-on-plate machines do not accommodate the increased performance requirements associated with more extreme kinematic conditions, therefore a next-generation pin-on-plate tribometer has been developed to bridge the gap between current technology and future research requirements. Methodology: The design was driven by several physiologically relevant requirements. Firstly, an increased loading capacity was essential to replicate the peak pressures that occur in the natural hip joint during running and chair-rising, as well as increasing the understanding of wear rates in obese patients. Secondly, the introduction of mid-cycle load variation was of paramount importance, as this allows for an approximation of the loads present in a gait cycle to be applied and to test the fatigue properties of materials. Finally, the rig must be validated against previous-generation pin-on-plate and arthroplasty wear data. Results: The resulting machine is a twelve station device that is split into three sets of four stations, providing an increased testing capacity compared to most current pin-on-plate tribometers. The loading of the pins is generated using a pneumatic system, which can produce contact pressures of up to 201 MPa on a 3.2 mm² round pin face. This greatly exceeds currently achievable contact pressures in literature and opens new research avenues such as testing rim wear of mal-positioned hip implants. Additionally, the contact pressure of each set can be changed independently of the others, allowing multiple loading conditions to be tested simultaneously. Using pneumatics also allows the applied pressure to be switched ON/OFF mid-cycle, another feature not currently reported elsewhere, which allows for investigation into intermittent loading and material fatigue. The device is currently undergoing a series of validation tests using Ultra-High-Molecular-Weight-Polyethylene pins and 316L Stainless Steel Plates (polished to a Ra < 0.05 µm). The operating pressures will be between 2-6 MPa, operating at 1 Hz, allowing for validation of the machine against results reported previously in the literature. The successful production of this next-generation pin-on-plate tribometer will, following its validation, unlock multiple previously unavailable research avenues.

Keywords: arthroplasty, mechanical design, pin-on-plate, total joint replacement, wear testing

Procedia PDF Downloads 93

Authors: B. Bouadjemi, S. Bentata, T. Lantri, A. Abbad, W. Benstaali, A. Zitouni, S. Cherid

Abstract:

We investigate the electronic structure, magnetic and optical properties of the orthorhombic NdMnO3 through density-functional-theory (DFT) calculations using both generalized gradient approximation GGA and GGA+U approaches, the exchange and correlation effects are taken into account by an orbital independent modified Becke Johnson (MBJ). The predicted band gaps using the MBJ exchange approximation show a significant improvement over previous theoretical work with the common GGA and GGA+U very closer to the experimental results. Band gap dependent optical parameters like dielectric constant, index of refraction, absorption coefficient, reflectivity and conductivity are calculated and analyzed. We find that when using MBJ we have obtained better results for band gap of NdMnO3 than in the case of GGA and GGA+U. The values of band gap founded in this work by MBJ are in a very good agreement with corresponding experimental values compared to other calculations. This comprehensive theoretical study of the optoelectronic properties predicts that this material can be effectively used in optical devices.

Keywords: DFT, optical properties, absorption coefficient, strong correlation, MBJ, orthorhombic NdMnO3, optoelectronic

Procedia PDF Downloads 908

Authors: Shayan Mohajer Hamidi

Abstract:

Federated Learning (FL) has emerged as a promising paradigm for training machine learning models on distributed data without the need for centralized data aggregation. In the realm of wireless communications, FL has the potential to leverage the vast amounts of data generated by wireless devices to improve model performance and enable intelligent applications. However, the fairness aspect of FL in wireless communications remains largely unexplored. This abstract presents an idea for fair federated learning in wireless communications, addressing the challenges of imbalanced data distribution, privacy preservation, and resource allocation. Firstly, the proposed approach aims to tackle the issue of imbalanced data distribution in wireless networks. In typical FL scenarios, the distribution of data across wireless devices can be highly skewed, resulting in unfair model updates. To address this, we propose a weighted aggregation strategy that assigns higher importance to devices with fewer samples during the aggregation process. By incorporating fairness-aware weighting mechanisms, the proposed approach ensures that each participating device's contribution is proportional to its data distribution, thereby mitigating the impact of data imbalance on model performance. Secondly, privacy preservation is a critical concern in federated learning, especially in wireless communications where sensitive user data is involved. The proposed approach incorporates privacy-enhancing techniques, such as differential privacy, to protect user privacy during the model training process. By adding carefully calibrated noise to the gradient updates, the proposed approach ensures that the privacy of individual devices is preserved without compromising the overall model accuracy. Moreover, the approach considers the heterogeneity of devices in terms of computational capabilities and energy constraints, allowing devices to adaptively adjust the level of privacy preservation to strike a balance between privacy and utility. Thirdly, efficient resource allocation is crucial for federated learning in wireless communications, as devices operate under limited bandwidth, energy, and computational resources. The proposed approach leverages optimization techniques to allocate resources effectively among the participating devices, considering factors such as data quality, network conditions, and device capabilities. By intelligently distributing the computational load, communication bandwidth, and energy consumption, the proposed approach minimizes resource wastage and ensures a fair and efficient FL process in wireless networks. To evaluate the performance of the proposed fair federated learning approach, extensive simulations and experiments will be conducted. The experiments will involve a diverse set of wireless devices, ranging from smartphones to Internet of Things (IoT) devices, operating in various scenarios with different data distributions and network conditions. The evaluation metrics will include model accuracy, fairness measures, privacy preservation, and resource utilization. The expected outcomes of this research include improved model performance, fair allocation of resources, enhanced privacy preservation, and a better understanding of the challenges and solutions for fair federated learning in wireless communications. The proposed approach has the potential to revolutionize wireless communication systems by enabling intelligent applications while addressing fairness concerns and preserving user privacy.

Keywords: federated learning, wireless communications, fairness, imbalanced data, privacy preservation, resource allocation, differential privacy, optimization

Procedia PDF Downloads 75

Authors: Sergio Andres Rojas, Julian Benavides Franco, Juan Tomas Sayago

Abstract:

An increasing amount of research demonstrates how market mood affects financial markets, but their primary goal is to demonstrate how Trump's tweets impacted US interest rate volatility. Following that lead, this work evaluates the effect that Trump's tweets had during his presidency on local and international stock markets, considering not just volatility but the direction of the movement. Three indexes for Trump's tweets were created relating his activity with movements in the S&P500 using natural language analysis and machine learning algorithms. The indexes consider Trump's tweet activity and the positive or negative market sentiment they might inspire. The first explores the relationship between tweets generating negative movements in the S&P500; the second explores positive movements, while the third explores the difference between up and down movements. A pseudo-investment strategy using the indexes produced statistically significant above-average abnormal returns. The findings also showed that the pseudo strategy generated a higher return in the local market if applied to intraday data. However, only a negative market sentiment caused this effect on daily data. These results suggest that the market reacted primarily to a negative idea reflected in the negative index. In the international market, it is not possible to identify a pervasive effect. A rolling window regression model was also performed. The result shows that the impact on the local and international markets is heterogeneous, time-changing, and differentiated for the market sentiment. However, the negative sentiment was more prone to have a significant correlation most of the time.

Keywords: market sentiment, Twitter market sentiment, machine learning, natural dialect analysis

Procedia PDF Downloads 62

Authors: Lorenzo Petrucci

Abstract:

This paper is intended to give insight into the potential use of small-scale off-grid trigeneration systems powered by biogas generated in a dairy farm. The off-grid plant object of analysis comprises a dual-fuel Genset as well as electrical and thermal storage equipment and an adsorption machine. The loads are the different apparatus used in the dairy farm, a household where the workers live and a small electric vehicle whose batteries can also be used as a power source in case of emergency. The insertion in the plant of an adsorption machine is mainly justified by the abundance of thermal energy and the simultaneous high cooling demand associated with the milk-chilling process. In the evaluated operational scenario, our research highlights the importance of prioritizing specific small loads which cannot sustain an interrupted supply of power over time. As a consequence, a photovoltaic and thermal panel is included in the plant and is tasked with providing energy independently of potentially disruptive events such as engine malfunctioning or scarce and unstable supplies of fuels. To efficiently manage the plant an energy dispatch strategy is created in order to control the flow of energy between the power sources and the thermal and electric storages. In this article we elaborate on models of the equipment and from these models, we extract parameters useful to build load-dependent profiles of the prime movers and storage efficiencies. We show that under reasonable assumptions the analysis provides a sensible estimate of the generated energy. The simulations indicate that a Diesel Generator sized to a value 25% higher than the total electrical peak demand operates 65% of the time below the minimum acceptable load threshold. To circumvent such a critical operating mode, dump loads are added through the activation and deactivation of small resistors. In this way, the excess of electric energy generated can be transformed into useful heat. The combination of PVT and electrical storage to support the prioritized load in an emergency scenario is evaluated in two different days of the year having the lowest and highest irradiation values, respectively. The results show that the renewable energy component of the plant can successfully sustain the prioritized loads and only during a day with very low irradiation levels it also needs the support of the EVs’ battery. Finally, we show that the adsorption machine can reduce the ice builder and the air conditioning energy consumption by 40%.

Keywords: hybrid power plants, mathematical modeling, off-grid plants, renewable energy, trigeneration

Procedia PDF Downloads 173

Authors: Lavanya Annadi, Fahimeh Jafari

Abstract:

Transportation brings immense benefits to society, but it also has its costs. Costs include such as the cost of infrastructure, personnel and equipment, but also the loss of life and property in traffic accidents on the road, delays in travel due to traffic congestion and various indirect costs in terms of air transport. More research has been done to identify the various factors that affect road accidents, such as road infrastructure, traffic, sociodemographic characteristics, land use, and the environment. The aim of this research is to predict the probabilistic crash prediction of vehicles using machine learning due to natural and structural reasons by excluding spontaneous reasons like overspeeding etc., in the United States. These factors range from weather factors, like weather conditions, precipitation, visibility, wind speed, wind direction, temperature, pressure, and humidity to human made structures like road structure factors like bump, roundabout, no exit, turning loop, give away, etc. Probabilities are dissected into ten different classes. All the predictions are based on multiclass classification techniques, which are supervised learning. This study considers all crashes that happened in all states collected by the US government. To calculate the probability, multinomial expected value was used and assigned a classification label as the crash probability. We applied three different classification models, including multiclass Logistic Regression, Random Forest and XGBoost. The numerical results show that XGBoost achieved a 75.2% accuracy rate which indicates the part that is being played by natural and structural reasons for the crash. The paper has provided in-deep insights through exploratory data analysis.

Keywords: road safety, crash prediction, exploratory analysis, machine learning

Procedia PDF Downloads 109

Authors: Luis C. Parra

Abstract:

The significant wave height prediction is an issue of great interest in the field of coastal activities because of the non-linear behavior of the wave height and its complexity of prediction. This study aims to present a machine learning model to forecast the significant wave height of the oceanographic wave measuring buoys anchored at Mooloolaba of the Queensland Government Data. Modeling was performed by a multilayer perceptron neural network-genetic algorithm (GA-MLP), considering Relu(x) as the activation function of the MLPNN. The GA is in charge of optimized the MLPNN hyperparameters (learning rate, hidden layers, neurons, and activation functions) and wrapper feature selection for the window width size. Results are assessed using Mean Square Error (MSE), Root Mean Square Error (RMSE), and Mean Absolute Error (MAE). The GAMLPNN algorithm was performed with a population size of thirty individuals for eight generations for the prediction optimization of 5 steps forward, obtaining a performance evaluation of 0.00104 MSE, 0.03222 RMSE, 0.02338 MAE, and 0.71163% of MAPE. The results of the analysis suggest that the MLPNNGA model is effective in predicting significant wave height in a one-step forecast with distant time windows, presenting 0.00014 MSE, 0.01180 RMSE, 0.00912 MAE, and 0.52500% of MAPE with 0.99940 of correlation factor. The GA-MLP algorithm was compared with the ARIMA forecasting model, presenting better performance criteria in all performance criteria, validating the potential of this algorithm.

Keywords: significant wave height, machine learning optimization, multilayer perceptron neural networks, evolutionary algorithms

Procedia PDF Downloads 106

Authors: Merve Yünlü, Nihat Kandemir, Aylin Ersoy

Abstract:

Temperature sensors are used in home appliances not only to monitor the basic functions of the machine but also to minimize energy consumption and ensure safe operation. In parallel with the development of smart home applications and IoT algorithms, these sensors produce important data such as the frequency of use of the machine, user preferences, and the compilation of critical data in terms of diagnostic processes for fault detection throughout an appliance's operational lifespan. Commercially available thin-film resistive temperature sensors have a well-established manufacturing procedure that allows them to operate over a wide temperature range. However, these sensors are over-designed for white goods applications. The operating temperature range of these sensors is between -70°C and 850°C, while the temperature range requirement in home appliance applications is between 23°C and 500°C. To ensure the operation of commercial sensors in this wide temperature range, usually, a platinum coating of approximately 1-micron thickness is applied to the wafer. However, the use of platinum in coating and the high coating thickness extends the sensor production process time and therefore increases sensor costs. In this study, an attempt was made to develop a low-cost temperature sensor design and production method that meets the technical requirements of white goods applications. For this purpose, a custom design was made, and design parameters (length, width, trim points, and thin film deposition thickness) were optimized by using statistical methods to achieve the desired resistivity value. To develop thin film resistive temperature sensors, one side polished sapphire wafer was used. To enhance adhesion and insulation 100 nm silicon dioxide was coated by inductively coupled plasma chemical vapor deposition technique. The lithography process was performed by a direct laser writer. The lift-off process was performed after the e-beam evaporation of 10 nm titanium and 280 nm platinum layers. Standard four-point probe sheet resistance measurements were done at room temperature. The annealing process was performed. Resistivity measurements were done with a probe station before and after annealing at 600°C by using a rapid thermal processing machine. Temperature dependence between 25-300 °C was also tested. As a result of this study, a temperature sensor has been developed that has a lower coating thickness than commercial sensors but can produce reliable data in the white goods application temperature range. A relatively simplified but optimized production method has also been developed to produce this sensor.

Keywords: thin film resistive sensor, temperature sensor, household appliance, sustainability, energy efficiency

Procedia PDF Downloads 70

Authors: Nabila Jaman, K. E. Hoque, S. Sawall, M. Ferdows

Abstract:

Coronary artery disease (CAD) is one of the most lethal diseases of the cardiovascular diseases. Coronary arteries stenosis and bifurcation angles closely interact for myocardial infarction. We want to use computer-aided design model coupled with computational hemodynamics (CHD) simulation for detecting several types of coronary artery stenosis with different locations in an idealized model for identifying virtual fractional flow reserve (vFFR). The vFFR provides us the information about the severity of stenosis in the computational models. Another goal is that we want to imitate patient-specific computed tomography coronary artery angiography model for constructing our idealized models with different left anterior descending (LAD) and left circumflex (LCx) bifurcation angles. Further, we want to analyze whether the bifurcation angles has an impact on the creation of narrowness in coronary arteries or not. The numerical simulation provides the CHD parameters such as wall shear stress (WSS), velocity magnitude and pressure gradient (PGD) that allow us the information of stenosis condition in the computational domain.

Keywords: CAD, CHD, vFFR, bifurcation angles, coronary stenosis

Procedia PDF Downloads 156

Authors: Mark Ashton Newman, Richard Blagrove, Jonathan Folland

Abstract:

The force-velocity profile of an individual has been shown to influence success in ballistic movements, independent of the individuals' maximal power output; therefore, effective and accurate evaluation of an individual’s F-V characteristics and not solely maximal power output is important. The relatively narrow range of loads typically utilised during force-velocity profiling protocols due to the difficulty in obtaining force data at high velocities may bring into question the accuracy of the F-V slope along with predictions pertaining to the maximum force that the system can produce at a velocity of null (F₀) and the theoretical maximum velocity against no load (V₀). As such, the reliability of the slope of the force-velocity profile, as well as V₀, has been shown to be relatively poor in comparison to F₀ and maximal power, and it has been recommended to assess velocity at loads closer to both F₀ and V₀. The aim of the present study was to assess the relative and absolute reliability of an instrumented novel leg press machine which enables the assessment of force and velocity data at loads equivalent to ≤ 10% of one repetition maximum (1RM) through to 1RM during a ballistic leg press movement. The reliability of maximal and mean force, velocity, and power, as well as the respective force-velocity and power-velocity relationships and the linearity of the force-velocity relationship, were evaluated. Sixteen male strength-trained individuals (23.6 ± 4.1 years; 177.1 ± 7.0 cm; 80.0 ± 10.8 kg) attended four sessions; during the initial visit, participants were familiarised with the leg press, modified to include a mounted force plate (Type SP3949, Force Logic, Berkshire, UK) and a Micro-Epsilon WDS-2500-P96 linear positional transducer (LPT) (Micro-Epsilon, Merseyside, UK). Peak isometric force (IsoMax) and a dynamic 1RM, both from a starting position of 81% leg length, were recorded for the dominant leg. Visits two to four saw the participants carry out the leg press movement at loads equivalent to ≤ 10%, 30%, 50%, 70%, and 90% 1RM. IsoMax was recorded during each testing visit prior to dynamic F-V profiling repetitions. The novel leg press machine used in the present study appears to be a reliable tool for measuring F and V-related variables across a range of loads, including velocities closer to V₀ when compared to some of the findings within the published literature. Both linear and polynomial models demonstrated good to excellent levels of reliability for SFV and F₀ respectively, with reliability for V₀ being good using a linear model but poor using a 2nd order polynomial model. As such, a polynomial regression model may be most appropriate when using a similar unilateral leg press setup to predict maximal force production capabilities due to only a 5% difference between F₀ and obtained IsoMax values with a linear model being best suited to predict V₀.

Keywords: force-velocity, leg-press, power-velocity, profiling, reliability

Procedia PDF Downloads 57

Authors: Shraddha Jain Sharma, Ratnalata Gupta

Abstract:

Predicting stock movements in the financial market is both difficult and rewarding. Analysts and academics are increasingly using advanced approaches such as machine learning techniques to anticipate stock price patterns, thanks to the expanding capacity of computing and the recent advent of graphics processing units and tensor processing units. Stock market prediction is a type of time series prediction that is incredibly difficult to do since stock prices are influenced by a variety of financial, socioeconomic, and political factors. Furthermore, even minor mistakes in stock market price forecasts can result in significant losses for companies that employ the findings of stock market price prediction for financial analysis and investment. Soft computing techniques are increasingly being employed for stock market prediction due to their better accuracy than traditional statistical methodologies. The proposed research looks at the need for soft computing techniques in stock market prediction, the numerous soft computing approaches that are important to the field, past work in the area with their prominent features, and the significant problems or issue domain that the area involves. For constructing a predictive model, the major focus is on neural networks and fuzzy logic. The stock market is extremely unpredictable, and it is unquestionably tough to correctly predict based on certain characteristics. This study provides a complete overview of the numerous strategies investigated for high accuracy prediction, with a focus on the most important characteristics.

Keywords: stock market prediction, artificial intelligence, artificial neural networks, fuzzy logic, accuracy, deep learning, machine learning, stock price, trading volume

Procedia PDF Downloads 88

Authors: Yiding Qu, Svetlana V. Komarova

Abstract:

Chemokines acting through their cognate chemokine receptors guide the directional migration of the cell along the chemokine gradient. Several chemokine receptors were recently identified as non-signaling (decoy), based on their ability to bind the chemokine but produce no measurable signal in the cell. The function of these decoy receptors is not well understood. We examined the expression of a decoy receptor CCRL1 and a signaling receptor that binds to the same ligands, CCR7, in prostate cancer using publically available microarray data (www.oncomine.org). The expression of both CCRL1 and CCR7 increased in an approximately half of prostate carcinoma samples and the majority of metastatic cancer samples compared to normal prostate. Moreover, the expression of CCRL1 positively correlated with the expression of CCR7. These data suggest that CCR7 and CCRL1 can be used as clinical markers for the early detection of transformation from carcinoma to metastatic cancer. In addition, these data support our hypothesis that the non-signaling chemokine receptors actively stimulate cell migration.

Keywords: bioinformatics, cell migration, decoy receptor, meta-analysis, prostate cancer

Procedia PDF Downloads 466

Authors: Meriem Harmel, Houari Khachai

Abstract:

We have investigated the structural, electronic and optical properties of a compound perovskite CsSrF3 using the full-potential linearized augmented plane wave (FP-LAPW) method within density functional theory (DFT). In this approach, both the local density approximation (LDA) and the generalized gradient approximation (GGA) were used for exchange-correlation potential calculation. The ground state properties such as lattice parameter, bulk modulus and its pressure derivative were calculated and the results are compared whit experimental and theoretical data. Electronic and bonding properties are discussed from the calculations of band structure, density of states and electron charge density, where the fundamental energy gap is direct under ambient conditions. The contribution of the different bands was analyzed from the total and partial density of states curves. The optical properties (namely: the real and the imaginary parts of the dielectric function ε(ω), the refractive index n(ω) and the extinction coefficient k(ω)) were calculated for radiation up to 35.0 eV. This is the first quantitative theoretical prediction of the optical properties for the investigated compound and still awaits experimental confirmations.

Keywords: DFT, fluoroperovskite, electronic structure, optical properties

Procedia PDF Downloads 476