Search results for: realtime recurrent learning

Authors: Yakin Hajlaoui, Richard Labib, Jean-Franc¸ois Plante, Michel Gamache

Abstract:

This study presents the Multi-Layer Inverse Distance Weighting Model (ML-IDW), inspired by the mathematical formulation of both multi-layer neural networks (ML-NNs) and Inverse Distance Weighting model (IDW). ML-IDW leverages ML-NNs’ processing capabilities, characterized by compositions of learnable non-linear functions applied to input features, and incorporates IDW’s ability to learn anisotropic spatial dependencies, presenting a promising solution for nonlinear spatial interpolation and learning from complex spatial data. We employ gradient descent and backpropagation to train ML-IDW. The performance of the proposed model is compared against conventional spatial interpolation models such as Kriging and standard IDW on regression and classification tasks using simulated spatial datasets of varying complexity. Our results highlight the efficacy of ML-IDW, particularly in handling complex spatial dataset, exhibiting lower mean square error in regression and higher F1 score in classification.

Keywords: Deep Learning, Multi-Layer Neural Networks, Gradient Descent, Spatial Interpolation, Inverse Distance Weighting.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 37

Authors: Qiuyu Dai, Haochong Zhang, Xiangrong Liu

Abstract:

Efficient matrix-vector multiplication with diagonal sparse matrices is pivotal in a multitude of computational domains, ranging from scientific simulations to machine learning workloads. When encoded in the conventional Diagonal (DIA) format, these matrices often induce computational overheads due to extensive zero-padding and non-linear memory accesses, which can hamper the computational throughput, and elevate the usage of precious compute and memory resources beyond necessity. The ’DIA-Adaptive’ approach, a methodological enhancement introduced in this paper, confronts these challenges head-on by leveraging the advanced parallel instruction sets embedded within Machine Learning Units (MLUs). This research presents a thorough analysis of the DIA-Adaptive scheme’s efficacy in optimizing Sparse Matrix-Vector Multiplication (SpMV) operations. The scope of the evaluation extends to a variety of hardware architectures, examining the repercussions of distinct thread allocation strategies and cluster configurations across multiple storage formats. A dedicated computational kernel, intrinsic to the DIA-Adaptive approach, has been meticulously developed to synchronize with the nuanced performance characteristics of MLUs. Empirical results, derived from rigorous experimentation, reveal that the DIA-Adaptive methodology not only diminishes the performance bottlenecks associated with the DIA format but also exhibits pronounced enhancements in execution speed and resource utilization. The analysis delineates a marked improvement in parallelism, showcasing the DIA-Adaptive scheme’s ability to adeptly manage the interplay between storage formats, hardware capabilities, and algorithmic design. The findings suggest that this approach could set a precedent for accelerating SpMV tasks, thereby contributing significantly to the broader domain of high-performance computing and data-intensive applications.

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

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 235

Authors: Seyoung Kim, Jeongmin Kim, Kwang Ryel Ryu

Abstract:

A database that records average traffic speeds measured at five-minute intervals for all the links in the traffic network of a metropolitan city. While learning from this data the models that can predict future traffic speed would be beneficial for the applications such as the car navigation system, building predictive models for every link becomes a nontrivial job if the number of links in a given network is huge. An advantage of adopting k-nearest neighbor (k-NN) as predictive models is that it does not require any explicit model building. Instead, k-NN takes a long time to make a prediction because it needs to search for the k-nearest neighbors in the database at prediction time. In this paper, we investigate how much we can speed up k-NN in making traffic speed predictions by reducing the amount of data to be searched for without a significant sacrifice of prediction accuracy. The rationale behind this is that we had a better look at only the recent data because the traffic patterns not only repeat daily or weekly but also change over time. In our experiments, we build several different k-NN models employing different sets of features which are the current and past traffic speeds of the target link and the neighbor links in its up/down-stream. The performances of these models are compared by measuring the average prediction accuracy and the average time taken to make a prediction using various amounts of data.

Keywords: Big data, k-NN, machine learning, traffic speed prediction.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1376

Authors: S. Sarumathi, P. Ranjetha, C. Saraswathy, M. Vaishnavi, S. Geetha

Abstract:

Clustering is an unsupervised learning technique for aggregating data objects into meaningful classes so that intra cluster similarity is maximized and inter cluster similarity is minimized in data mining. However, no single clustering algorithm proves to be the most effective in producing the best result. As a result, a new challenging technique known as the cluster ensemble approach has blossomed in order to determine the solution to this problem. For the cluster analysis issue, this new technique is a successful approach. The cluster ensemble's main goal is to combine similar clustering solutions in a way that achieves the precision while also improving the quality of individual data clustering. Because of the massive and rapid creation of new approaches in the field of data mining, the ongoing interest in inventing novel algorithms necessitates a thorough examination of current techniques and future innovation. This paper presents a comparative analysis of various cluster ensemble approaches, including their methodologies, formal working process, and standard accuracy and error rates. As a result, the society of clustering practitioners will benefit from this exploratory and clear research, which will aid in determining the most appropriate solution to the problem at hand.

Keywords: Clustering, cluster ensemble methods, consensus function, data mining, unsupervised learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 821

Authors: M. Zerikat, S. Chekroun

Abstract:

This paper proposes an effective adaptation learning algorithm based on artificial neural networks for speed control of an induction motor assumed to operate in a high-performance drives environment. The structure scheme consists of a neural network controller and an algorithm for changing the NN weights in order that the motor speed can accurately track of the reference command. This paper also makes uses a very realistic and practical scheme to estimate and adaptively learn the noise content in the speed load torque characteristic of the motor. The availability of the proposed controller is verified by through a laboratory implementation and under computation simulations with Matlab-software. The process is also tested for the tracking property using different types of reference signals. The performance and robustness of the proposed control scheme have evaluated under a variety of operating conditions of the induction motor drives. The obtained results demonstrate the effectiveness of the proposed control scheme system performances, both in steady state error in speed and dynamic conditions, was found to be excellent and those is not overshoot.

Keywords: Electric drive, Induction motor, speed control, Adaptive control, neural network, High Performance.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2027

Authors: S. Odeh, E. Abdelghani

Abstract:

Collaborative working environments for distance education can be considered as a more generic form of contemporary remote labs. At present, the majority of existing real laboratories are not constructed to allow the involved participants to collaborate in real time. To make this revolutionary learning environment possible we must allow the different users to carry out an experiment simultaneously. In recent times, multi-user environments are successfully applied in many applications such as air traffic control systems, team-oriented military systems, chat-text tools, multi-player games etc. Thus, understanding the ideas and techniques behind these systems could be of great importance in the contribution of ideas to our e-learning environment for collaborative working. In this investigation, collaborative working environments from theoretical and practical perspectives are considered in order to build an effective collaborative real laboratory, which allows two students or more to conduct remote experiments at the same time as a team. In order to achieve this goal, we have implemented distributed system architecture, enabling students to obtain an automated help by either a human tutor or a rule-based e-tutor.

Keywords: Collaboration environment, e-tutor, multi-user environments, socio-technical system.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1483

Authors: Ifeyinwa E. Achumba, Djamel Azzi, Rinat Khusainov

Abstract:

There are three approaches to complete Bayesian Network (BN) model construction: total expert-centred, total datacentred, and semi data-centred. These three approaches constitute the basis of the empirical investigation undertaken and reported in this paper. The objective is to determine, amongst these three approaches, which is the optimal approach for the construction of a BN-based model for the performance assessment of students- laboratory work in a virtual electronic laboratory environment. BN models were constructed using all three approaches, with respect to the focus domain, and compared using a set of optimality criteria. In addition, the impact of the size and source of the training, on the performance of total data-centred and semi data-centred models was investigated. The results of the investigation provide additional insight for BN model constructors and contribute to literature providing supportive evidence for the conceptual feasibility and efficiency of structure and parameter learning from data. In addition, the results highlight other interesting themes.

Keywords: Bayesian networks, model construction, parameterlearning, structure learning, performance index, model comparison.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1727

Authors: Rohan Putatunda, Aryya Gangopadhyay

Abstract:

Acoustic sensors, if embedded in smart street lights, can help in capturing the activities (car honking, sirens, events, traffic, etc.) in cities. Needless to say, the acoustic data from such scenarios are complex due to multiple audio streams originating from different events, and when decomposed to independent signals, the amount of retrieved data volume is small in quantity which is inadequate to train deep neural networks. So, in this paper, we address the two challenges: a) separating the mixed signals, and b) developing an efficient acoustic classifier under data paucity. So, to address these challenges, we propose an architecture with supervised deep learning, where the initial captured mixed acoustics data are analyzed with Fast Fourier Transformation (FFT), followed by filtering the noise from the signal, and then decomposed to independent signals by fast independent component analysis (Fast ICA). To address the challenge of data paucity, we propose a multi feature-based deep neural network with high performance that is reflected in our experiments when compared to the conventional convolutional neural network (CNN) and multi-layer perceptron (MLP).

Keywords: FFT, ICA, vehicle classification, multi-feature DNN, CNN, MLP.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 432

Authors: J. P. Dubois, O. M. Abdul-Latif

Abstract:

Support Vector Machine (SVM) is a statistical learning tool that was initially developed by Vapnik in 1979 and later developed to a more complex concept of structural risk minimization (SRM). SVM is playing an increasing role in applications to detection problems in various engineering problems, notably in statistical signal processing, pattern recognition, image analysis, and communication systems. In this paper, SVM was applied to the detection of medical ultrasound images in the presence of partially developed speckle noise. The simulation was done for single look and multi-look speckle models to give a complete overlook and insight to the new proposed model of the SVM-based detector. The structure of the SVM was derived and applied to clinical ultrasound images and its performance in terms of the mean square error (MSE) metric was calculated. We showed that the SVM-detected ultrasound images have a very low MSE and are of good quality. The quality of the processed speckled images improved for the multi-look model. Furthermore, the contrast of the SVM detected images was higher than that of the original non-noisy images, indicating that the SVM approach increased the distance between the pixel reflectivity levels (detection hypotheses) in the original images.

Keywords: LS-SVM, medical ultrasound imaging, partially developed speckle, multi-look model.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1341

Authors: Vladimir Simovic, Matija Varga, Tonco Marusic

Abstract:

This research paper shows matrix technology models and examples of information systems in education (in the Republic of Croatia and in the Germany) in support of business, education (when learning and teaching) and e-learning. Here we researched and described the aims and objectives of the main process in education and technology, with main matrix classes of data. In this paper, we have example of matrix technology with detailed description of processes related to specific data classes in the processes of education and an example module that is support for the process: ‘Filling in the directory and the diary of work’ and ‘evaluation’. Also, on the lower level of the processes, we researched and described all activities which take place within the lower process in education. We researched and described the characteristics and functioning of modules: ‘Fill the directory and the diary of work’ and ‘evaluation’. For the analysis of the affinity between the aforementioned processes and/or sub-process we used our application model created in Visual Basic, which was based on the algorithm for analyzing the affinity between the observed processes and/or sub-processes.

Keywords: Designing, education management, information systems, matrix technology, process affinity.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1096

Authors: P. Phenpun, S. Wareewan

Abstract:

This qualitative study aimed to describe the opinions in relation to humanized care emerging from the volunteer activities of nursing students at Boromarajonani College of Nursing, Chonburi, Thailand. One hundred and twenty-seven second-year nursing students participated in this study. The volunteer activity model was composed of preparation, implementation, and evaluation through a learning log, in which students were encouraged to write their daily activities after completing practical training at the healthcare center. The preparation content included three main categories: service minded, analytical thinking, and client participation. The preparation process took over three days that accumulates up to 20 hours only. The implementation process was held over 10 days, but with a total of 70 hours only, with participants taking part in volunteer work activities at a healthcare center. A learning log was used for evaluation and data were analyzed using content analysis. The findings were as follows. With service minded, there were two subcategories that emerged from volunteer activities, which were service minded towards patients and within themselves. There were three categories under service minded towards patients, which were rapport, compassion, and empathy service behaviors, and there were four categories under service minded within themselves, which were self-esteem, self-value, management potential, and preparedness in providing good healthcare services. In line with analytical thinking, there were two components of analytical thinking, which were analytical skill for their works and analytical thinking for themselves. There were four subcategories under analytical thinking for their works, which were evidence based thinking, real situational thinking, cause analysis thinking, and systematic thinking, respectively. There were four subcategories under analytical thinking for themselves, which were comparative between themselves, towards their clients that leads to the changing of their service behaviors, open-minded thinking, modernized thinking, and verifying both verbal and non-verbal cues. Lastly, there were three categories under participation, which were mutual rapport relationship; reconsidering client’s needs services and providing useful health care information.

Keywords: Humanized care service, volunteer activity, nursing student, and learning log.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1571

Authors: Leandro Marcos Alves Vaz

Abstract:

The teaching of physics in Brazilian public schools emphasizes strongly the theoretical aspects of this science, showing its philosophical and mathematical basis, but neglecting its experimental character. Perhaps the lack of science laboratories explains this practice. In this work, we present a method of teaching physics using the computer. As alternatives to real experiments, we have the trials through simulators, many of which are free software available on the internet. In order to develop a study on the use of simulators in teaching, knowing the impossibility of simulations on all topics in a given subject, we combined these programs with phenomenological and/or experimental texts in order to mitigate this limitation. This study proposes the use of simulators and the debate using phenomenological/experimental texts on electrostatic theme in groups of the 3rd year of EJA (Adult and Youth Education) in order to verify the advantages of this methodology. Some benefits of the hybridization of the traditional method with the tools used were: Greater motivation of the students in learning, development of experimental notions, proactive socialization to learning, greater easiness to understand some concepts and the creation of collaborative activities that can reduce timidity of part of the students.

Keywords: Physics teaching, simulators, youth and adult education, experimentation, electrostatic.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1190

Authors: Andreas Heindl, Alexander K. Seewald, Martin Schepelmann, Radu Rogojanu, Giovanna Bises, Theresia Thalhammer, Isabella Ellinger

Abstract:

Bone remodeling occurs by the balanced action of bone resorbing osteoclasts (OC) and bone-building osteoblasts. Increased bone resorption by excessive OC activity contributes to malignant and non-malignant diseases including osteoporosis. To study OC differentiation and function, OC formed in in vitro cultures are currently counted manually, a tedious procedure which is prone to inter-observer differences. Aiming for an automated OC-quantification system, classification of OC and precursor cells was done on fluorescence microscope images based on the distinct appearance of fluorescent nuclei. Following ellipse fitting to nuclei, a combination of eight features enabled clustering of OC and precursor cell nuclei. After evaluating different machine-learning techniques, LOGREG achieved 74% correctly classified OC and precursor cell nuclei, outperforming human experts (best expert: 55%). In combination with the automated detection of total cell areas, this system allows to measure various cell parameters and most importantly to quantify proteins involved in osteoclastogenesis.

Keywords: osteoclasts, machine learning, ellipse fitting.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1913

Authors: Agni Stylianou-Georgiou, Eliza Pitri

Abstract:

This study is a design narrative that discusses researchers’ new learning based on changes made in pedagogies and learning opportunities in the context of a Cognitive Psychology and an Art History undergraduate course. The purpose of this study was to investigate how to encourage creative problem-based play in tertiary education engaging instructors and student-teachers in designing educational games. Course instructors modified content to encourage flexible thinking during game design problem-solving. Qualitative analyses of data sources indicated that Thinking Birds’ questions could encourage flexible thinking as instructors engaged in creative problem-based play. However, student-teachers demonstrated weakness in adopting flexible thinking during game design problem solving. Further studies of student-teachers’ shifting perspectives during different instructional design tasks would provide insights for developing the Thinking Birds’ questions as tools for creative problem solving.

Keywords: Creative problem-based play, educational games, flexible thinking, tertiary education.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 884

Authors: Sacide Güzin Mazman, Yasemin Koçak Usluel

Abstract:

Possible advantages of technology in educational context required the defining boundaries of formal and informal learning. Increasing opportunity to ubiquitous learning by technological support has revealed a question of how to discover the potential of individuals in the spontaneous environments such as social networks. This seems to be related with the question of what purposes in social networks have been being used? Social networks provide various advantages in educational context as collaboration, knowledge sharing, common interests, active participation and reflective thinking. As a consequence of these, the purpose of this study is composed of proposing a new model that could determine factors which effect adoption of social network applications for usage in educational context. While developing a model proposal, the existing adoption and diffusion models have been reviewed and they are thought to be suitable on handling an original perspective instead of using completely other diffusion or acceptance models because of different natures of education from other organizations. In the proposed model; social factors, perceived ease of use, perceived usefulness and innovativeness are determined four direct constructs that effect adoption process. Facilitating conditions, image, subjective norms and community identity are incorporated to model as antecedents of these direct four constructs.

Keywords: Adoption of innovation, educational context, social networks.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3877

Authors: Rishabh Garg, Anuja Vyas, Aamna Khan, Muhammad Azwan Tariq

Abstract:

The present study focuses on integrating Machine Learning and Genomics, hereafter termed ‘GenoLearning’, to develop Artificial Life (AL). This is achieved by leveraging gene editing to imbue genes with sequences capable of performing desired functions. To accomplish this, a specialized sub-network of Siamese Neural Network (SNN), named Transformer Architecture specialized in Sequence Analysis of Genes (TASAG), compares two sequences: the desired and target sequences. Differences between these sequences are analyzed, and necessary edits are made on-screen to incorporate the desired sequence into the target sequence. The edited sequence can then be synthesized chemically using a Computerized DNA Synthesizer (CDS). The CDS fabricates DNA strands according to the sequence displayed on a computer screen, aided by microprocessors. These synthesized DNA strands can be inserted into an ovum to initiate further development, eventually leading to the creation of an Embot, and ultimately, an H-Bot. While this study aims to explore the potential benefits of Artificial Intelligence (AI) technology, it also acknowledges and addresses the ethical considerations associated with its implementation.

Keywords: Machine Learning, Genomics, Genetronics, DNA, Transformer, Siamese Neural Network, Gene Editing, Artificial Life, H-Bot, Zoobot.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 76

Authors: Yassamina Berkane, Leïla Kloul, Yoann Demoli

Abstract:

Quality of life, environmental impact, congestion of mobility means, and infrastructures remain significant challenges for urban mobility. Solutions like car sharing, spatial redesign, eCommerce, and autonomous vehicles will likely increase the unit veh-km and the density of cars in urban traffic, thus reducing congestion. However, the impact of such solutions is not clear for researchers. Congestion arises from growing populations that must travel greater distances to arrive at similar locations (e.g., workplaces, schools) during the same time frame (e.g., rush hours). This paper first reviews the research and application cases of urban congestion methods through recent years. Rethinking the question of time, it then investigates people’s willingness and flexibility to adapt their arrival and departure times from workplaces. We use neural networks and methods of supervised learning to apply a methodology for predicting peoples’ intentions from their responses in a questionnaire. We created and distributed a questionnaire to more than 50 companies in the Paris suburb. Obtained results illustrate that our methodology can predict peoples’ intentions to reschedule their activities (work, study, commerce, etc.).

Keywords: Urban mobility, decongestion, machine learning, neural network.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 481

Authors: A. M. Pashayev, D. D. Askerov, C. Ardil, R. A. Sadiqov, P. S. Abdullayev

Abstract:

Researches show that probability-statistical methods application, especially at the early stage of the aviation Gas Turbine Engine (GTE) technical condition diagnosing, when the flight information has property of the fuzzy, limitation and uncertainty is unfounded. Hence the efficiency of application of new technology Soft Computing at these diagnosing stages with the using of the Fuzzy Logic and Neural Networks methods is considered. According to the purpose of this problem training with high accuracy of fuzzy multiple linear and non-linear models (fuzzy regression equations) which received on the statistical fuzzy data basis is made. For GTE technical condition more adequate model making dynamics of skewness and kurtosis coefficients- changes are analysed. Researches of skewness and kurtosis coefficients values- changes show that, distributions of GTE work parameters have fuzzy character. Hence consideration of fuzzy skewness and kurtosis coefficients is expedient. Investigation of the basic characteristics changes- dynamics of GTE work parameters allows drawing conclusion on necessity of the Fuzzy Statistical Analysis at preliminary identification of the engines' technical condition. Researches of correlation coefficients values- changes shows also on their fuzzy character. Therefore for models choice the application of the Fuzzy Correlation Analysis results is offered. At the information sufficiency is offered to use recurrent algorithm of aviation GTE technical condition identification (Hard Computing technology is used) on measurements of input and output parameters of the multiple linear and non-linear generalised models at presence of noise measured (the new recursive Least Squares Method (LSM)). The developed GTE condition monitoring system provides stageby- stage estimation of engine technical conditions. As application of the given technique the estimation of the new operating aviation engine technical condition was made.

Keywords: aviation gas turbine engine, technical condition, fuzzy logic, neural networks, fuzzy statistics

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1570

Authors: Sunee Pongpinigpinyo, Wanchai Rivepiboon

Abstract:

Word sense disambiguation is one of the most important open problems in natural language processing applications such as information retrieval and machine translation. Many approach strategies can be employed to resolve word ambiguity with a reasonable degree of accuracy. These strategies are: knowledgebased, corpus-based, and hybrid-based. This paper pays attention to the corpus-based strategy that employs an unsupervised learning method for disambiguation. We report our investigation of Latent Semantic Indexing (LSI), an information retrieval technique and unsupervised learning, to the task of Thai noun and verbal word sense disambiguation. The Latent Semantic Indexing has been shown to be efficient and effective for Information Retrieval. For the purposes of this research, we report experiments on two Thai polysemous words, namely  /hua4/ and /kep1/ that are used as a representative of Thai nouns and verbs respectively. The results of these experiments demonstrate the effectiveness and indicate the potential of applying vector-based distributional information measures to semantic disambiguation.

Keywords: Distributional semantics, Latent Semantic Indexing, natural language processing, Polysemous words, unsupervisedlearning, Word Sense Disambiguation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1814

Authors: Hernán G. Cortés-Mora, José I. Péna-Reyes, Alfonso Herrera-Jiménez

Abstract:

This article describes the implementation experience of Project-Based Learning (PBL) in an engineering course of the Universidad Nacional de Colombia, with the aim of strengthening student skills necessary for the exercise of their profession under a sustainability framework. Firstly, we present a literature review on the education for sustainability field, emphasizing the skills and knowledge areas required for its development, as well as the commitment of the Faculty of Engineering of the Universidad Nacional de Colombia, and other engineering faculties of the country, regarding education for sustainability. This article covers the general aspects of the course, describes how students team were formed, and how their experience was during the first semester of 2017. During this period two groups of students decided to develop their course project aiming to solve a problem regarding a Non-Governmental Organization (NGO) that works with head-of-household mothers in a low-income neighborhood in Bogota (Colombia). Subsequently, we show how sustainability is involved in the course, how tools are provided to students, and how activities are developed as to strengthen their abilities, which allows them to incorporate sustainability in their projects while also working on the methodology used to develop said projects. Finally, we introduce the results obtained by the students who sent the prototypes of their projects to the community they were working on and the conclusions reached by them regarding the course experience.

Keywords: Sustainability, project based learning, engineering education, higher education for sustainability.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 822

Authors: Georgia H. Mega

Abstract:

Street art, a category of artwork displayed in public spaces, has been recognized as a potential tool for promoting reflective thinking in both adult and primary education. Educational techniques that encourage critical and creative thinking, as well as deeper reflection, have been developed and applied in educational curricula. This paper aims to explore the potential of art street in cultivating learners' reflective awareness towards multiculturalism. More specifically, two artworks displayed in public spaces have been selected: the artwork of Kleomenis Kostopoulos and the artwork of Rustam Obic. The reason of this selection is because of their strong symbolism towards multiculturalism. The street arts have been elaborated by adult (+18) and minor students (K-12) in educational settings, under the same educator’s guidance, following appropriate for each age learning techniques. Adults cultivate their reflection using Freire’s learning method, whereas minors cultivate critical thinking using visible thinking techniques from Project Zero. Through qualitative methodology (context analysis) the depth of reflection/critical thinking has been emphasized for both age groups. The case study shows that street art can play a significant role to the promotion/cultivation of deep thinking towards challenging contemporary phenomena like multiculturalism.

Keywords: Street art, observation of art works, reflective awareness, educational techniques, multiculturalism.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 99

Authors: M. A. S. Fahim, J. Sužiedelytė Visockienė

Abstract:

With the growing concern over air pollution (AP), it is clear that this has gained more prominence than ever before. The level of consciousness has increased and a sense of knowledge now has to be forwarded as a duty by those enlightened enough to disseminate it to others. This realization often comes after an understanding of how poor air quality indices (AQI) damage human health. The study focuses on assessing air pollution prediction models specifically for Lithuania, addressing a substantial need for empirical research within the region. Concentrating on Vilnius, it specifically examines particulate matter concentrations 10 micrometers or less in diameter (PM10). Utilizing Gaussian Process Regression (GPR) and Regression Tree Ensemble, and Regression Tree methodologies, predictive forecasting models are validated and tested using hourly data from January 2020 to December 2022. The study explores the classification of AP data into anthropogenic and natural sources, the impact of AP on human health, and its connection to cardiovascular diseases. The study revealed varying levels of accuracy among the models, with GPR achieving the highest accuracy, indicated by an RMSE of 4.14 in validation and 3.89 in testing.

Keywords: Air pollution, anthropogenic and natural sources, machine learning, Gaussian process regression, tree ensemble, forecasting models, particulate matter.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 119

Authors: O. S. Ebrahim, K. O. Shawky, M. A. Badr, P. K. Jain

Abstract:

This paper proposes an intelligent, supervisory, hysteresis liquid-level control with three-state energy saving mode (ESM) for induction motor (IM) in fluid transportation system (FTS) including storage tank. The IM pump drive comprises a modified star/delta switch and hydromantic coupler. Three-state ESM is defined, along with the normal running, and named analog to the computer’s ESMs as follows: Sleeping mode in which the motor runs at no load with delta stator connection, hibernate mode in which the motor runs at no load with a star connection, and motor shutdown is the third energy saver mode. Considering the motor’s thermal capacity used (TCU) and grid-compatible tariff structure, a logic flow-chart is synthesized to select the motor state at no-load for best energetic cost reduction. Fuzzy-logic (FL) based availability assessment is designed and deployed on cloud, in order to provide mobilized service for the star/delta switch and highly reliable contactors. Moreover, an artificial neural network (ANN) state estimator, based on the recurrent architecture, is constructed and learned in order to provide fault-tolerant capability for the supervisory controller. Sequential test of Wald is used for sensor fault detection. Theoretical analysis, preliminary experimental testing and computer simulations are performed to demonstrate the validity and effectiveness of the proposed control system in terms of reliability, power quality and operational cost reduction with a motivation of power factor correction.

Keywords: Artificial Neural Network, ANN, Contactor Health Assessment, Energy Saving Mode, Induction Machine, IM, Supervisory Control, Fluid Transportation, Fuzzy Logic, FL, cloud computing, pumped storage.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 446

Authors: Jiann-Ming Wu, Hsiao-Chang Chen, Chun-Chang Wu, Pei-Hsun Hsu

Abstract:

This work explores blind image deconvolution by recursive function approximation based on supervised learning of neural networks, under the assumption that a degraded image is linear convolution of an original source image through a linear shift-invariant (LSI) blurring matrix. Supervised learning of neural networks of radial basis functions (RBF) is employed to construct an embedded recursive function within a blurring image, try to extract non-deterministic component of an original source image, and use them to estimate hyper parameters of a linear image degradation model. Based on the estimated blurring matrix, reconstruction of an original source image from a blurred image is further resolved by an annealed Hopfield neural network. By numerical simulations, the proposed novel method is shown effective for faithful estimation of an unknown blurring matrix and restoration of an original source image.

Keywords: Blind image deconvolution, linear shift-invariant(LSI), linear image degradation model, radial basis functions (rbf), recursive function, annealed Hopfield neural networks.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2061

Authors: Shivangi Agrawal, Hsiu-I Ting

Abstract:

Entrepreneurship is an essential source of economic growth and a prominent factor influencing socio-economic development. Entrepreneurship education educates and enhances entrepreneurial activity. This study aims to understand current trends in entrepreneurship education and evaluate the effectiveness of diverse entrepreneurship education programs. An increasing number of universities offer entrepreneurship education courses to create and successfully continue entrepreneurial ventures. Despite the prevalence of entrepreneurship education, research studies lack inconsistency about the effectiveness of entrepreneurship education to promote and develop entrepreneurship. Strategies to develop entrepreneurial attitudes and intentions among individuals are hindered by a lack of understanding of entrepreneurs' educational purposes, components, methodology, and resources required. Lack of adequate entrepreneurship education has been linked with low self-efficacy and lack of entrepreneurial intent. Moreover, in the age of digitisation and during the COVID-19 pandemic, digital learning platforms (e.g. online entrepreneurship education courses and programs) and other digital tools (e.g. digital game-based entrepreneurship education) have become more relevant to entrepreneurship education. This paper contributes to the continuation of academic literature in entrepreneurship education by evaluating and assessing current trends in entrepreneurship education programs, leading to better understanding to reduce gaps between entrepreneurial development requirements and higher education institutions.

Keywords: entrepreneurship education, digital technologies, academic entrepreneurship, COVID-19

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1707

Authors: S. Shubha, B. N. Meera

Abstract:

Physics Education Research (PER) results have shown that students do not achieve the expected level of competency in understanding the concepts of different domains of Physics learning when taught by the traditional teaching methods, the concepts of Electricity and Magnetism (E&M) being one among them. Simulation being one of the valuable instructional tools renders an opportunity to visualize varied experiences with such concepts. Considering the electric force concept which requires extensive use of vector representations, we report here the outcome of the research results pertaining to the student understanding of this concept and the role of simulation in using vector representation. The simulation platform provides a positive impact on the use of vector representation. The first stage of this study involves eliciting and analyzing student responses to questions that probe their understanding of the concept of electrostatic force and this is followed by four stages of student interviews as they use the interactive simulations of electric force in one dimension. Student responses to the questions are recorded in real time using electronic pad. A validation test interview is conducted to evaluate students' understanding of the electric force concept after using interactive simulation. Results indicate lack of procedural knowledge of the vector representation. The study emphasizes the need for the choice of appropriate simulation and mode of induction for learning.

Keywords: Electric Force, Interactive, Representation, Simulation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2233

Authors: Hany Alashwal, Safaai Deris, Razib M. Othman

Abstract:

Understanding proteins functions is a major goal in the post-genomic era. Proteins usually work in context of other proteins and rarely function alone. Therefore, it is highly relevant to study the interaction partners of a protein in order to understand its function. Machine learning techniques have been widely applied to predict protein-protein interactions. Kernel functions play an important role for a successful machine learning technique. Choosing the appropriate kernel function can lead to a better accuracy in a binary classifier such as the support vector machines. In this paper, we describe a Bayesian kernel for the support vector machine to predict protein-protein interactions. The use of Bayesian kernel can improve the classifier performance by incorporating the probability characteristic of the available experimental protein-protein interactions data that were compiled from different sources. In addition, the probabilistic output from the Bayesian kernel can assist biologists to conduct more research on the highly predicted interactions. The results show that the accuracy of the classifier has been improved using the Bayesian kernel compared to the standard SVM kernels. These results imply that protein-protein interaction can be predicted using Bayesian kernel with better accuracy compared to the standard SVM kernels.

Keywords: Bioinformatics, Protein-protein interactions, Bayesian Kernel, Support Vector Machines.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2164

Authors: Hira Lal Gope, Hidekazu Fukai

Abstract:

The aim of this study is to develop a system which can identify and sort peaberries automatically at low cost for coffee producers in developing countries. In this paper, the focus is on the classification of peaberries and normal coffee beans using image processing and machine learning techniques. The peaberry is not bad and not a normal bean. The peaberry is born in an only single seed, relatively round seed from a coffee cherry instead of the usual flat-sided pair of beans. It has another value and flavor. To make the taste of the coffee better, it is necessary to separate the peaberry and normal bean before green coffee beans roasting. Otherwise, the taste of total beans will be mixed, and it will be bad. In roaster procedure time, all the beans shape, size, and weight must be unique; otherwise, the larger bean will take more time for roasting inside. The peaberry has a different size and different shape even though they have the same weight as normal beans. The peaberry roasts slower than other normal beans. Therefore, neither technique provides a good option to select the peaberries. Defect beans, e.g., sour, broken, black, and fade bean, are easy to check and pick up manually by hand. On the other hand, the peaberry pick up is very difficult even for trained specialists because the shape and color of the peaberry are similar to normal beans. In this study, we use image processing and machine learning techniques to discriminate the normal and peaberry bean as a part of the sorting system. As the first step, we applied Deep Convolutional Neural Networks (CNN) and Support Vector Machine (SVM) as machine learning techniques to discriminate the peaberry and normal bean. As a result, better performance was obtained with CNN than with SVM for the discrimination of the peaberry. The trained artificial neural network with high performance CPU and GPU in this work will be simply installed into the inexpensive and low in calculation Raspberry Pi system. We assume that this system will be used in under developed countries. The study evaluates and compares the feasibility of the methods in terms of accuracy of classification and processing speed.

Keywords: Convolutional neural networks, coffee bean, peaberry, sorting, support vector machine.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1553

Authors: Marco Leite, J. M. Vilas-Boas da Silva, Isabel Duarte de Almeida

Abstract:

New Product Development (NPD) has got its roots on an Engineering background. Thus, one might wonder about the interest, opportunity, contents and delivery process, if students from soft sciences were involved. This paper addressed «What to teach?» and «How to do it?», as the preliminary research questions that originated the introduced propositions. The curriculum-developer model that was purposefully chosen to adapt the coursebook by pursuing macro/micro strategies was found significant by an exploratory qualitative case study. Moreover, learning was developed and value created by implementing the institutional curriculum through a creative, hands-on, experiencing, problem-solving, problem-based but organized teamwork approach. Product design of an orange squeezer complying with ill-defined requirements, including drafts, sketches, prototypes, CAD simulations and a business plan, plus a website, written reports and presentations were the deliverables that confirmed an innovative contribution towards research and practice of teaching and learning of engineering subjects to non-specialist operations managers candidates.

Keywords: Teaching Engineering to Non-specialists, Operations Managers Education, Teamwork, Product Design and Development, Market- driven NPD, Curriculum development.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2410

Authors: Rami Rashkovits, Ilana Lavy

Abstract:

In this study we present our developed formative assessment tool for students' assignments. The tool enables lecturers to define assignments for the course and assign each problem in each assignment a list of criteria and weights by which the students' work is evaluated. During assessment, the lecturers feed the scores for each criterion with justifications. When the scores of the current assignment are completely fed in, the tool automatically generates reports for both students and lecturers. The students receive a report by email including detailed description of their assessed work, their relative score and their progress across the criteria along the course timeline. This information is presented via charts generated automatically by the tool based on the scores fed in. The lecturers receive a report that includes summative (e.g., averages, standard deviations) and detailed (e.g., histogram) data of the current assignment. This information enables the lecturers to follow the class achievements and adjust the learning process accordingly. The tool was examined on two pilot groups of college students that study a course in (1) Object-Oriented Programming (2) Plane Geometry. Results reveal that most of the students were satisfied with the assessment process and the reports produced by the tool. The lecturers who used the tool were also satisfied with the reports and their contribution to the learning process.

Keywords: Computer-based formative assessment tool, science education.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1891