Search results for: machine learning
Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 8530

Search results for: machine learning

6910 Mining Big Data in Telecommunications Industry: Challenges, Techniques, and Revenue Opportunity

Authors: Hoda A. Abdel Hafez

Abstract:

Mining big data represents a big challenge nowadays. Many types of research are concerned with mining massive amounts of data and big data streams. Mining big data faces a lot of challenges including scalability, speed, heterogeneity, accuracy, provenance and privacy. In telecommunication industry, mining big data is like a mining for gold; it represents a big opportunity and maximizing the revenue streams in this industry. This paper discusses the characteristics of big data (volume, variety, velocity and veracity), data mining techniques and tools for handling very large data sets, mining big data in telecommunication and the benefits and opportunities gained from them.

Keywords: mining big data, big data, machine learning, telecommunication

Procedia PDF Downloads 407
6909 A Model Towards Creating Positive Accounting Classroom Conditions That Supports Successful Learning at School

Authors: Vine Petzer, Mirna Nel

Abstract:

An explanatory mixed method design was used to investigate accounting classroom conditions in the Further Education and Training (FET) Phase in South Africa. A descriptive survey research study with a heterogeneous group of learners and teachers was conducted in the first phase. In the qualitative phase, semi-structured individual interviews with learners and teachers, as well as observations in the accounting classroom, were employed to gain more in depth understanding of the learning conditions in the accounting classroom. The findings of the empirical research informed the development of a model for teachers in accounting, supporting them to use more effective teaching methods and create positive learning conditions for all learners to experience successful learning. A model towards creating positive Accounting classroom conditions that support successful learning was developed and recommended for education policy and decision-makers for use as a classroom intervention capacity building tool. The model identifies and delineates classroom practices that exert significant effect on learner attainment of quality education.

Keywords: accounting classroom conditions, positive education, successful learning, teaching accounting

Procedia PDF Downloads 145
6908 Predicting Student Performance Based on Coding Behavior in STEAMplug

Authors: Giovanni Gonzalez Araujo, Michael Kyrilov, Angelo Kyrilov

Abstract:

STEAMplug is a web-based innovative educational platform which makes teaching easier and learning more effective. It requires no setup, eliminating the barriers to entry, allowing students to focus on their learning throughreal-world development environments. The student-centric tools enable easy collaboration between peers and teachers. Analyzing user interactions with the system enables us to predict student performance and identify at-risk students, allowing early instructor intervention.

Keywords: plagiarism detection, identifying at-Risk Students, education technology, e-learning system, collaborative development, learning and teaching with technology

Procedia PDF Downloads 151
6907 Tracing Back the Bot Master

Authors: Sneha Leslie

Abstract:

The current situation in the cyber world is that crimes performed by Botnets are increasing and the masterminds (botmaster) are not detectable easily. The botmaster in the botnet compromises the legitimate host machines in the network and make them bots or zombies to initiate the cyber-attacks. This paper will focus on the live detection of the botmaster in the network by using the strong framework 'metasploit', when distributed denial of service (DDOS) attack is performed by the botnet. The affected victim machine will be continuously monitoring its incoming packets. Once the victim machine gets to know about the excessive count of packets from any IP, that particular IP is noted and details of the noted systems are gathered. Using the vulnerabilities present in the zombie machines (already compromised by botmaster), the victim machine will compromise them. By gaining access to the compromised systems, applications are run remotely. By analyzing the incoming packets of the zombies, the victim comes to know the address of the botmaster. This is an effective and a simple system where no specific features of communication protocol are considered.

Keywords: bonet, DDoS attack, network security, detection system, metasploit framework

Procedia PDF Downloads 252
6906 Brain-Computer Interface Based Real-Time Control of Fixed Wing and Multi-Rotor Unmanned Aerial Vehicles

Authors: Ravi Vishwanath, Saumya Kumaar, S. N. Omkar

Abstract:

Brain-computer interfacing (BCI) is a technology that is almost four decades old, and it was developed solely for the purpose of developing and enhancing the impact of neuroprosthetics. However, in the recent times, with the commercialization of non-invasive electroencephalogram (EEG) headsets, the technology has seen a wide variety of applications like home automation, wheelchair control, vehicle steering, etc. One of the latest developed applications is the mind-controlled quadrotor unmanned aerial vehicle. These applications, however, do not require a very high-speed response and give satisfactory results when standard classification methods like Support Vector Machine (SVM) and Multi-Layer Perceptron (MLPC). Issues are faced when there is a requirement for high-speed control in the case of fixed-wing unmanned aerial vehicles where such methods are rendered unreliable due to the low speed of classification. Such an application requires the system to classify data at high speeds in order to retain the controllability of the vehicle. This paper proposes a novel method of classification which uses a combination of Common Spatial Paradigm and Linear Discriminant Analysis that provides an improved classification accuracy in real time. A non-linear SVM based classification technique has also been discussed. Further, this paper discusses the implementation of the proposed method on a fixed-wing and VTOL unmanned aerial vehicles.

Keywords: brain-computer interface, classification, machine learning, unmanned aerial vehicles

Procedia PDF Downloads 281
6905 Morphological and Syntactic Meaning: An Interactive Crossword Puzzle Approach

Authors: Ibrahim Garba

Abstract:

This research involved the use of word distributions and morphological knowledge by speakers of Arabic learning English connected different allomorphs in order to realize how the morphology and syntax of English gives meaning through using interactive crossword puzzles (ICP). Fifteen chapters covered with a class of nine learners over an academic year of an intensive English program were reviewed using the ICP. Learners were questioned about how the use of this gaming element enhanced and motivated their learning of English. The findings were positive indicating a successful implementation of ICP both at creational and user levels. This indicated a positive role technology had when learning and teaching English through adopting an interactive gaming element for learning English.

Keywords: distribution, gaming, interactive-crossword-puzzle, morphology

Procedia PDF Downloads 329
6904 A Fully Interpretable Deep Reinforcement Learning-Based Motion Control for Legged Robots

Authors: Haodong Huang, Zida Zhao, Shilong Sun, Chiyao Li, Wenfu Xu

Abstract:

The control methods for legged robots based on deep reinforcement learning have seen widespread application; however, the inherent black-box nature of neural networks presents challenges in understanding the decision-making motives of the robots. To address this issue, we propose a fully interpretable deep reinforcement learning training method to elucidate the underlying principles of legged robot motion. We incorporate the dynamics of legged robots into the policy, where observations serve as inputs and actions as outputs of the dynamics model. By embedding the dynamics equations within the multi-layer perceptron (MLP) computation process and making the parameters trainable, we enhance interpretability. Additionally, Bayesian optimization is introduced to train these parameters. We validate the proposed fully interpretable motion control algorithm on a legged robot, opening new research avenues for motion control and learning algorithms for legged robots within the deep learning framework.

Keywords: deep reinforcement learning, interpretation, motion control, legged robots

Procedia PDF Downloads 19
6903 The Influence of E-Learning on Teachers and Students Educational Interactions in Tehran City

Authors: Hadi Manjiri, Mahdyeh Bakhshi, Ali Jafari, Maryam Salati

Abstract:

This study investigates the influence of e-learning on teacher-student instructional interactions through the mediating role of computer literacy among elementary school teachers in Tehran. The research method is a survey that was conducted among elementary school students in Tehran. A sample size of 338 was determined based on Morgan's table. A stratified random sampling method was used to select 228 women and 110 men for the study. Bagherpour et al.'s computer literacy questionnaire, Elahi et al.'s e-learning questionnaire, and Lourdusamy and Khine's questionnaire on teacher-student instructional interactions were used to measure the variables. The data were analyzed using SPSS and LISREL software. It was found that e-learning affects teacher-student instructional interactions, mediated by teachers' computer literacy. In addition, the results suggest that e-learning predicts a 0.66 change in teacher-student instructional interactions, while computer literacy predicts a 0.56 change in instructional interactions between teachers and students.

Keywords: e-learning, instructional interactions, computer literacy, students

Procedia PDF Downloads 116
6902 Robust Fuzzy PID Stabilizer: Modified Shuffled Frog Leaping Algorithm

Authors: Oveis Abedinia, Noradin Ghadimi, Nasser Mikaeilvand, Roza Poursoleiman, Asghar Poorfaraj

Abstract:

In this paper a robust Fuzzy Proportional Integral Differential (PID) controller is applied to multi-machine power system based on Modified Shuffled Frog Leaping (MSFL) algorithm. This newly proposed controller is more efficient because it copes with oscillations and different operating points. In this strategy the gains of the PID controller is optimized using the proposed technique. The nonlinear problem is formulated as an optimization problem for wide ranges of operating conditions using the MSFL algorithm. The simulation results demonstrate the effectiveness, good robustness and validity of the proposed method through some performance indices such as ITAE and FD under wide ranges operating conditions in comparison with TS and GSA techniques. The single-machine infinite bus system and New England 10-unit 39-bus standard power system are employed to illustrate the performance of the proposed method.

Keywords: fuzzy PID, MSFL, multi-machine, low frequency oscillation

Procedia PDF Downloads 428
6901 Connecting Life and Learning: Transformative Learning to Increase Student Engagement

Authors: Kashi Raj Pandey

Abstract:

Transformative learning is a form of learning rooted in learners' life experiences and their inherent love for learning. It emphasizes the importance of incorporating students' everyday work through the use of learning diaries and reflective journals. It encourages learners to take a proactive role in their own improvement, fostering creativity and promoting informed discussions about the learning process. Reflecting on the personal experience with English language learning in a rural village in Nepal where rote memorization was the prevailing teaching method, this traditional approach hindered a deeper understanding of the language, prompting the author to recognize the need for more effective pedagogy. In this study, the author delved into the cultural contextualization of English language learning, taking into account learners' backgrounds. The study’s findings highlighted the importance of equity, inclusion, mutuality, and social justice in the classroom, emphasizing the significance of integrating students' lived experiences into the pedagogical approach. This, in turn, can encourage students to engage in profound and collaborative learning practices within the realm of English language education. Upon successfully implementing the research findings, including the eight key conditions of transformative learning, in multiple classrooms, the author collaborated with international educationists and government stakeholders in Nepal. The purpose was to disseminate the research findings, conduct teacher training workshops, and systematically enhance Nepali students’ English language learning. These methods have already demonstrated a significant improvement in student engagement within the same school where the author once learned English as a child. This study aims to explore teachers’ decision-making process regarding the transition from traditional teaching methods to interactive ones, which have gained national recognition within the ESL/EFL teaching community in Nepal. By sharing these experiences, it is expected that other teachers will also contemplate adopting transformative learning pedagogy in their own classrooms.

Keywords: reflection, student engagement, pedagogy, transformative learning

Procedia PDF Downloads 79
6900 Effectiveness of Electronic Learning for Continuing Interprofessional Education on Behavior Change of Healthcare Professionals: A Scoping Review

Authors: Kailin K. Zhang, Anne W. Thompson

Abstract:

Electronic learning for continuing professional education (CPE) and interprofessional education (IPE) in healthcare have been shown to improve learners’ satisfaction, attitudes, and performance. Yet, their impact on behavior change in healthcare professionals through continuing interprofessional education (CIPE) is less known. A scoping review of 32 articles from 2010 to 2020 was conducted using the Arksey and O’Malley framework across all healthcare settings. It focused on evaluating the effectiveness of CIPE on behavior change of healthcare professionals, as well as identifying course features of electronic CIPE programs facilitating behavior change. Eight different types of electronic learning methods, including online programs, tele-education, and social media, were identified as interventions. More than 35,542 healthcare professionals participated in the interventions. Electronic learning for CIPE led to positive behavior outcomes in 30 out of 32 studies, especially through a change in patient care practices. The most successful programs provided interactive and authentic learning experiences tailored to learners’ needs while promoting the direct application of what was learned in their clinical settings. Future research should include monitoring of sustained behavior changes and their resultant patient outcomes.

Keywords: behavior change, continuing interprofessional education, distance learning, electronic learning

Procedia PDF Downloads 143
6899 Comparison of Linear Discriminant Analysis and Support Vector Machine Classifications for Electromyography Signals Acquired at Five Positions of Elbow Joint

Authors: Amna Khan, Zareena Kausar, Saad Malik

Abstract:

Bio Mechatronics has extended applications in the field of rehabilitation. It has been contributing since World War II in improving the applicability of prosthesis and assistive devices in real life scenarios. In this paper, classification accuracies have been compared for two classifiers against five positions of elbow. Electromyography (EMG) signals analysis have been acquired directly from skeletal muscles of human forearm for each of the three defined positions and at modified extreme positions of elbow flexion and extension using 8 electrode Myo armband sensor. Features were extracted from filtered EMG signals for each position. Performance of two classifiers, support vector machine (SVM) and linear discriminant analysis (LDA) has been compared by analyzing the classification accuracies. SVM illustrated classification accuracies between 90-96%, in contrast to 84-87% depicted by LDA for five defined positions of elbow keeping the number of samples and selected feature the same for both SVM and LDA.

Keywords: classification accuracies, electromyography, linear discriminant analysis (LDA), Myo armband sensor, support vector machine (SVM)

Procedia PDF Downloads 366
6898 Developing Leadership and Teamwork Skills of Pre-Service Teachers through Learning Camp

Authors: Sirimanee Banjong

Abstract:

This study aimed to 1) develop pre-service teachers’ leadership skills through camp-based learning, and 2) develop pre-service teachers’ teamwork skills through camp-based learning. An applied research methodology was used. The target group was derived from a purposive selection. It involved 32 fourth-year students in Early Childhood Education Program enrolling in a course entitled Seminar in Early Childhood Education provided during the second semester of the academic year 2013. The treatment was camp-based learning activities which applied a PDCA process including four stages: 1) plan, 2) do, 3) check, and 4) act. Research instruments were a learning camp program, a camp-based learning management plan, a 5-level assessment form for leadership skills and a 5-level assessment form for assessing teamwork skills. Data were analyzed using descriptive statistics. Results were: 1) pre-service teachers’ leadership skills yielded the before treatment average score at ¯("x" )=3.4, S.D.= 0.62 and the after-treatment average score at ¯("x" ) 4.29, S.D.=0.66 pre-service teachers’ teamwork skills yielded the before-treatment average score at ¯("x" )=3.31, S.D.= 0.60 and the after-treatment average score at ¯("x" )=4.42, S.D.= 0.66. Both differences were statistically significant at the .05 level. Thus, the pre-service teachers’ leadership and teamwork skills were significantly improved through the camp-based learning approach.

Keywords: learning camp, leadership skills, teamwork skills, pre-service teachers

Procedia PDF Downloads 360
6897 Study of Education Learning Techniques and Game Genres

Authors: Khadija Al Farei, Prakash Kumar, Vikas Rao Naidu

Abstract:

Games are being developed with different genres for different age groups, for many decades. In many places, educational games are playing a vital role for active classroom environment and better learning among students. Currently, the educational games have assumed an important place in children and teenagers lives. The role of educational games is important for improving the learning capability among the students especially of this generation, who really live among electronic gadgets. Hence, it is now important to make sure that in our educational system, we are updated with all such advancement in technologies. Already much research is going on in this area of edutainment. This research paper will review around ten different research papers to find the relation between the education learning techniques and games. The result of this review provides guidelines for enhanced teaching and learning solutions in education. In-house developed educational games proved to be more effective, compared to the one which is readily available in the market.

Keywords: education, education game, educational technology, edutainment, game genres, gaming in education

Procedia PDF Downloads 413
6896 Reinforcement Learning for Classification of Low-Resolution Satellite Images

Authors: Khadija Bouzaachane, El Mahdi El Guarmah

Abstract:

The classification of low-resolution satellite images has been a worthwhile and fertile field that attracts plenty of researchers due to its importance in monitoring geographical areas. It could be used for several purposes such as disaster management, military surveillance, agricultural monitoring. The main objective of this work is to classify efficiently and accurately low-resolution satellite images by using novel technics of deep learning and reinforcement learning. The images include roads, residential areas, industrial areas, rivers, sea lakes, and vegetation. To achieve that goal, we carried out experiments on the sentinel-2 images considering both high accuracy and efficiency classification. Our proposed model achieved a 91% accuracy on the testing dataset besides a good classification for land cover. Focus on the parameter precision; we have obtained 93% for the river, 92% for residential, 97% for residential, 96% for the forest, 87% for annual crop, 84% for herbaceous vegetation, 85% for pasture, 78% highway and 100% for Sea Lake.

Keywords: classification, deep learning, reinforcement learning, satellite imagery

Procedia PDF Downloads 211
6895 Classification of Emotions in Emergency Call Center Conversations

Authors: Magdalena Igras, Joanna Grzybowska, Mariusz Ziółko

Abstract:

The study of emotions expressed in emergency phone call is presented, covering both statistical analysis of emotions configurations and an attempt to automatically classify emotions. An emergency call is a situation usually accompanied by intense, authentic emotions. They influence (and may inhibit) the communication between caller and responder. In order to support responders in their responsible and psychically exhaustive work, we studied when and in which combinations emotions appeared in calls. A corpus of 45 hours of conversations (about 3300 calls) from emergency call center was collected. Each recording was manually tagged with labels of emotions valence (positive, negative or neutral), type (sadness, tiredness, anxiety, surprise, stress, anger, fury, calm, relief, compassion, satisfaction, amusement, joy) and arousal (weak, typical, varying, high) on the basis of perceptual judgment of two annotators. As we concluded, basic emotions tend to appear in specific configurations depending on the overall situational context and attitude of speaker. After performing statistical analysis we distinguished four main types of emotional behavior of callers: worry/helplessness (sadness, tiredness, compassion), alarm (anxiety, intense stress), mistake or neutral request for information (calm, surprise, sometimes with amusement) and pretension/insisting (anger, fury). The frequency of profiles was respectively: 51%, 21%, 18% and 8% of recordings. A model of presenting the complex emotional profiles on the two-dimensional (tension-insecurity) plane was introduced. In the stage of acoustic analysis, a set of prosodic parameters, as well as Mel-Frequency Cepstral Coefficients (MFCC) were used. Using these parameters, complex emotional states were modeled with machine learning techniques including Gaussian mixture models, decision trees and discriminant analysis. Results of classification with several methods will be presented and compared with the state of the art results obtained for classification of basic emotions. Future work will include optimization of the algorithm to perform in real time in order to track changes of emotions during a conversation.

Keywords: acoustic analysis, complex emotions, emotion recognition, machine learning

Procedia PDF Downloads 395
6894 Adult Language Learning in the Institute of Technology Sector in the Republic of Ireland

Authors: Una Carthy

Abstract:

A recent study of third level institutions in Ireland reveals that both age and aptitude can be overcome by teaching methodologies to motivate second language learners. This PhD investigation gathered quantitative and qualitative data from 14 Institutes of Technology over a three years period from 2011 to 2014. The fundamental research question was to establish the impact of institutional language policy on attitudes towards language learning. However, other related issues around second language acquisition arose in the course of the investigation. Data were collected from both lectures and students, allowing interesting points of comparison to emerge from both datasets. Negative perceptions among lecturers regarding language provision were often associated with the view that language learning belongs to primary and secondary level and has no place in third level education. This perception was offset by substantial data showing positive attitudes towards adult language learning. Lenneberg’s Critical Age Theory postulated that the optimum age for learning a second language is before puberty. More recently, scholars have challenged this theory in their studies, revealing that mature learners can and do succeed at learning languages. With regard to aptitude, a preoccupation among lecturers regarding poor literacy skills among students emerged and was often associated with resistance to second language acquisition. This was offset by a preponderance of qualitative data from students highlighting the crucial role which teaching approaches play in the learning process. Interestingly, the data collected regarding learning disabilities reveals that, given the appropriate learning environments, individuals can be motivated to acquire second languages, and indeed succeed at learning them. These findings are in keeping with other recent studies regarding attitudes towards second language learning among students with learning disabilities. Both sets of findings reinforce the case for language policies in the Institute of Technology (IoTs). Supportive and positive learning environments can be created in third level institutions to motivate adult learners, thereby overcoming perceived obstacles relating to age and aptitude.

Keywords: age, aptitude, second language acquisition, teaching methodologies

Procedia PDF Downloads 122
6893 Assessing the Efficacy of Artificial Intelligence Integration in the FLO Health Application

Authors: Reema Alghamdi, Rasees Aleisa, Layan Sukkar

Abstract:

The primary objective of this research is to conduct an examination of the Flo menstrual cycle application. We do that by evaluating the user experience and their satisfaction with integrated AI features. The study seeks to gather data from primary resources, primarily through surveys, to gather different insights about the application, like its usability functionality in addition to the overall user satisfaction. The focus of our project will be particularly directed towards the impact and user perspectives regarding the integration of artificial intelligence features within the application, contributing to an understanding of the holistic user experience.

Keywords: period, women health, machine learning, AI features, menstrual cycle

Procedia PDF Downloads 73
6892 Surveying the Effects of Online Learning On High School Student’s Motivation: A Case Study of Pinewood School

Authors: Robert Cui

Abstract:

COVID-19 has drastically changed the way students interact and engage with their environments. Students, in particular, have been forced to change from in-person to online learning. How can we ensure that students continue to remain motivated even as their mode of education transitions to online learning? In this study conducted on high school students from a small private school (n = 50), we investigate the factors that predict student motivation during online learning. Using the framework of self-determination theory, we examine the three facets of student motivation during online learning: engagement, autonomy, and competence. We find that students' perception of their peers' engagement with the curriculum, feelings of parental academic expectations, perceptions of favoritism by the teacher, and perceived clarity of instruction given by the teacher all predict student engagement in online learning. Student autonomy is predicted by the amount of parental control a student feels, the clarity of instruction given by the teacher, and also the amount to which a student is perceiving their peers to be paying attention. Finally, competence is predicted by favoritism a student perceives from a teacher and also the amount of which a student is perceiving their peers to be paying attention. Based on these findings, we provide insights on how three important stakeholders –parents, teachers, and peers can enhance students' motivation during online learning.

Keywords: academic performance, motivation, online learning, parental influence, teacher, peers

Procedia PDF Downloads 140
6891 Improving Effectiveness of Students' Learning during Clinical Rotations at a Teaching Hospital in Rwanda

Authors: Nanyombi Lubimbi, Josette Niyokindi

Abstract:

Background: As in many other developing countries in Africa, Rwanda suffers from a chronic shortage of skilled Health Care professionals including Clinical Instructors. This shortage negatively affects the clinical instruction quality therefore impacting student-learning outcomes. Due to poor clinical supervision, it is often noted that students have no structure or consistent guidance in their learning process. The Clinical Educators and the Rwandan counterparts identified the need to create a favorable environment for learning. Description: During orientation the expectations of the student learning process, collaboration of the clinical instructors with the nurses and Clinical Educators is outlined. The ward managers facilitate structured learning by helping the students identify a maximum of two patients using the school’s objectives to guide the appropriate selection of patients. Throughout the day, Clinical Educators with collaboration of Clinical Instructors when present conduct an ongoing assessment of learning and provide feedback to the students. Post-conference is provided once or twice a week to practice critical thinking skills of patient cases that they have been taking care of during the day. Lessons Learned: The students are found to be more confident with knowledge and skills gained during rotations. Clinical facility evaluations completed by students at the end of their rotations highlight the student’s satisfaction and recommendation for continuation of structured learning. Conclusion: Based on the satisfaction of both students and Clinical Instructors, we have identified need for structured learning during clinical rotations. We acknowledge that more evidence-based practice is necessary to effectively address the needs of nursing and midwifery students throughout the country.

Keywords: Rwanda, clinical rotation, structured learning, critical thinking skills, post-conference

Procedia PDF Downloads 237
6890 Restricted Boltzmann Machines and Deep Belief Nets for Market Basket Analysis: Statistical Performance and Managerial Implications

Authors: H. Hruschka

Abstract:

This paper presents the first comparison of the performance of the restricted Boltzmann machine and the deep belief net on binary market basket data relative to binary factor analysis and the two best-known topic models, namely Dirichlet allocation and the correlated topic model. This comparison shows that the restricted Boltzmann machine and the deep belief net are superior to both binary factor analysis and topic models. Managerial implications that differ between the investigated models are treated as well. The restricted Boltzmann machine is defined as joint Boltzmann distribution of hidden variables and observed variables (purchases). It comprises one layer of observed variables and one layer of hidden variables. Note that variables of the same layer are not connected. The comparison also includes deep belief nets with three layers. The first layer is a restricted Boltzmann machine based on category purchases. Hidden variables of the first layer are used as input variables by the second-layer restricted Boltzmann machine which then generates second-layer hidden variables. Finally, in the third layer hidden variables are related to purchases. A public data set is analyzed which contains one month of real-world point-of-sale transactions in a typical local grocery outlet. It consists of 9,835 market baskets referring to 169 product categories. This data set is randomly split into two halves. One half is used for estimation, the other serves as holdout data. Each model is evaluated by the log likelihood for the holdout data. Performance of the topic models is disappointing as the holdout log likelihood of the correlated topic model – which is better than Dirichlet allocation - is lower by more than 25,000 compared to the best binary factor analysis model. On the other hand, binary factor analysis on its own is clearly surpassed by both the restricted Boltzmann machine and the deep belief net whose holdout log likelihoods are higher by more than 23,000. Overall, the deep belief net performs best. We also interpret hidden variables discovered by binary factor analysis, the restricted Boltzmann machine and the deep belief net. Hidden variables characterized by the product categories to which they are related differ strongly between these three models. To derive managerial implications we assess the effect of promoting each category on total basket size, i.e., the number of purchased product categories, due to each category's interdependence with all the other categories. The investigated models lead to very different implications as they disagree about which categories are associated with higher basket size increases due to a promotion. Of course, recommendations based on better performing models should be preferred. The impressive performance advantages of the restricted Boltzmann machine and the deep belief net suggest continuing research by appropriate extensions. To include predictors, especially marketing variables such as price, seems to be an obvious next step. It might also be feasible to take a more detailed perspective by considering purchases of brands instead of purchases of product categories.

Keywords: binary factor analysis, deep belief net, market basket analysis, restricted Boltzmann machine, topic models

Procedia PDF Downloads 199
6889 Formation of Academia-Industry Collaborative Model to Improve the Quality of Teaching-Learning Process

Authors: M. Dakshayini, P. Jayarekha

Abstract:

In traditional output-based education system, class room lecture and laboratory are the traditional delivery methods used during the course. Written examination and lab examination have been used as a conventional tool for evaluating student’s performance. Hence, there are certain apprehensions that the traditional education system may not efficiently prepare the students for competent professional life. This has led for the change from Traditional output-based education to Outcome-Based Education (OBE). OBE first sets the ideal programme learning outcome consecutively on increasing degree of complexity that students are expected to master. The core curriculum, teaching methodologies and assessment tools are then designed to achieve the proposed outcomes mainly focusing on what students can actually attain after they are taught. In this paper, we discuss a promising applications based learning and evaluation component involving industry collaboration to improve the quality of teaching and student learning process. Incorporation of this component definitely improves the quality of student learning in engineering education and helps the student to attain the competency as per the graduate attributes. This may also reduce the Industry-academia gap.

Keywords: outcome-based education, programme learning outcome, teaching-learning process, evaluation, industry collaboration

Procedia PDF Downloads 448
6888 English Language Teaching and Learning Analysis in Iran

Authors: F. Zarrabi, J. R. Brown

Abstract:

Although English is not a second language in Iran, it has become an inseparable part of many Iranian people’s lives and is becoming more and more widespread. This high demand has caused a significant increase in the number of private English language institutes in Iran. Although English is a compulsory course in schools and universities, the majority of Iranian people are unable to communicate easily in English. This paper reviews the current state of teaching and learning English as an international language in Iran. Attitudes and motivations about learning English are reviewed. Five different aspects of using English within the country are analysed, including: English in public domain, English in Media, English in organizations/businesses, English in education, and English in private language institutes. Despite the time and money spent on English language courses in private language institutes, the majority of learners seem to forget what has been learned within months of completing their course. That is, when they are students with the support of the teacher and formal classes, they appear to make progress and use English more or less fluently. When this support is removed, their language skills either stagnant or regress. The findings of this study suggest that a dependant approach to learning is potentially one of the main reasons for English language learning problems and this is encouraged by English course books and approaches to teaching.

Keywords: English in Iran, English language learning, English language teaching, evaluation

Procedia PDF Downloads 417
6887 Novel Hole-Bar Standard Design and Inter-Comparison for Geometric Errors Identification on Machine-Tool

Authors: F. Viprey, H. Nouira, S. Lavernhe, C. Tournier

Abstract:

Manufacturing of freeform parts may be achieved on 5-axis machine tools currently considered as a common means of production. In particular, the geometrical quality of the freeform parts depends on the accuracy of the multi-axis structural loop, which is composed of several component assemblies maintaining the relative positioning between the tool and the workpiece. Therefore, to reach high quality of the geometries of the freeform parts the geometric errors of the 5 axis machine should be evaluated and compensated, which leads one to master the deviations between the tool and the workpiece (volumetric accuracy). In this study, a novel hole-bar design was developed and used for the characterization of the geometric errors of a RRTTT 5-axis machine tool. The hole-bar standard design is made of Invar material, selected since it is less sensitive to thermal drift. The proposed design allows once to extract 3 intrinsic parameters: one linear positioning and two straightnesses. These parameters can be obtained by measuring the cylindricity of 12 holes (bores) and 11 cylinders located on a perpendicular plane. By mathematical analysis, twelve 3D points coordinates can be identified and correspond to the intersection of each hole axis with the least square plane passing through two perpendicular neighbour cylinders axes. The hole-bar was calibrated using a precision CMM at LNE traceable the SI meter definition. The reversal technique was applied in order to separate the error forms of the hole bar from the motion errors of the mechanical guiding systems. An inter-comparison was additionally conducted between four NMIs (National Metrology Institutes) within the EMRP IND62: JRP-TIM project. Afterwards, the hole-bar was integrated in RRTTT 5-axis machine tool to identify its volumetric errors. Measurements were carried out in real time and combine raw data acquired by the Renishaw RMP600 touch probe and the linear and rotary encoders. The geometric errors of the 5 axis machine were also evaluated by an accurate laser tracer interferometer system. The results were compared to those obtained with the hole bar.

Keywords: volumetric errors, CMM, 3D hole-bar, inter-comparison

Procedia PDF Downloads 383
6886 Exploring Smartphone Applications for Enhancing Second Language Vocabulary Learning

Authors: Abdulmajeed Almansour

Abstract:

Learning a foreign language with the assistant of technological tools has become an interest of learners and educators. Increased use of smartphones among undergraduate students has made them popular for not only social communication but also for entertainment and educational purposes. Smartphones have provided remarkable advantages in language learning process. Learning vocabulary is an important part of learning a language. The use of smartphone applications for English vocabulary learning provides an opportunity for learners to improve vocabulary knowledge beyond the classroom wall anytime anywhere. Recently, various smartphone applications were created specifically for vocabulary learning. This paper aims to explore the use of smartphone application Memrise designed for vocabulary learning to enhance academic vocabulary among undergraduate students. It examines whether the use of a Memrise smartphone application designed course enhances the academic vocabulary learning among ESL learners. The research paradigm used in this paper followed a mixed research model combining quantitative and qualitative research. The study included two hundred undergraduate students randomly assigned to the experimental and controlled group during the first academic year at the Faculty of English Language, Imam University. The research instruments included an attitudinal questionnaire and an English vocabulary pre-test administered to students at the beginning of the semester whereas post-test and semi-structured interviews administered at the end of the semester. The findings of the attitudinal questionnaire revealed a positive attitude towards using smartphones in learning vocabulary. The post-test scores showed a significant difference in the experimental group performance. The results from the semi-structure interviews showed that there were positive attitudes towards Memrise smartphone application. The students found the application enjoyable, convenient and efficient learning tool. From the study, the use of the Memrise application is seen to have long-term and motivational benefits to students. For this reason, there is a need for further research to identify the long-term optimal effects of learning a language using smartphone applications.

Keywords: second language vocabulary learning, academic vocabulary, mobile learning technologies, smartphone applications

Procedia PDF Downloads 160
6885 Analytical Study: An M-Learning App Reflecting the Factors Affecting Student’s Adoption of M-Learning

Authors: Ahmad Khachan, Ahmet Ozmen

Abstract:

This study aims to introduce a mobile bite-sized learning concept, a mobile application with social networks motivation factors that will encourage students to practice critical thinking, improve analytical skills and learn knowledge sharing. We do not aim to propose another e-learning or distance learning based tool like Moodle and Edmodo; instead, we introduce a mobile learning tool called Interactive M-learning Application. The tool reconstructs and strengthens the bonds between educators and learners and provides a foundation for integrating mobile devices in education. The application allows learners to stay connected all the time, share ideas, ask questions and learn from each other. It is built on Android since the Android has the largest platform share in the world and is dominating the market with 74.45% share in 2018. We have chosen Google-Firebase server for hosting because of flexibility, ease of hosting and real time update capabilities. The proposed m-learning tool was offered to four groups of university students in different majors. An improvement in the relation between the students, the teachers and the academic institution was obvious. Student’s performance got much better added to better analytical and critical skills advancement and moreover a willingness to adopt mobile learning in class. We have also compared our app with another tool in the same class for clarity and reliability of the results. The student’s mobile devices were used in this experimental study for diversity of devices and platform versions.

Keywords: education, engineering, interactive software, undergraduate education

Procedia PDF Downloads 153
6884 Intelligent Adaptive Learning in a Changing Environment

Authors: G. Valentis, Q. Berthelot

Abstract:

Nowadays the trend to develop ever more intelligent and autonomous systems often takes its inspiration in the living beings on Earth. Some simple isolated systems are able, once brought together, to form a strong and reliable system. When trying to adapt the idea to man-made systems it is not possible to include in their program everything the system may encounter during its life cycle. It is, thus, necessary to make the system able to take decisions based on other criteria such as its past experience, i.e. to make the system learn on its own. However, at some point the acquired knowledge depends also on environment. So the question is: if system environment is modified, how could the system respond to it quickly and appropriately enough? Here, starting from reinforcement learning to rate its decisions, and using adaptive learning algorithms for gain and loss reward, the system is made able to respond to changing environment and to adapt its knowledge as time passes. Application is made to a robot finding an exit in a labyrinth.

Keywords: reinforcement learning, neural network, autonomous systems, adaptive learning, changing environment

Procedia PDF Downloads 423
6883 A Study on the Accelerated Life Cycle Test Method of the Motor for Home Appliances by Using Acceleration Factor

Authors: Youn-Sung Kim, Mi-Sung Kim, Jae-Kun Lee

Abstract:

This paper deals with the accelerated life cycle test method of the motor for home appliances that demand high reliability. Life Cycle of parts in home appliances also should be 10 years because life cycle of the home appliances such as washing machine, refrigerator, TV is at least 10 years. In case of washing machine, the life cycle test method of motor is advanced for 3000 cycle test (1cycle = 2hours). However, 3000 cycle test incurs loss for the time and cost. Objectives of this study are to reduce the life cycle test time and the number of test samples, which could be realized by using acceleration factor for the test time and reduction factor for the number of sample.

Keywords: accelerated life cycle test, motor reliability test, motor for washing machine, BLDC motor

Procedia PDF Downloads 633
6882 An Application of E-Learning Technology for Students with Deafness and Hearing Impairment

Authors: Eyup Bayram Guzel

Abstract:

There have been growing awareness that technology offers unique and promising advantages by offering up-to-data educational materials in promoting teaching and learning materials, new strategies for building enhanced communication environment for people with disabilities and specifically for this study concentrated on the students with deafness and hearing impairments. Creating e-learning environment where teachers and students work in collaboration to develop better educational outcomes is the foremost reason of conducting this research. This study examined the perspectives of special education teachers’ regarding an application of e-learning software called Multimedia Builder on the students with deafness and hearing impairments. Initial and follow up interviews were conducted with 15 special education teachers around the scope of qualitative case study. Grounded approach has been used to analyse and interpret the data. The research results revealed that application of Multimedia Builder software were influential on reading, sign language, vocabulary improvements, computer and ICT usage developments and on audio-visual learning achievements for the advantages of students with deafness and hearing impairments. The implications of the study encouraged the ways of using e-learning tools and strategies to promote unique and comprehensive learning experiences for the targeted students and their teachers.

Keywords: e-learning, special education, deafness and hearing impairment, computer-ICT usage.

Procedia PDF Downloads 437
6881 The Impact of Information and Communication Technology on Learning Quality and Conceptual Change in Moroccan High School Students

Authors: Azzeddine Atibi, Khadija El Kababi, Salim Ahmed, Mohamed Radid

Abstract:

Teaching and learning occupy a significant position globally, as the sustainable development of all sectors is intrinsically linked to the improvement of the educational system. The COVID-19 pandemic demonstrated that the integration of Information and Communication Technology (ICT) in the learning process is not optional but essential, and that proficiency in computer tools is an asset that will enhance pedagogy and ensure the continuity of learning under any circumstances. The objective of our study is to evaluate the impact of introducing computer tools on the quality of learning and the realization of conceptual change in learners. To this end, a learning situation was meticulously prepared, targeting first-year baccalaureate students in experimental sciences at a public high school, "Khadija Oum Almouminin," focusing on the chapter on glycemia regulation in the Moroccan Life and Earth Sciences (LES) curriculum. The learning situation was implemented with a pilot group that utilized computer tools and a control group that studied the same chapter without using ICT. The analysis and comparison of the results allowed us to verify the research question posed and to propose perspectives to ensure conceptual change in learners.

Keywords: information and communication technology, conceptual change, continuity of learning, life and earth sciences, glycemia regulation

Procedia PDF Downloads 36