Search results for: language learning model
18503 Design and Implementation of Generative Models for Odor Classification Using Electronic Nose
Authors: Kumar Shashvat, Amol P. Bhondekar
Abstract:
In the midst of the five senses, odor is the most reminiscent and least understood. Odor testing has been mysterious and odor data fabled to most practitioners. The delinquent of recognition and classification of odor is important to achieve. The facility to smell and predict whether the artifact is of further use or it has become undesirable for consumption; the imitation of this problem hooked on a model is of consideration. The general industrial standard for this classification is color based anyhow; odor can be improved classifier than color based classification and if incorporated in machine will be awfully constructive. For cataloging of odor for peas, trees and cashews various discriminative approaches have been used Discriminative approaches offer good prognostic performance and have been widely used in many applications but are incapable to make effectual use of the unlabeled information. In such scenarios, generative approaches have better applicability, as they are able to knob glitches, such as in set-ups where variability in the series of possible input vectors is enormous. Generative models are integrated in machine learning for either modeling data directly or as a transitional step to form an indeterminate probability density function. The algorithms or models Linear Discriminant Analysis and Naive Bayes Classifier have been used for classification of the odor of cashews. Linear Discriminant Analysis is a method used in data classification, pattern recognition, and machine learning to discover a linear combination of features that typifies or divides two or more classes of objects or procedures. The Naive Bayes algorithm is a classification approach base on Bayes rule and a set of qualified independence theory. Naive Bayes classifiers are highly scalable, requiring a number of restraints linear in the number of variables (features/predictors) in a learning predicament. The main recompenses of using the generative models are generally a Generative Models make stronger assumptions about the data, specifically, about the distribution of predictors given the response variables. The Electronic instrument which is used for artificial odor sensing and classification is an electronic nose. This device is designed to imitate the anthropological sense of odor by providing an analysis of individual chemicals or chemical mixtures. The experimental results have been evaluated in the form of the performance measures i.e. are accuracy, precision and recall. The investigational results have proven that the overall performance of the Linear Discriminant Analysis was better in assessment to the Naive Bayes Classifier on cashew dataset.Keywords: odor classification, generative models, naive bayes, linear discriminant analysis
Procedia PDF Downloads 37818502 A Hierarchical Method for Multi-Class Probabilistic Classification Vector Machines
Authors: P. Byrnes, F. A. DiazDelaO
Abstract:
The Support Vector Machine (SVM) has become widely recognised as one of the leading algorithms in machine learning for both regression and binary classification. It expresses predictions in terms of a linear combination of kernel functions, referred to as support vectors. Despite its popularity amongst practitioners, SVM has some limitations, with the most significant being the generation of point prediction as opposed to predictive distributions. Stemming from this issue, a probabilistic model namely, Probabilistic Classification Vector Machines (PCVM), has been proposed which respects the original functional form of SVM whilst also providing a predictive distribution. As physical system designs become more complex, an increasing number of classification tasks involving industrial applications consist of more than two classes. Consequently, this research proposes a framework which allows for the extension of PCVM to a multi class setting. Additionally, the original PCVM framework relies on the use of type II maximum likelihood to provide estimates for both the kernel hyperparameters and model evidence. In a high dimensional multi class setting, however, this approach has been shown to be ineffective due to bad scaling as the number of classes increases. Accordingly, we propose the application of Markov Chain Monte Carlo (MCMC) based methods to provide a posterior distribution over both parameters and hyperparameters. The proposed framework will be validated against current multi class classifiers through synthetic and real life implementations.Keywords: probabilistic classification vector machines, multi class classification, MCMC, support vector machines
Procedia PDF Downloads 21818501 A Model for Analyzing the Startup Dynamics of a Belt Transmission Driven by a DC Motor
Authors: Giovanni Incerti
Abstract:
In this paper the dynamic behavior of a synchronous belt drive during start-up is analyzed and discussed. Besides considering the belt elasticity, the mathematical model here proposed also takes into consideration the electrical behaviour of the DC motor. The solution of the motion equations is obtained by means of the modal analysis in state space, which allows to obtain the decoupling of all equations of the mathematical model without introducing the hypothesis of proportional damping. The mathematical model of the transmission and the solution algorithms have been implemented within a computing software that allows the user to simulate the dynamics of the system and to evaluate the effects due to the elasticity of the belt branches and to the electromagnetic behavior of the DC motor. In order to show the details of the calculation procedure, the paper presents a case study developed with the aid of the abovementioned software.Keywords: belt drive, vibrations, startup, DC motor
Procedia PDF Downloads 57018500 Anxiety and Self-Perceived L2 Proficiency: A Comparison of Which Can Better Predict L2 Pronunciation Performance
Authors: Jiexuan Lin, Huiyi Chen
Abstract:
The development of L2 pronunciation competence remains understudied in the literature and it is not clear what may influence learners’ development of L2 pronunciation. The present study was an attempt to find out which of the two common factors in L2 acquisition, i.e., foreign language anxiety or self-perceived L2 proficiency, can better predict Chinese EFL learners’ pronunciation performance. 78 first-year English majors, who had received a three-month pronunciation training course, were asked to 1) fill out a questionnaire on foreign language classroom anxiety, 2) self-report their L2 proficiency in general, in speaking and in pronunciation, and 3) complete an oral and a written test on their L2 pronunciation (the score of the oral part indicates participants’ pronunciation proficiency in oral production, and the score of the written part indexes participants’ ability in applying pronunciation knowledge in comprehension.) Results showed that the pronunciation scores were negatively correlated with the anxiety scores, and were positively correlated with the self-perceived pronunciation proficiency. But only the written scores in the L2 pronunciation test, not the oral scores, were positively correlated with the L2 self-perceived general proficiency. Neither the oral nor the written scores in the L2 pronunciation test had a significant correlation with the self-perceived speaking proficiency. Given the fairly strong correlations, the anxiety scores and the self-perceived pronunciation proficiency were put in regression models to predict L2 pronunciation performance. The anxiety factor alone accounted for 13.9% of the variance and the self-perceived pronunciation proficiency alone explained 12.1% of the variance. But when both anxiety scores and self-perceived pronunciation proficiency were put in a stepwise regression model, only the anxiety scores had a significant and unique contribution to the L2 pronunciation performance (4.8%). Taken together, the results suggested that the learners’ anxiety level could better predict their L2 pronunciation performance, compared with the self-perceived proficiency levels. The obtained data have the following pedagogical implications. 1) Given the fairly strong correlation between anxiety and L2 pronunciation performance, the instructors who are interested in predicting learners’ L2 pronunciation proficiency may measure their anxiety level, instead of their proficiency, as the predicting variable. 2) The correlation of oral scores (in the pronunciation test) with pronunciation proficiency, rather than with speaking proficiency, indicates that a) learners after receiving some amounts of training are to some extent able to evaluate their own pronunciation ability, implying the feasibility of incorporating self-evaluation and peer comments in course instruction; b) the ‘proficiency’ measure used to predict pronunciation performance should be used with caution. The proficiency of specific skills seemingly highly related to pronunciation (i.e., speaking in this case) may not be taken for granted as an effective predictor for pronunciation performance. 3) The correlation between the written scores with general L2 proficiency is interesting.Keywords: anxiety, Chinese EFL learners, L2 pronunciation, self-perceived L2 proficiency
Procedia PDF Downloads 35418499 Design and Analysis of a Lightweight Fire-Resistant Door
Authors: Zainab Fadil, Mouath Alawadhi, Abdullah Alhusainan, Fahad Alqadiri, Abdulaziz Alqadiri
Abstract:
This study investigates how lightweight a fire resistance door will perform with under types of insulation materials. Data is initially collected from various websites, scientific books and research papers. Results show that different layers of insulation in a single door can perform better than one insulator. Furthermore, insulation materials that are lightweight, high strength and low thermal conductivity are the most preferred for fire-rated doors. Whereas heavy weight, low strength, and high thermal conductivity are least preferred for fire-resistance doors. Fire-rated doors specifications, theoretical test methodology, structural analysis, and comparison between five different models with diverse layers insulations are presented. Five different door models are being investigated with different insulation materials and arrangements. Model 1 contains an air gap between door layers. Model 2 includes phenolic foam, mild steel and polyurethane. Model 3 includes phenolic foam and glass wool. Model 4 includes polyurethane and glass wool. Model 5 includes only rock wool between the door layers. It is noticed that model 5 is the most efficient model and its design is simple compared to other models. For this model, numerical calculations are performed to check its efficiency and the results are compared to data from experiments for validation. Good agreement was noticed.Keywords: fire resistance, insulation, strength, thermal conductivity, lightweight, layers
Procedia PDF Downloads 8118498 A Regional Innovation System Model Based on the Systems Thinking Approach
Authors: Samara E., Kilintzis P., Katsoras E., Martinidis G.
Abstract:
Regions play an important role in the global economy by driving research and innovation policies through a major tool, the Regional Innovation System (RIS). RIS is a social system that encompasses the systematic interaction of the various organizations that comprise it in order to improve local knowledge and innovation. This article describes the methodological framework for developing and validating a RIS model utilizing system dynamics. This model focuses on the functional structure of the RIS, separating it in six diverse, interacting sub-systems.Keywords: innovations, regional development, systems thinking, social system
Procedia PDF Downloads 6918497 Biosorption of Phenol onto Water Hyacinth Activated Carbon: Kinetics and Isotherm Study
Authors: Manoj Kumar Mahapatra, Arvind Kumar
Abstract:
Batch adsorption experiments were carried out for the removal of phenol from its aqueous solution using water hyancith activated carbon (WHAC) as an adsorbent. The sorption kinetics were analysed using pseudo-first order kinetics and pseudo-second order model, and it was observed that the sorption data tend to fit very well in pseudo-second order model for the entire sorption time. The experimental data were analyzed by the Langmuir and Freundlich isotherm models. Equilibrium data fitted well to the Freundlich model with a maximum biosorption capacity of 31.45 mg/g estimated using Langmuir model. The adsorption intensity 3.7975 represents a favorable adsorption condition.Keywords: adsorption, isotherm, kinetics, phenol
Procedia PDF Downloads 43818496 Development of Star Tracker for Satellite
Authors: S. Yelubayev, V. Ten, B. Albazarov, E. Sarsenbayev, К. Аlipbayev, A. Shamro, Т. Bopeyev, А. Sukhenko
Abstract:
Currently in Kazakhstan much attention is paid to the development of space branch. Successful launch of two Earth remote sensing satellite is carried out, projects on development of components for satellite are being carried out. In particular, the project on development of star tracker experimental model is completed. In the future it is planned to use this experimental model for development of star tracker prototype. Main stages of star tracker experimental model development are considered in this article.Keywords: development, prototype, satellite, star tracker
Procedia PDF Downloads 47118495 STEAM and Project-Based Learning: Equipping Young Women with 21st Century Skills
Authors: Sonia Saddiqui, Maya Marcus
Abstract:
UTS STEAMpunk Girls is an educational program for young women (aged 12-16), to empower them to be more informed and active members of the 21st century workforce. With the number of STEM graduates on the decline, especially among young women, an additional aim of the program is to trial a STEAM (Science, Technology, Engineering, Arts/Humanities/Social Sciences, Mathematics), inter-disciplinary approach to improving STEM engagement. In-line with UNESCO’s recent focus on promoting ‘transversal competencies’ in future graduates, the program utilised co-design, project-based learning, entrepreneurial processes, and inter-disciplinary learning. The program consists of two phases. Taking a participatory design approach, the first phase (co-design workshops) provided valuable insight into student perspectives around engaging young women in STEM and inter-disciplinary thinking. The workshops positioned 26 young women from three schools as subject matter experts (SMEs), providing a platform for them to share their opinions, experiences and findings around the STEAM disciplines. The second (pilot) phase put the co-design phase findings into practice, with 64 students from four schools working in groups to articulate problems with real-world implications, and utilising design-thinking to solve them. The pilot phase utilised project-based learning to engage young women in entrepreneurial and STEAM frameworks and processes. Scalable program design and educational resources were trialed to determine appropriate mechanisms for engaging young women in STEM and in STEAM thinking. Across both phases, data was collected via longitudinal surveys to obtain pre-program, baseline attitudinal information, and compare that against post-program responses. Preliminary findings revealed students’ improved understanding of the STEM disciplines, industries and professions, improved awareness of STEAM as a concept, and improved understanding regarding inter-disciplinary and design thinking. Program outcomes will be of interest to high-school educators in both STEM and the Arts, Humanities and Social Sciences fields, and will hopefully inform future programmatic approaches to introducing inter-disciplinary STEAM learning in STEM curriculum.Keywords: co-design, STEM, STEAM, project-based learning, inter-disciplinary
Procedia PDF Downloads 19418494 Automatic Identification and Classification of Contaminated Biodegradable Plastics using Machine Learning Algorithms and Hyperspectral Imaging Technology
Authors: Nutcha Taneepanichskul, Helen C. Hailes, Mark Miodownik
Abstract:
Plastic waste has emerged as a critical global environmental challenge, primarily driven by the prevalent use of conventional plastics derived from petrochemical refining and manufacturing processes in modern packaging. While these plastics serve vital functions, their persistence in the environment post-disposal poses significant threats to ecosystems. Addressing this issue necessitates approaches, one of which involves the development of biodegradable plastics designed to degrade under controlled conditions, such as industrial composting facilities. It is imperative to note that compostable plastics are engineered for degradation within specific environments and are not suited for uncontrolled settings, including natural landscapes and aquatic ecosystems. The full benefits of compostable packaging are realized when subjected to industrial composting, preventing environmental contamination and waste stream pollution. Therefore, effective sorting technologies are essential to enhance composting rates for these materials and diminish the risk of contaminating recycling streams. In this study, it leverage hyperspectral imaging technology (HSI) coupled with advanced machine learning algorithms to accurately identify various types of plastics, encompassing conventional variants like Polyethylene terephthalate (PET), Polypropylene (PP), Low density polyethylene (LDPE), High density polyethylene (HDPE) and biodegradable alternatives such as Polybutylene adipate terephthalate (PBAT), Polylactic acid (PLA), and Polyhydroxyalkanoates (PHA). The dataset is partitioned into three subsets: a training dataset comprising uncontaminated conventional and biodegradable plastics, a validation dataset encompassing contaminated plastics of both types, and a testing dataset featuring real-world packaging items in both pristine and contaminated states. Five distinct machine learning algorithms, namely Partial Least Squares Discriminant Analysis (PLS-DA), Support Vector Machine (SVM), Convolutional Neural Network (CNN), Logistic Regression, and Decision Tree Algorithm, were developed and evaluated for their classification performance. Remarkably, the Logistic Regression and CNN model exhibited the most promising outcomes, achieving a perfect accuracy rate of 100% for the training and validation datasets. Notably, the testing dataset yielded an accuracy exceeding 80%. The successful implementation of this sorting technology within recycling and composting facilities holds the potential to significantly elevate recycling and composting rates. As a result, the envisioned circular economy for plastics can be established, thereby offering a viable solution to mitigate plastic pollution.Keywords: biodegradable plastics, sorting technology, hyperspectral imaging technology, machine learning algorithms
Procedia PDF Downloads 7018493 Intelligent Control Design of Car Following Behavior Using Fuzzy Logic
Authors: Abdelkader Merah, Kada Hartani
Abstract:
A reference model based control approach for improving behavior following car is proposed in this paper. The reference model is nonlinear and provides dynamic solutions consistent with safety constraints and comfort specifications. a robust fuzzy logic based control strategy is further proposed in this paper. A set of simulation results showing the suitability of the proposed technique for various demanding cenarios is also included in this paper.Keywords: reference model, longitudinal control, fuzzy logic, design of car
Procedia PDF Downloads 42218492 Validation of Codes Dragon4 and Donjon4 by Calculating Keff of a Slowpoke-2 Reactor
Authors: Otman Jai, Otman Elhajjaji, Jaouad Tajmouati
Abstract:
Several neutronic calculation codes must be used to solve the equation for different levels of discretization which all necessitate a specific modelisation. This chain of such models, known as a calculation scheme, leads to the knowledge of the neutron flux in a reactor from its own geometry, its isotopic compositions and a cross-section library. Being small in size, the 'Slowpoke-2' reactor is difficult to model due to the importance of the leaking neutrons. In the paper, the simulation model is presented (geometry, cross section library, assumption, etc.), and the results obtained by DRAGON4/DONJON4 codes were compared to the calculations performed with Monte Carlo code MCNP using detailed geometrical model of the reactor and the experimental data. Criticality calculations have been performed to verify and validate the model. Since created model properly describes the reactor core, it can be used for calculations of reactor core parameters and for optimization of research reactor application.Keywords: transport equation, Dragon4, Donjon4, neutron flux, effective multiplication factor
Procedia PDF Downloads 46318491 Active Contours for Image Segmentation Based on Complex Domain Approach
Authors: Sajid Hussain
Abstract:
The complex domain approach for image segmentation based on active contour has been designed, which deforms step by step to partition an image into numerous expedient regions. A novel region-based trigonometric complex pressure force function is proposed, which propagates around the region of interest using image forces. The signed trigonometric force function controls the propagation of the active contour and the active contour stops on the exact edges of the object accurately. The proposed model makes the level set function binary and uses Gaussian smoothing kernel to adjust and escape the re-initialization procedure. The working principle of the proposed model is as follows: The real image data is transformed into complex data by iota (i) times of image data and the average iota (i) times of horizontal and vertical components of the gradient of image data is inserted in the proposed model to catch complex gradient of the image data. A simple finite difference mathematical technique has been used to implement the proposed model. The efficiency and robustness of the proposed model have been verified and compared with other state-of-the-art models.Keywords: image segmentation, active contour, level set, Mumford and Shah model
Procedia PDF Downloads 9918490 Comparison of Fundamental Frequency Model and PWM Based Model for UPFC
Authors: S. A. Al-Qallaf, S. A. Al-Mawsawi, A. Haider
Abstract:
Among all FACTS devices, the unified power flow controller (UPFC) is considered to be the most versatile device. This is due to its capability to control all the transmission system parameters (impedance, voltage magnitude, and phase angle). With the growing interest in UPFC, the attention to develop a mathematical model has increased. Several models were introduced for UPFC in literature for different type of studies in power systems. In this paper a novel comparison study between two dynamic models of UPFC with their proposed control strategies.Keywords: FACTS, UPFC, dynamic modeling, PWM, fundamental frequency
Procedia PDF Downloads 33918489 Modelling of Cavity Growth in Underground Coal Gasification
Authors: Preeti Aghalayam, Jay Shah
Abstract:
Underground coal gasification (UCG) is the in-situ gasification of unmineable coals to produce syngas. In UCG, gasifying agents are injected into the coal seam, and a reactive cavity is formed due to coal consumption. The cavity formed is typically hemispherical, and this report consists of the MATLAB model of the UCG cavity to predict the composition of the output gases. There are seven radial and two time-variant ODEs. A MATLAB solver (ode15s) is used to solve the radial ODEs from the above equations. Two for-loops are implemented in the model, i.e., one for time variations and another for radial variation. In the time loop, the radial odes are solved using the MATLAB solver. The radial loop is nested inside the time loop, and the density odes are numerically solved using the Euler method. The model is validated by comparing it with the literature results of laboratory-scale experiments. The model predicts the radial and time variation of the product gases inside the cavity.Keywords: gasification agent, MATLAB model, syngas, underground coal gasification (UCG)
Procedia PDF Downloads 19618488 Investigation of the Influence of Student’s Characteristics on Mathematics Achievement in Junior Secondary School in Ibadan, Nigeria
Authors: Babatunde Kasim Oladele
Abstract:
This current study investigated students’ characteristics as factors that influence Mathematics Achievement of junior secondary school students. The study adopted a descriptive survey design. The population of the study was one hundred and twenty-three (123) JSS students of secondary schools in Ibadan North Local Government in Oyo State. A Mathematics achievement test and three questionnaires on student’s self-efficacy belief, attitude, and learning style were the instruments used. Prior to the administration of the constructed mathematics achievement test, 100-item mathematics was subjected to the expert review, and items analysis was carried out. Fifty items were retained. The Cronbach Alpha reliability coefficients of the instruments were 0.71, 0.76, and 0.83, respectively. Collected data were analysed using the frequency count, percentages, mean, standard deviation, and Path Analysis in Amos SPSS Version 20. Students characteristics: gender, age, self-efficacy, attitude and learning style had positive direct effects on students’ achievement in Mathematics as indicated by their respective beta weights (β = 0.36, 0.203, 0.92, 0.079, 0.69 p < 0.05). Consequently, the study concluded that student’s characteristics (Age, gender, and learning style) explained a significant part of the variability in students’ achievement in Mathematics.Keywords: mathematics achievement, students’ characteristics, junior secondary school, Ibadan
Procedia PDF Downloads 31718487 Learning Made Right: Building World Class Engineers in Tunisia
Authors: Zayen Chagra
Abstract:
Several educational institutions are experimenting new approaches in learning in order to guarantee the success of its students. In Tunisia, and since 2011, the experience of making a new software engineering branch called mobile software engineering began at ESPRIT: Higher School of Engineering and Technology. The project was surprisingly a success since its creation, and even before the graduation of the first generation, partnerships were held with the biggest mobile technology manufacturers and several international awards were won by teams of students. This session presents this experience with details of the approaches made from idea stage to the actual stage where the project counts 32 graduated engineers, 90 graduate students and 120 new participants.Keywords: innovation, education, engineering education, mobile
Procedia PDF Downloads 42018486 An Investigation into the Role of School Social Workers and Psychologists with Children Experiencing Special Educational Needs in Libya
Authors: Abdelbasit Gadour
Abstract:
This study explores the function of schools’ psychosocial services within Libyan mainstream schools in relation to children’s special educational needs (SEN). This is with the aim to examine the role of school social workers and psychologists in the assessment procedure of children with special educational needs. A semi-structured interview was used in this study, with 21 professionals working in the schools’ psychosocial services, of whom thirteen were school social workers (SSWs) and eight were school psychologists (SPs). The results of the interviews with SSWs and SPs provided insights into how SEN children are identified, assessed, and dealt with by school professionals. It appears from the results that what constitutes a problem has not changed significantly, and the link between learning difficulties and behavioral difficulties is also evident from this study. Children with behavior difficulties are more likely to be referred to school psychosocial services than children with learning difficulties. Yet, it is not clear from the interviews with SSWs and SPs whether children are excluded merely because of their behavior problems. Instead, they would surely be expelled from the school if they failed academically. Furthermore, the interviews with SSWs and SPs yield a rather unusual source accountable for children’s SEN; school-related difficulties were a major factor in which almost all participants attributed children’s learning and behavior problems to teachers’ deficiencies, followed by school lack of resources.Keywords: psychologist, school, social workers, special education
Procedia PDF Downloads 10318485 Creativity in Development of Multimedia Presentation
Authors: Mahathir Sarjan, Ramos Radzly, Noor Baiti Jamaluddin, Mohd Hafiz Zakaria, Hisham Suhadi
Abstract:
Creativity is marked by the ability or power, to produce through imaginative skill and create something anew. The University is one of the great places to improve the talent in imaginative skill. Thus, it is important that for the student have a creativity to adapt the multimedia element in the development of presentation products for learning and teaching the process. The purpose of this study was to identify a creativity of the student in presentation product development. Two hundred seventeen Technical and Vocational Education (TVE) students in Universiti Tun Hussein Onn had chosen as a respondent. This study is to survey the level of creativity which is focused on knowledge, skills, presentation style and character of creative personnel. The level of creativity was measured based on the scale at low, medium and high followed by mean score level. The data collected by questionnaire then analyzed using SPSS version 20.0. The result of the study indicated that the students showed a higher of creativity (mean score in Knowledge = 4.12 and Skills= 4.02). In conjunction with the findings s implications and recommendations were suggested forward like to ensconce the research and improve with a more creativity concept in presentation product of development for learning and teaching the process.Keywords: creativity, technical, vocational education, presentation products and development for learning and teaching process
Procedia PDF Downloads 42118484 Prediction Compressive Strength of Self-Compacting Concrete Containing Fly Ash Using Fuzzy Logic Inference System
Authors: Belalia Douma Omar, Bakhta Boukhatem, Mohamed Ghrici
Abstract:
Self-compacting concrete (SCC) developed in Japan in the late 80s has enabled the construction industry to reduce demand on the resources, improve the work condition and also reduce the impact of environment by elimination of the need for compaction. Fuzzy logic (FL) approaches has recently been used to model some of the human activities in many areas of civil engineering applications. Especially from these systems in the model experimental studies, very good results have been obtained. In the present study, a model for predicting compressive strength of SCC containing various proportions of fly ash, as partial replacement of cement has been developed by using Adaptive Neuro-Fuzzy Inference System (ANFIS). For the purpose of building this model, a database of experimental data were gathered from the literature and used for training and testing the model. The used data as the inputs of fuzzy logic models are arranged in a format of five parameters that cover the total binder content, fly ash replacement percentage, water content, super plasticizer and age of specimens. The training and testing results in the fuzzy logic model have shown a strong potential for predicting the compressive strength of SCC containing fly ash in the considered range.Keywords: self-compacting concrete, fly ash, strength prediction, fuzzy logic
Procedia PDF Downloads 32818483 Early Impact Prediction and Key Factors Study of Artificial Intelligence Patents: A Method Based on LightGBM and Interpretable Machine Learning
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 3818482 Review and Comparison of Associative Classification Data Mining Approaches
Authors: Suzan Wedyan
Abstract:
Data mining is one of the main phases in the Knowledge Discovery Database (KDD) which is responsible of finding hidden and useful knowledge from databases. There are many different tasks for data mining including regression, pattern recognition, clustering, classification, and association rule. In recent years a promising data mining approach called associative classification (AC) has been proposed, AC integrates classification and association rule discovery to build classification models (classifiers). This paper surveys and critically compares several AC algorithms with reference of the different procedures are used in each algorithm, such as rule learning, rule sorting, rule pruning, classifier building, and class allocation for test cases.Keywords: associative classification, classification, data mining, learning, rule ranking, rule pruning, prediction
Procedia PDF Downloads 53018481 A Mathematical Description of a Growing Cell Colony Based on the Mechanical Bidomain Model
Authors: Debabrata Auddya, Bradley J. Roth
Abstract:
The mechanical bidomain model is used to describe a colony of cells growing on a substrate. Analytical expressions are derived for the intracellular and extracellular displacements. Mechanotransduction events are driven by the difference between the displacements in the two spaces, corresponding to the force acting on integrins. The equation for the displacement consists of two terms: one proportional to the radius that is the same in the intracellular and extracellular spaces (the monodomain term) and one that is proportional to a modified Bessel function that is responsible for mechanotransduction (the bidomain term). The model predicts that mechanotransduction occurs within a few length constants of the colony’s edge, and an expression for the length constant contains the intracellular and extracellular shear moduli and the spring constant of the integrins coupling the two spaces. The model predictions are qualitatively consistent with experiments on human embryonic stem cell colonies, in which differentiation is localized near the edge.Keywords: cell colony, integrin, mechanical bidomain model, stem cell, stress-strain, traction force
Procedia PDF Downloads 23518480 The Student's Satisfaction toward Web Based Instruction on Puppet Show
Authors: Piyanut Suchit
Abstract:
The purposes of this study was to investigate students’ satisfaction learning with the web based instruction on the puppet show. The population of this study includes 53 students in the Program of Library and Information Sciences who registered in the subject of Puppet for Assisting Learning Development in semester 2/2011, Suansunandha Rajabhat University, Bangkok, Thailand. The research instruments consist of web based instruction on the puppet show, and questionnaires for students’ satisfaction. The research statistics includes arithmetic mean, and standard deviation. The results revealed that the students reported very high satisfaction with mean = 4.63, SD = 0.52, on the web based instruction.Keywords: puppet show, web based instruction, satisfaction, Suansunandha Rajabhat University
Procedia PDF Downloads 38118479 Bridge Health Monitoring: A Review
Authors: Mohammad Bakhshandeh
Abstract:
Structural Health Monitoring (SHM) is a crucial and necessary practice that plays a vital role in ensuring the safety and integrity of critical structures, and in particular, bridges. The continuous monitoring of bridges for signs of damage or degradation through Bridge Health Monitoring (BHM) enables early detection of potential problems, allowing for prompt corrective action to be taken before significant damage occurs. Although all monitoring techniques aim to provide accurate and decisive information regarding the remaining useful life, safety, integrity, and serviceability of bridges, understanding the development and propagation of damage is vital for maintaining uninterrupted bridge operation. Over the years, extensive research has been conducted on BHM methods, and experts in the field have increasingly adopted new methodologies. In this article, we provide a comprehensive exploration of the various BHM approaches, including sensor-based, non-destructive testing (NDT), model-based, and artificial intelligence (AI)-based methods. We also discuss the challenges associated with BHM, including sensor placement and data acquisition, data analysis and interpretation, cost and complexity, and environmental effects, through an extensive review of relevant literature and research studies. Additionally, we examine potential solutions to these challenges and propose future research ideas to address critical gaps in BHM.Keywords: structural health monitoring (SHM), bridge health monitoring (BHM), sensor-based methods, machine-learning algorithms, and model-based techniques, sensor placement, data acquisition, data analysis
Procedia PDF Downloads 8418478 Teachers' Perceptions of Physical Education and Sports Calendar and Conducted in the Light of the Objective of the Lesson Approach Competencies
Authors: Chelali Mohammed
Abstract:
In the context of the application of the competency-based approach in the system educational Algeria, the price of physical education and sport must privilege the acquisition of learning approaches and especially the approach science, which from problem situations, research and develops him information processing and application of knowledge and know-how in new situations in the words of ‘JOHN DEWEY’ ‘learning by practice’. And to achieve these goals and make teaching more EPS motivating, consistent and concrete, it is appropriate to perform a pedagogical approach freed from the constraints and open to creativity and student-centered in the light of the competency approach adopted in the formal curriculum. This approach is not unusual, but we think it is a highly professional nature requires the competence of the teacher.Keywords: approach competencies, physical, education, teachers
Procedia PDF Downloads 59718477 A Model of Preventing Global Financial Crisis: Gauss Law Model Proposal Used in Electrical Field Calculations
Authors: Arzu K. Kamberli
Abstract:
This article examines the relationship between economics and physics, starting with Adam Smith, with a new econophysics approach in Economics-Physics with the Gauss Law model proposal using for the Electric Field calculation, which will allow us to anticipate the Global Financial Crisis. For this purpose, the similarities between the Gauss Law using the electric field calculations and the global financial crisis have been explained on the formula, and a model has been suggested to predict the risks of the financial systems from the electricity field calculations. Thus, this study is expected to help for preventing the Global Financial Crisis with the contribution of the science of economics and physics from the aspect of econophysics.Keywords: econophysics, electric field, financial system, Gauss law, global financial crisis
Procedia PDF Downloads 27518476 Analysis of Multilayer Neural Network Modeling and Long Short-Term Memory
Authors: Danilo López, Nelson Vera, Luis Pedraza
Abstract:
This paper analyzes fundamental ideas and concepts related to neural networks, which provide the reader a theoretical explanation of Long Short-Term Memory (LSTM) networks operation classified as Deep Learning Systems, and to explicitly present the mathematical development of Backward Pass equations of the LSTM network model. This mathematical modeling associated with software development will provide the necessary tools to develop an intelligent system capable of predicting the behavior of licensed users in wireless cognitive radio networks.Keywords: neural networks, multilayer perceptron, long short-term memory, recurrent neuronal network, mathematical analysis
Procedia PDF Downloads 41018475 Interoperability Maturity Models for Consideration When Using School Management Systems in South Africa: A Scoping Review
Authors: Keneilwe Maremi, Marlien Herselman, Adele Botha
Abstract:
The main purpose and focus of this paper are to determine the Interoperability Maturity Models to consider when using School Management Systems (SMS). The importance of this is to inform and help schools with knowing which Interoperability Maturity Model is best suited for their SMS. To address the purpose, this paper will apply a scoping review to ensure that all aspects are provided. The scoping review will include papers written from 2012-2019 and a comparison of the different types of Interoperability Maturity Models will be discussed in detail, which includes the background information, the levels of interoperability, and area for consideration in each Maturity Model. The literature was obtained from the following databases: IEEE Xplore and Scopus, the following search engines were used: Harzings, and Google Scholar. The topic of the paper was used as a search term for the literature and the term ‘Interoperability Maturity Models’ was used as a keyword. The data were analyzed in terms of the definition of Interoperability, Interoperability Maturity Models, and levels of interoperability. The results provide a table that shows the focus area of concern for each Maturity Model (based on the scoping review where only 24 papers were found to be best suited for the paper out of 740 publications initially identified in the field). This resulted in the most discussed Interoperability Maturity Model for consideration (Information Systems Interoperability Maturity Model (ISIMM) and Organizational Interoperability Maturity Model for C2 (OIM)).Keywords: interoperability, interoperability maturity model, school management system, scoping review
Procedia PDF Downloads 19818474 Stability Bound of Ruin Probability in a Reduced Two-Dimensional Risk Model
Authors: Zina Benouaret, Djamil Aissani
Abstract:
In this work, we introduce the qualitative and quantitative concept of the strong stability method in the risk process modeling two lines of business of the same insurance company or an insurance and re-insurance companies that divide between them both claims and premiums with a certain proportion. The approach proposed is based on the identification of the ruin probability associate to the model considered, with a stationary distribution of a Markov random process called a reversed process. Our objective, after clarifying the condition and the perturbation domain of parameters, is to obtain the stability inequality of the ruin probability which is applied to estimate the approximation error of a model with disturbance parameters by the considered model. In the stability bound obtained, all constants are explicitly written.Keywords: Markov chain, risk models, ruin probabilities, strong stability analysis
Procedia PDF Downloads 244