Search results for: statistical machine learning

Authors: Qiuyu Dai, Haochong Zhang, Xiangrong Liu

Abstract:

Diagonal sparse matrix-vector multiplication is a well-studied topic in the fields of scientific computing and big data processing. However, when diagonal sparse matrices are stored in DIA format, there can be a significant number of padded zero elements and scattered points, which can lead to a degradation in the performance of the current DIA kernel. This can also lead to excessive consumption of computational and memory resources. In order to address these issues, the authors propose the DIA-Adaptive scheme and its kernel, which leverages the parallel instruction sets on MLU. The researchers analyze the effect of allocating a varying number of threads, clusters, and hardware architectures on the performance of SpMV using different formats. The experimental results indicate that the proposed DIA-Adaptive scheme performs well and offers excellent parallelism.

Keywords: adaptive method, DIA, diagonal sparse matrices, MLU, sparse matrix-vector multiplication

Procedia PDF Downloads 135

Authors: Sirapop Nuannimnoi, Hojjat Baghban, Ching-Yao Huang

Abstract:

Over the past decade, with the fast development of blockchain technology since the birth of Bitcoin, there has been a massive increase in the usage of Cryptocurrencies. Cryptocurrencies are not seen as an investment opportunity due to the market’s erratic behavior and high price volatility. With the recent success of deep reinforcement learning (DRL), portfolio management can be modeled and automated. In this paper, we propose a novel DRL-based multi-agent system to automatically make proper trading decisions on multiple cryptocurrencies and gain profits in the highly volatile cryptocurrency market. We also extend this multi-agent system with horizontal federated transfer learning for better adapting to the inclusion of new cryptocurrencies in our portfolio; therefore, we can, through the concept of diversification, maximize our profits and minimize the trading risks. Experimental results through multiple simulation scenarios reveal that this proposed algorithmic trading system can offer three promising key advantages over other systems, including maximized profits, minimized risks, and adaptability.

Keywords: cryptocurrency portfolio management, algorithmic trading, federated learning, multi-agent reinforcement learning

Procedia PDF Downloads 119

Authors: Kemal Izci

Abstract:

Assessment forms an important part of instruction. Assessment that aims to support learning is known as formative assessment and it contributes student’s learning gain and motivation. However, teachers rarely use assessment formatively to aid their students’ learning. Thus, reviewing the factors that limit or support teachers’ practices of formative assessment will be crucial for guiding educators to support prospective teachers in using formative assessment and also eliminate limiting factors to let practicing teachers to engage in formative assessment practices during their instruction. The study, by using teacher’s change environment framework, reviews literature on formative assessment and presents a tentative model that illustrates the factors impacting teachers’ adoption of formative assessment in their teaching. The results showed that there are four main factors consisting personal, contextual, resource-related and external factors that influence teachers’ practices of formative assessment.

Keywords: assessment practices, formative assessment, teacher education, factors for use of formative assessment

Procedia PDF Downloads 376

Authors: Ida Srdić, Luka Mandić, LidijaMandić

Abstract:

Digitization and intensive use of tablets, smartphones, the internet, mobile, and web applications have massively disrupted our habits, and the way audiences (especially youth) consume content. To introduce educational content in games and animations, and at the same time to keep it interesting and compelling for kids, is a challenge. In our work, we are comparing the different possibilities and potentials that digital games could provide to successfully mitigate direct connection with education. We analyze the main directions and educational methods in game-based learning and the possibilities of interactive modeling through questionnaires for user experience and requirements. A pre and post-quantitative survey will be conducted in order to measure levels of objective knowledge as well as the games perception. This approach enables quantitative and objective evaluation of the impact the game has on participants. Also, we will discuss the main barriers to the use of games in education and how games can be best used for learning.

Keywords: Bloom’s taxonomy, epistemic games, learning objectives, virtual learning environments

Procedia PDF Downloads 98

Authors: Saman Khairani

Abstract:

Assessment is a pivotal component of the teaching and learning process, serving as a critical tool for evaluating student progress, diagnosing learning needs, and informing instructional decisions. In the context of English Language Teaching (ELT), effective assessment practices are essential to promote meaningful learning experiences and foster continuous improvement in language proficiency. This paper delves into various assessment strategies, explores associated challenges, and highlights best practices for assessing student learning in ELT. The paper begins by examining the diverse forms of assessment, including formative assessments that provide timely feedback during the learning process and summative assessments that evaluate overall achievement. Additionally, alternative methods such as portfolios, self-assessment, and peer assessment play a significant role in capturing various aspects of language learning. Aligning assessments with learning objectives is crucial. Educators must ensure that assessment tasks reflect the desired language skills, communicative competence, and cultural awareness. Validity, reliability, and fairness are essential considerations in assessment design. Challenges in assessing language skills—such as speaking, listening, reading, and writing—are discussed, along with practical solutions. Constructive feedback, tailored to individual learners, guides their language development. In conclusion, this paper synthesizes research findings and practical insights, equipping ELT practitioners with the knowledge and tools necessary to design, implement, and evaluate effective assessment practices. By fostering meaningful learning experiences, educators contribute significantly to learners’ language proficiency and overall success.

Keywords: ELT, formative, summative, fairness, validity, reliability

Procedia PDF Downloads 56

Authors: Muhammet Baldan, Emel Timuçin

Abstract:

Generally, absorption and bioavailability increase if solubility increases; therefore, it is crucial to predict them in drug discovery applications. Molecular descriptors and Molecular properties are traditionally used for the prediction of water solubility. There are various key descriptors that are used for this purpose, namely Drogan Descriptors, Morgan Descriptors, Maccs keys, etc., and each has different prediction capabilities with differentiating successes between different data sets. Another source for the prediction of solubility is structural features; they are commonly used for the prediction of solubility. However, there are little to no studies that combine three or more properties or descriptors for prediction to produce a more powerful prediction model. Unlike available models, we used a combination of those features in a random forest machine learning model for improved solubility prediction to better predict and, therefore, contribute to drug discovery systems.

Keywords: solubility, random forest, molecular descriptors, maccs keys

Procedia PDF Downloads 46

Authors: Sushil Kumar, M. Dakshina Murty

Abstract:

Thermal network modelling has proven to be important tool for thermal analysis of electrical machine. This article investigates numerical thermal network model and experimental performance of a large-scale AC motor. Experimental temperatures were measured using RTD in the stator which have been compared with the numerical data. Thermal network modelling fairly predicts the temperature of various components inside the large-scale AC motor. Results of stator winding temperature is compared with experimental results which are in close agreement with accuracy of 6-10%. This method of predicting hot spots within AC motors can be readily used by the motor designers for estimating the thermal hot spots of the machine.

Keywords: AC motor, thermal network, heat transfer, modelling

Procedia PDF Downloads 326

Authors: Adil Ishag

Abstract:

Diglossia emerges in a situation where two distinctive varieties of a language are used alongside within a certain community. In this case, one is considered as a high or standard variety and the second one as a low or colloquial variety. Arabic is an extreme example of a highly diglossic language. This diglossity is due to the fact that Arabic is one of the most spoken languages and spread over 22 Countries in two continents as a mother tongue, and it is also widely spoken in many other Islamic countries as a second language or simply the language of Quran. The geographical variation between the countries where the language is spoken and the duality of the classical Arabic and daily spoken dialects in the Arab world on the other hand; makes the Arabic language one of the most diglossic languages. This paper tries to investigate this phenomena and its relation to learning Arabic as a first and second language.

Keywords: Arabic language, diglossia, first and second language, language learning

Procedia PDF Downloads 564

Authors: Barış Ozluoymak, Emin Guzel, Ahmet İnce

Abstract:

Since chemical fertilizers are used for meeting the deficiency of plant nutrients, its many harmful effects are not taken into consideration for the structure of the earth. These fertilizers are hampering the work of the organisms in the soil immediately after thrown to the ground. This interference is first started with a change of the soil pH and micro organismic balance is disrupted by reaction in the soil. Since there can be no fragmentation of plant residues, organic matter in the soil will be increasingly impoverished in the absence of micro organismic living. Biological activity reduction brings about a deterioration of the soil structure. If the chemical fertilization continues intensively, soils will get worse every year; plant growth will slow down and stop due to the intensity of chemical fertilizers, yield decline will be experienced and farmer will not receive an adequate return on his investment. In this research, a prototype of automatic farm manure spreading machine for orange orchards that not just manufactured in Turkey was designed, constructed, tested and eliminate the human drudgery involved in spreading of farm manure in the field. The machine comprised several components as a 5 m3 volume hopper, automatic controlled hydraulically driven chain conveyor device and side delivery conveyor belts. To spread the solid farm manure automatically, the machine was equipped with an electronic control system. The hopper and side delivery conveyor designs fitted between orange orchard tree row spacing. Test results showed that the control system has significant effects on reduction in the amount of unnecessary solid farm manure use and avoiding inefficient manual labor.

Keywords: automatic control system, conveyor belt application, orchard, solid farm manure

Procedia PDF Downloads 285

Authors: Olubukola Olumuyiwa Tokede, Dominic D. Ahiaga-Dagbui, John Morrison

Abstract:

The project environment in construction has been widely criticised for its inability to learn from experience effectively. As each project is bespoke, learning is ephemeral, as it is often confined within its bounds and seldom assimilated with others that are being delivered in the project environment. To engender learning across construction projects, collaborative contractual arrangements, such as alliancing and partnering, have been embraced to aid the transferability of lessons across projects. These cooperative arrangements, however, tend to be costly, and hence construction organisations could revert to less expensive traditional procurement approaches after successful collaborative project delivery. This research, therefore, seeks to assess the lessons-learned in a post-alliance contractual framework. Using a case-study approach, we examine the experiences of a public sector authority who engaged a project facilitator to foster learning during the delivery of a significant piece of critical infrastructure. It was found that the facilitator enabled optimal learning outcomes in post-alliance contractual frameworks by attenuating the otherwise adversarial relationship between clients and contractors. Further research will seek to assess the effectiveness of different knowledge-brokering agencies in construction projects.

Keywords: facilitation, knowledge-brokering, learning, projects

Procedia PDF Downloads 136

Authors: Richard Ren

Abstract:

Air pollution is a serious danger to international well-being and economies - it will kill an estimated 7 million people every year, costing world economies $2.6 trillion by 2060 due to sick days, healthcare costs, and reduced productivity. In the United States alone, 60,000 premature deaths are caused by poor air quality. For this reason, there is a crucial need to develop effective methods to forecast air quality, which can mitigate air pollution’s detrimental public health effects and associated costs by helping people plan ahead and avoid exposure. The goal of this study is to propose an artificial intelligence framework for predicting future air quality based on timing variables (i.e. season, weekday/weekend), future weather forecasts, as well as past pollutant and air quality measurements. The proposed framework utilizes multiple machine learning algorithms (logistic regression, random forest, neural network) with different specifications and averages the results of the three top-performing models to eliminate inaccuracies, weaknesses, and biases from any one individual model. Over time, the proposed framework uses new data to self-adjust model parameters and increase prediction accuracy. To demonstrate its applicability, a prototype of this framework was created to forecast air quality in Los Angeles, California using datasets from the RP4 weather data repository and EPA pollutant measurement data. The results showed good agreement between the framework’s predictions and real-life observations, with an overall 92% model accuracy. The combined model is able to predict more accurately than any of the individual models, and it is able to reliably forecast season-based variations in air quality levels. Top air quality predictor variables were identified through the measurement of mean decrease in accuracy. This study proposed and demonstrated the efficacy of a comprehensive air quality prediction framework leveraging multiple machine learning algorithms to overcome individual algorithm shortcomings. Future enhancements should focus on expanding and testing a greater variety of modeling techniques within the proposed framework, testing the framework in different locations, and developing a platform to automatically publish future predictions in the form of a web or mobile application. Accurate predictions from this artificial intelligence framework can in turn be used to save and improve lives by allowing individuals to protect their health and allowing governments to implement effective pollution control measures.Air pollution is a serious danger to international wellbeing and economies - it will kill an estimated 7 million people every year, costing world economies $2.6 trillion by 2060 due to sick days, healthcare costs, and reduced productivity. In the United States alone, 60,000 premature deaths are caused by poor air quality. For this reason, there is a crucial need to develop effective methods to forecast air quality, which can mitigate air pollution’s detrimental public health effects and associated costs by helping people plan ahead and avoid exposure. The goal of this study is to propose an artificial intelligence framework for predicting future air quality based on timing variables (i.e. season, weekday/weekend), future weather forecasts, as well as past pollutant and air quality measurements. The proposed framework utilizes multiple machine learning algorithms (logistic regression, random forest, neural network) with different specifications and averages the results of the three top-performing models to eliminate inaccuracies, weaknesses, and biases from any one individual model. Over time, the proposed framework uses new data to self-adjust model parameters and increase prediction accuracy. To demonstrate its applicability, a prototype of this framework was created to forecast air quality in Los Angeles, California using datasets from the RP4 weather data repository and EPA pollutant measurement data. The results showed good agreement between the framework’s predictions and real-life observations, with an overall 92% model accuracy. The combined model is able to predict more accurately than any of the individual models, and it is able to reliably forecast season-based variations in air quality levels. Top air quality predictor variables were identified through the measurement of mean decrease in accuracy. This study proposed and demonstrated the efficacy of a comprehensive air quality prediction framework leveraging multiple machine learning algorithms to overcome individual algorithm shortcomings. Future enhancements should focus on expanding and testing a greater variety of modeling techniques within the proposed framework, testing the framework in different locations, and developing a platform to automatically publish future predictions in the form of a web or mobile application. Accurate predictions from this artificial intelligence framework can in turn be used to save and improve lives by allowing individuals to protect their health and allowing governments to implement effective pollution control measures.Air pollution is a serious danger to international wellbeing and economies - it will kill an estimated 7 million people every year, costing world economies $2.6 trillion by 2060 due to sick days, healthcare costs, and reduced productivity. In the United States alone, 60,000 premature deaths are caused by poor air quality. For this reason, there is a crucial need to develop effective methods to forecast air quality, which can mitigate air pollution’s detrimental public health effects and associated costs by helping people plan ahead and avoid exposure. The goal of this study is to propose an artificial intelligence framework for predicting future air quality based on timing variables (i.e. season, weekday/weekend), future weather forecasts, as well as past pollutant and air quality measurements. The proposed framework utilizes multiple machine learning algorithms (logistic regression, random forest, neural network) with different specifications and averages the results of the three top-performing models to eliminate inaccuracies, weaknesses, and biases from any one individual model. Over time, the proposed framework uses new data to self-adjust model parameters and increase prediction accuracy. To demonstrate its applicability, a prototype of this framework was created to forecast air quality in Los Angeles, California using datasets from the RP4 weather data repository and EPA pollutant measurement data. The results showed good agreement between the framework’s predictions and real-life observations, with an overall 92% model accuracy. The combined model is able to predict more accurately than any of the individual models, and it is able to reliably forecast season-based variations in air quality levels. Top air quality predictor variables were identified through the measurement of mean decrease in accuracy. This study proposed and demonstrated the efficacy of a comprehensive air quality prediction framework leveraging multiple machine learning algorithms to overcome individual algorithm shortcomings. Future enhancements should focus on expanding and testing a greater variety of modeling techniques within the proposed framework, testing the framework in different locations, and developing a platform to automatically publish future predictions in the form of a web or mobile application. Accurate predictions from this artificial intelligence framework can in turn be used to save and improve lives by allowing individuals to protect their health and allowing governments to implement effective pollution control measures.

Keywords: air quality prediction, air pollution, artificial intelligence, machine learning algorithms

Procedia PDF Downloads 127

Authors: Shwadhin Sharma

Abstract:

As there has been increasing focus on the shorter attention span of the millennials students, there is a relative absence of instructional tools on behavioral assessments in learning information technology skills within the information systems field and textbooks. This study uses project-based learning in which students gain knowledge and skills related to information technology by working on an extended project that allows students to find a real business problem design information systems based on information collected from the company and develop an information system that solves the problem of the company. Eighty students from two sections of the same course engage in the project from the first week of the class till the sixteenth week of the class to deliver a small business information system that allows them to employ all the skills and knowledge that they learned in the class into the systems they are creating. Computer Information Systems related courses are often difficult to understand and process especially for the Under Representative Minorities students who have limited computer or information systems related (academic) experiences. Project-based learning demands constant attention of the students and forces them to apply knowledge learned in the class to a project that helps retaining knowledge. To make sure our assumption is correct, we started with a pre-test and post-test to test the students learning (of skills) based on the project. Our test showed that almost 90% of the students from the two sections scored higher in post-test as compared to pre-test. Based on this premise, we conducted a further survey that measured student’s job-search preparation, knowledge of data analysis, involved with the course, satisfaction with the course, student’s overall reaction the course and students' ability to meet the traditional learning goals related to the course.

Keywords: project-based learning, job-search preparation, satisfaction with course, traditional learning goals

Procedia PDF Downloads 206

Authors: Klaus Peter Scherer, Daniel Knöll, Constantin Rieder

Abstract:

Problem and Purpose: Intelligent systems are available and helpful to support the human being decision process, especially when complex surgical eye interventions are necessary and must be performed. Normally, such a decision support system consists of a knowledge-based module, which is responsible for the real assistance power, given by an explanation and logical reasoning processes. The interview based acquisition and generation of the complex knowledge itself is very crucial, because there are different correlations between the complex parameters. So, in this project (semi)automated self-learning methods are researched and developed for an enhancement of the quality of such a decision support system. Methods: For ophthalmic data sets of real patients in a hospital, advanced data mining procedures seem to be very helpful. Especially subgroup analysis methods are developed, extended and used to analyze and find out the correlations and conditional dependencies between the structured patient data. After finding causal dependencies, a ranking must be performed for the generation of rule-based representations. For this, anonymous patient data are transformed into a special machine language format. The imported data are used as input for algorithms of conditioned probability methods to calculate the parameter distributions concerning a special given goal parameter. Results: In the field of knowledge discovery advanced methods and applications could be performed to produce operation and patient related correlations. So, new knowledge was generated by finding causal relations between the operational equipment, the medical instances and patient specific history by a dependency ranking process. After transformation in association rules logically based representations were available for the clinical experts to evaluate the new knowledge. The structured data sets take account of about 80 parameters as special characteristic features per patient. For different extended patient groups (100, 300, 500), as well one target value as well multi-target values were set for the subgroup analysis. So the newly generated hypotheses could be interpreted regarding the dependency or independency of patient number. Conclusions: The aim and the advantage of such a semi-automatically self-learning process are the extensions of the knowledge base by finding new parameter correlations. The discovered knowledge is transformed into association rules and serves as rule-based representation of the knowledge in the knowledge base. Even more, than one goal parameter of interest can be considered by the semi-automated learning process. With ranking procedures, the most strong premises and also conjunctive associated conditions can be found to conclude the interested goal parameter. So the knowledge, hidden in structured tables or lists can be extracted as rule-based representation. This is a real assistance power for the communication with the clinical experts.

Keywords: an expert system, knowledge-based support, ophthalmic decision support, self-learning methods

Procedia PDF Downloads 253

Authors: Liliana O. Martínez, Juan E. González, Manuel Ramírez-Aranda, Ana Cervantes-Herrera

Abstract:

In this work, the use of a collection of mathematical challenges and puzzles aimed at students who are starting in algebra is proposed. The selected challenges and puzzles are intended to arouse students' interest in this area of mathematics, in addition to facilitating the teaching-learning process through challenges such as riddles, crossword puzzles, and board games, all in everyday situations that allow them to build themselves the learning. For this, it is proposed to carry out a "Math Rally: algebra" divided into four sections: mathematical reasoning, a hierarchy of operations, fractions, and algebraic equations.

Keywords: algebra, algebraic challenge, algebraic puzzle, math rally

Procedia PDF Downloads 171

Authors: Meng Su

Abstract:

High-dimensional data analysis often presents challenges in capturing the complex, nonlinear relationships and manifold structures inherent to the data. This article presents a novel approach that leverages the strengths of two powerful techniques, Diffusion Maps and Diffusion Probabilistic Models (DPMs), to address these challenges. By integrating the dimensionality reduction capability of Diffusion Maps with the data modeling ability of DPMs, the proposed method aims to provide a comprehensive solution for analyzing and generating high-dimensional data. The Diffusion Map technique preserves the nonlinear relationships and manifold structure of the data by mapping it to a lower-dimensional space using the eigenvectors of the graph Laplacian matrix. Meanwhile, DPMs capture the dependencies within the data, enabling effective modeling and generation of new data points in the low-dimensional space. The generated data points can then be mapped back to the original high-dimensional space, ensuring consistency with the underlying manifold structure. Through a detailed example implementation, the article demonstrates the potential of the proposed hybrid approach to achieve more accurate and effective modeling and generation of complex, high-dimensional data. Furthermore, it discusses possible applications in various domains, such as image synthesis, time-series forecasting, and anomaly detection, and outlines future research directions for enhancing the scalability, performance, and integration with other machine learning techniques. By combining the strengths of Diffusion Maps and DPMs, this work paves the way for more advanced and robust data analysis methods.

Keywords: diffusion maps, diffusion probabilistic models (DPMs), manifold learning, high-dimensional data analysis

Procedia PDF Downloads 108

Authors: J. Miranda, D. Chavarría-Barrientos, M. Ramírez-Cadena, M. E. Macías, P. Ponce, J. Noguez, R. Pérez-Rodríguez, P. K. Wright, A. Molina

Abstract:

Higher education methods need to evolve because the new generations of students are learning in different ways. One way is by adopting emergent technologies, new learning methods and promoting the maker movement. As a result, Tecnologico de Monterrey is developing Open Innovation Laboratories as an immediate response to educational challenges of the world. This paper presents an Open Innovation Laboratory for Rapid Realization of Sensing, Smart and Sustainable Products (S³ Products). The Open Innovation Laboratory is composed of a set of specific resources where students and teachers use them to provide solutions to current problems of priority sectors through the development of a new generation of products. This new generation of products considers the concepts Sensing, Smart, and Sustainable. The Open Innovation Laboratory has been implemented in different courses in the context of New Product Development (NPD) and Integrated Manufacturing Systems (IMS) at Tecnologico de Monterrey. The implementation consists of adapting this Open Innovation Laboratory within the course’s syllabus in combination with the implementation of specific methodologies for product development, learning methods (Active Learning and Blended Learning using Massive Open Online Courses MOOCs) and rapid product realization platforms. Using the concepts proposed it is possible to demonstrate that students can propose innovative and sustainable products, and demonstrate how the learning process could be improved using technological resources applied in the higher educational sector. Finally, examples of innovative S³ products developed at Tecnologico de Monterrey are presented.

Keywords: active learning, blended learning, maker movement, new product development, open innovation laboratory

Procedia PDF Downloads 395

Authors: Zhidong Zhang

Abstract:

This study established a mixed method model in assessing statistics learning with Bayesian network models. There are three variants in exploratory sequential designs. There are three linked steps in one of the designs: qualitative data collection and analysis, quantitative measure, instrument, intervention, and quantitative data collection analysis. The study used a scoring model of analysis of variance (ANOVA) as a content domain. The research study is to examine students’ learning in both semantic and performance aspects at fine grain level. The ANOVA score model, y = α+ βx1 + γx1+ ε, as a cognitive task to collect data during the student learning process. When the learning processes were decomposed into multiple steps in both semantic and performance aspects, a hierarchical Bayesian network was established. This is a theory-driven process. The hierarchical structure was gained based on qualitative cognitive analysis. The data from students’ ANOVA score model learning was used to give evidence to the hierarchical Bayesian network model from the evidential variables. Finally, the assessment results of students’ ANOVA score model learning were reported. Briefly, this was a mixed method research design applied to statistics learning assessment. The mixed methods designs expanded more possibilities for researchers to establish advanced quantitative models initially with a theory-driven qualitative mode.

Keywords: exploratory sequential design, ANOVA score model, Bayesian network model, mixed methods research design, cognitive analysis

Procedia PDF Downloads 179

Authors: Brwa Abdulrahman Abubaker

Abstract:

Recently, there has been a lot of interest in the difficult task of applying reinforcement learning to autonomous mobile robots. Conventional reinforcement learning (TRL) techniques have many drawbacks, such as lengthy computation times, intricate control frameworks, a great deal of trial and error searching, and sluggish convergence. In this paper, a modified Spiking Neural Network (SNN) is used to offer a distinct method for autonomous mobile robot learning and control in unexpected surroundings. As a learning algorithm, the suggested model combines dopamine modulation with spike-timing-dependent plasticity (STDP). In order to create more computationally efficient, biologically inspired control systems that are adaptable to changing settings, this work uses the effective and physiologically credible Izhikevich neuron model. This study is primarily focused on creating an algorithm for target tracking in the presence of obstacles. Results show that the SNN trained with three obstacles yielded an impressive 96% success rate for our proposal, with collisions happening in about 4% of the 214 simulated seconds.

Keywords: spiking neural network, spike-timing-dependent plasticity, dopamine modulation, reinforcement learning

Procedia PDF Downloads 21

Authors: Noriyuki Suyama

Abstract:

The progress and spread of digitalization have led to the provision of a variety of new services. The recent progress in digitization can be attributed to rapid developments in science and technology. First, the research and diffusion of artificial intelligence (AI) has made dramatic progress. Around 2000, the third wave of AI research, which had been underway for about 50 years, arrived. Specifically, machine learning and deep learning were made possible in AI, and the ability of AI to acquire knowledge, define the knowledge, and update its own knowledge in a quantitative manner made the use of big data practical even for commercial PCs. On the other hand, with the spread of social media, information exchange has become more common in our daily lives, and the lending and borrowing of goods and services, in other words, the sharing economy, has become widespread. The scope of this trend is not limited to any industry, and its momentum is growing as the SDGs take root. In addition, the Social Network Service (SNS), a part of social media, has brought about the evolution of the retail business. In the past few years, social network services (SNS) involving users or companies have especially flourished. The People's Republic of China (hereinafter referred to as "China") is a country that is stimulating enormous consumption through its own unique SNS, which is different from the SNS used in developed countries around the world. This paper focuses on the effectiveness and challenges of influencer marketing by focusing on the influence of influencers on users' behavior and satisfaction with Chinese SNSs. Specifically, Conducted was the quantitative survey of Tik Tok users living in China, with the aim of gaining new insights from the analysis and discussions. As a result, we found several important findings and knowledge.

Keywords: customer satisfaction, social networking services, influencer marketing, Chinese consumers’ behavior

Procedia PDF Downloads 89

Authors: Basiliyos Tilahun Betru, Charles Awono Onana, Bernabe Batchakui

Abstract:

Recommender systems have become increasingly popular in recent years, and are utilized in numerous areas. Nowadays many web services provide several information for users and recommender systems have been developed as critical element of these web applications to predict choice of preference and provide significant recommendations. With the help of the advantage of deep learning in modeling different types of data and due to the dynamic change of user preference, building a deep model can better understand users demand and further improve quality of recommendation. In this paper, deep neural network models for recommender system are evaluated. Most of deep neural network models in recommender system focus on the classical collaborative filtering user-item setting. Deep learning models demonstrated high level features of complex data can be learned instead of using metadata which can significantly improve accuracy of recommendation. Even though deep learning poses a great impact in various areas, applying the model to a recommender system have not been fully exploited and still a lot of improvements can be done both in collaborative and content-based approach while considering different contextual factors.

Keywords: big data, decision making, deep learning, recommender system

Procedia PDF Downloads 478

Authors: Sandip Suman

Abstract:

Mechanical defects (cracks, voids, irregularities) in rocket motor propellant are not new and it is induced due to various reasons, which could be an improper manufacturing process, lot-to-lot variation in chemicals or just the natural aging of the products. These defects are normally identified during the examination of radiographic films by quality inspectors. However, a lot of times, these defects are under or over-classified by human inspectors, which leads to unpredictable performance during lot acceptance tests and significant economic loss. The human eye can only visualize larger cracks and defects in the radiographs, and it is almost impossible to visualize every small defect through the human eye. A different artificial intelligence-based machine vision methodology has been proposed in this work to identify and classify the structural defects in the radiographic films of rocket motors with solid propellant. The proposed methodology can extract the features of defects, characterize them, and make intelligent decisions for acceptance or rejection as per the customer requirements. This will automatize the defect detection process during manufacturing with human-like intelligence. It will also significantly reduce production downtime and help to restore processes in the least possible time. The proposed methodology is highly scalable and can easily be transferred to various products and processes.

Keywords: artificial intelligence, machine vision, defect detection, rocket motor propellant grains

Procedia PDF Downloads 98

Authors: Uraib Sharaha, Ahmad Salman, Eladio Rodriguez-Diaz, Elad Shufan, Klaris Riesenberg, Irving J. Bigio, Mahmoud Huleihel

Abstract:

Antimicrobial drugs have an important role in controlling illness associated with infectious diseases in animals and humans. However, the increasing resistance of bacteria to a broad spectrum of commonly used antibiotics has become a global health-care problem. Rapid determination of antimicrobial susceptibility of a clinical isolate is often crucial for the optimal antimicrobial therapy of infected patients and in many cases can save lives. The conventional methods for susceptibility testing like disk diffusion are time-consuming and other method including E-test, genotyping are relatively expensive. Fourier transform infrared (FTIR) microscopy is rapid, safe, and low cost method that was widely and successfully used in different studies for the identification of various biological samples including bacteria. The new modern infrared (IR) spectrometers with high spectral resolution enable measuring unprecedented biochemical information from cells at the molecular level. Moreover, the development of new bioinformatics analyses combined with IR spectroscopy becomes a powerful technique, which enables the detection of structural changes associated with resistivity. The main goal of this study is to evaluate the potential of the FTIR microscopy in tandem with machine learning algorithms for rapid and reliable identification of bacterial susceptibility to antibiotics in time span of few minutes. The bacterial samples, which were identified at the species level by MALDI-TOF and examined for their susceptibility by the routine assay (micro-diffusion discs), are obtained from the bacteriology laboratories in Soroka University Medical Center (SUMC). These samples were examined by FTIR microscopy and analyzed by advanced statistical methods. Our results, based on 550 E.coli samples, were promising and showed that by using infrared spectroscopic technique together with multivariate analysis, it is possible to classify the tested bacteria into sensitive and resistant with success rate higher than 85% for eight different antibiotics. Based on these preliminary results, it is worthwhile to continue developing the FTIR microscopy technique as a rapid and reliable method for identification antibiotic susceptibility.

Keywords: antibiotics, E. coli, FTIR, multivariate analysis, susceptibility

Procedia PDF Downloads 265

Authors: Fetoon K. Algarawi, Wejdan A. Alslamah, Ahlam A. Alhabib, Afnan S. Alfehaid, Dina M. Ibrahim

Abstract:

Over the past 20 years, technology was rapidly developed and no one expected what will come next. Advancements in technology open new opportunities for immersive learning environments. There is a need to transmit education to a level that makes it more effective for the student. Augmented reality is one of the most popular technologies these days. This paper is an experience of applying Augmented Reality (AR) technology using a marker-based approach in E-learning system to transmitting virtual objects into the real-world scenes. We present a marker-based approach for transmitting virtual objects into real-world scenes to explain information in a better way after we developed a mobile phone application. The mobile phone application was then tested on students to determine the extent to which it encouraged them to learn and understand the subjects. In this paper, we talk about how the beginnings of AR, the fields using AR, how AR is effective in education, the spread of AR these days and the architecture of our work. Therefore, the aim of this paper is to prove how creating an interactive e-learning system using AR technology will encourage students to learn more.

Keywords: augmented reality, e-learning, marker-based, monitor-based

Procedia PDF Downloads 223

Authors: Abdulmutallib U. Baraya, Aishatu M. Chadi, Zainab A. Aliyu, Agatha Samson

Abstract:

Learning Resources is the field of study that investigates the process of analyzing, designing, developing, implementing, and evaluating learning materials, learners, and the learning process in order to improve teaching and learning in university-level education essential for empowering students and various sectors of Nigeria’s economy to succeed in a fast-changing global economy. Innovation in the information age of the 21st century is the use of educational technologies in the classroom for instructional delivery, it involves the use of appropriate educational technologies like smart boards, computers, projectors and other projected materials to facilitate learning and improve performance. The study examined learning resources as determinants for improving the teaching and learning process in Abubakar Tafawa Balewa University (ATBU), Bauchi, Bauchi state of Nigeria. Three objectives, three research questions and three null hypotheses guided the study. The study adopted a Survey research design. The population of the study was 880 lecturers. A sample of 260 was obtained using the research advisor table for determining sampling, and 250 from the sample was proportionately selected from the seven faculties. The instrument used for data collection was a structured questionnaire. The instrument was subjected to validation by two experts. The reliability of the instrument stood at 0.81, which is reliable. The researchers, assisted by six research assistants, distributed and collected the questionnaire with a 75% return rate. Data were analyzed using mean and standard deviation to answer the research questions, whereas simple linear regression was used to test the null hypotheses at a 0.05 level of significance. The findings revealed that physical facilities and digital technology tools significantly improved the teaching and learning process. Also, consumables, supplies and equipment do not significantly improve the teaching and learning process in the faculties. It was recommended that lecturers in the various faculties should strengthen and sustain the use of digital technology tools, and there is a need to strive and continue to properly maintain the available physical facilities. Also, the university management should, as a matter of priority, continue to adequately fund and upgrade equipment, consumables and supplies frequently to enhance the effectiveness of the teaching and learning process.

Keywords: education, facilities, learning-resources, technology-tools

Procedia PDF Downloads 23

Authors: Liu Yi Hui

Abstract:

The COVID-19 pandemic in 2020 has globally affected all aspects of life, with social distancing and quarantine orders causing turmoil and learning in community colleges being temporarily paused. In fact, this is the first time that adult education has faced such a severe challenge. It forces researchers to reflect on the impact of pandemics on adult education and ways to respond. Distance learning appears to be one of the pedagogical tools capable of dealing with interpersonal isolation and social distancing caused by the pandemic. This research aims to examine whether the impact of social distancing during COVID-19 will lead to increased acceptance of technology and, subsequently, an increase in adults ’ willingness to participate in distance learning. The hypothesis that social distancing and the desire to participate in distance learning affects learners’ tendency to accept technology is investigated. Teachers ’ participation in distance education and acceptance of technology are used as adjustment variables with the relationship to “social distancing,” “participation in distance learning,” and “acceptance of technology” of learners. A questionnaire survey was conducted over a period of twelve months for teachers and learners at all community colleges in Taiwan who enrolled in a basic unit course. Community colleges were separated using multi-stage cluster sampling, with their locations being metropolitan, non-urban, south, and east as criteria. Using the G*power software, 660 samples were selected and analyzed. The results show that through appropriate pedagogical strategies or teachers ’ own acceptance of technology, adult learners’ willingness to participate in distance learning could be influenced. A diverse model of participation can be developed, improving adult education institutions’ ability to plan curricula to be flexible to avoid the risk associated with epidemic diseases.

Keywords: social distancing, adult learning, community colleges, technology acceptance model

Procedia PDF Downloads 140

Authors: Yasaswi Palagummi, Sareh Rowlands

Abstract:

Generalised Zero-Shot Learning, often known as GZSL, is an advanced variant of zero-shot learning in which the samples in the unseen category may be either seen or unseen. GZSL methods typically have a bias towards the seen classes because they learn a model to perform recognition for both the seen and unseen classes using data samples from the seen classes. This frequently leads to the misclassification of data from the unseen classes into the seen classes, making the task of GZSL more challenging. In this work of ours, to solve the GZSL problem, we propose an approach leveraging the Shifted Window based Self-Attention in the Swin Transformer (Swin-GZSL) to work in the inductive GSZL problem setting. We run experiments on three popular benchmark datasets: CUB, SUN, and AWA2, which are specifically used for ZSL and its other variants. The results show that our model based on Swin Transformer has achieved state-of-the-art harmonic mean for two datasets -AWA2 and SUN and near-state-of-the-art for the other dataset - CUB. More importantly, this technique has a linear computational complexity, which reduces training time significantly. We have also observed less bias than most of the existing GZSL models.

Keywords: generalised, zero-shot learning, inductive learning, shifted-window attention, Swin transformer, vision transformer

Procedia PDF Downloads 71

Authors: Masayuki Mori

Abstract:

This study investigates the relationship between teachers’ perceptions of the usability of classroom space and various elements, including both physical and non-physical, of classroom environments. With the introduction of the GIGA School funding program in Japan in 2019, understanding its impact on learning in classroom space is crucial. The program enabled local educational authorities (LEA) to make it possible to provide one PC/tablet for each student of both elementary and junior high schools. Moreover, at the same time, the program also supported LEA to purchase other electronic devices for educational purposes such as electronic whiteboards, large displays, and real image projectors. A nationwide survey was conducted using random sampling methodology among 100 junior high schools to collect data on classroom space. Of those, 60 schools responded to the survey. The survey covered approximately fifty items, including classroom space size, class size, and educational electronic devices owned. After the data compilation, statistical analysis was used to identify correlations between the variables and to explore the extent to which classroom environment elements influenced teachers’ perceptions. Furthermore, decision tree analysis was applied to visualize the causal relationships between the variables. The findings indicate a significant negative correlation between class size and teachers’ evaluation of usability. In addition to the class size, the way students stored their belongings also influenced teachers’ perceptions. As for the placement of educational electronic devices, the installation of a projector produced a small negative correlation with teachers’ perceptions. The study suggests that while the GIGA School funding program is not significantly influential, traditional educational conditions such as class size have a greater impact on teachers’ perceptions of the usability of classroom space. These results highlight the need for awareness and strategies to integrate various elements in designing the learning environment of the classroom for teachers and students to improve their learning experience.

Keywords: classroom space, GIGA School, questionnaire survey, teachers’ perceptions

Procedia PDF Downloads 21

Authors: Diogo Ferreira Lima Filho, José Roberto Amazonas

Abstract:

Nanotechnology opens the door to new paradigms that introduces a variety of novel tools enabling a plethora of potential applications in the biomedical, industrial, environmental, and military fields. This work proposes an integrated node model by applying the same concepts of TCNet to networks of nanodevices where the nodes are cooperatively interconnected with a low-complexity Mealy Machine (MM) topology integrating in the same electronic system the modules necessary for independent operation in wireless sensor networks (WSNs), consisting of Rectennas (RF to DC power converters), Code Generators based on Finite State Machine (FSM) & Trellis Decoder and On-chip Transmit/Receive with autonomy in terms of energy sources applying the Energy Harvesting technique. This approach considers the use of a Graphene Composite Substrate (GCS) for the integrated electronic circuits meeting the following characteristics: mechanical flexibility, miniaturization, and optical transparency, besides being ecological. In addition, graphene consists of a layer of carbon atoms with the configuration of a honeycomb crystal lattice, which has attracted the attention of the scientific community due to its unique Electrical Characteristics.

Keywords: composite substrate, energy harvesting, finite state machine, graphene, nanotechnology, rectennas, wireless sensor networks

Procedia PDF Downloads 105

Authors: Ehi E. Aimiuwu

Abstract:

As of 2017, many online learning professionals, institutions, and journals are still wondering how instructors can keep student engaged in the online learning environment to facilitate active learning effectively. The purpose of this qualitative single-case and narrative research is to explore whether online professors understand their role as mentors and facilitators of students’ academic success by keeping students engaged in active learning based on personalized experience in the field. Data collection tools that were used in the study included an NVivo 12 Plus qualitative software, an interview protocol, a digital audiotape, an observation sheet, and a transcription. Seven online professors in the United States from LinkedIn and residencies were interviewed for this study. Eleven online teaching techniques from previous research were used as the study framework. Data analysis process, member checking, and key themes were used to achieve saturation. About 85.7% of professors agreed on rubric as the preferred online grading technique. About 57.1% agreed on professors logging in daily, students logging in about 2-5 times weekly, knowing students to increase accountability, email as preferred communication tool, and computer access for adequate online learning. About 42.9% agreed on syllabus for clear class expectations, participation to show what has been learned, and energizing students for creativity.

Keywords: class facilitation, class management, online teaching, online education, pedagogy

Procedia PDF Downloads 116

Authors: Isiya Shinkafi Salihu

Abstract:

Open education resources (OER) are open learning materials in different formats, course content and context to support learning globally. This study investigated the level of awareness of Hospitality and Tourism OER among students in the Department of Tourism and Hotel Management in a University. Specifically, it investigated students’ awareness, use and accessibility of OER in learning. The research design method used was the quantitative approach, using an online questionnaire. The thesis research shows that respondents frequently use OER but with little knowledge of the content and context of the material. Most of the respondents’ have little knowledge about the concept even though they use it. Information and communication technologies are tools for information gathering, social networking and knowledge sharing and transfer. OER are open education materials accessible online such as curriculum, maps, course materials, and videos that users create, adapt, reuse for learning and research. Few of the respondents that used OER in learning faced some challenges such as high cost of data, poor connectivity and lack of proper guidance. The results suggest a lack of awareness of OER among students in the faculty of tourism and the need for support from the teachers in the utilization of OER. The thesis also reveals that some of the international students are accessing the internet as beginners in their studies which require guidance. The research, however, recommends that further studies should be conducted to other faculties.

Keywords: creative commons, open education resources, open licenses, information and communication technology

Procedia PDF Downloads 178