Search results for: older adult learning
Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 8644

Search results for: older adult learning

7054 Comprehensive Machine Learning-Based Glucose Sensing from Near-Infrared Spectra

Authors: Bitewulign Mekonnen

Abstract:

Context: This scientific paper focuses on the use of near-infrared (NIR) spectroscopy to determine glucose concentration in aqueous solutions accurately and rapidly. The study compares six different machine learning methods for predicting glucose concentration and also explores the development of a deep learning model for classifying NIR spectra. The objective is to optimize the detection model and improve the accuracy of glucose prediction. This research is important because it provides a comprehensive analysis of various machine-learning techniques for estimating aqueous glucose concentrations. Research Aim: The aim of this study is to compare and evaluate different machine-learning methods for predicting glucose concentration from NIR spectra. Additionally, the study aims to develop and assess a deep-learning model for classifying NIR spectra. Methodology: The research methodology involves the use of machine learning and deep learning techniques. Six machine learning regression models, including support vector machine regression, partial least squares regression, extra tree regression, random forest regression, extreme gradient boosting, and principal component analysis-neural network, are employed to predict glucose concentration. The NIR spectra data is randomly divided into train and test sets, and the process is repeated ten times to increase generalization ability. In addition, a convolutional neural network is developed for classifying NIR spectra. Findings: The study reveals that the SVMR, ETR, and PCA-NN models exhibit excellent performance in predicting glucose concentration, with correlation coefficients (R) > 0.99 and determination coefficients (R²)> 0.985. The deep learning model achieves high macro-averaging scores for precision, recall, and F1-measure. These findings demonstrate the effectiveness of machine learning and deep learning methods in optimizing the detection model and improving glucose prediction accuracy. Theoretical Importance: This research contributes to the field by providing a comprehensive analysis of various machine-learning techniques for estimating glucose concentrations from NIR spectra. It also explores the use of deep learning for the classification of indistinguishable NIR spectra. The findings highlight the potential of machine learning and deep learning in enhancing the prediction accuracy of glucose-relevant features. Data Collection and Analysis Procedures: The NIR spectra and corresponding references for glucose concentration are measured in increments of 20 mg/dl. The data is randomly divided into train and test sets, and the models are evaluated using regression analysis and classification metrics. The performance of each model is assessed based on correlation coefficients, determination coefficients, precision, recall, and F1-measure. Question Addressed: The study addresses the question of whether machine learning and deep learning methods can optimize the detection model and improve the accuracy of glucose prediction from NIR spectra. Conclusion: The research demonstrates that machine learning and deep learning methods can effectively predict glucose concentration from NIR spectra. The SVMR, ETR, and PCA-NN models exhibit superior performance, while the deep learning model achieves high classification scores. These findings suggest that machine learning and deep learning techniques can be used to improve the prediction accuracy of glucose-relevant features. Further research is needed to explore their clinical utility in analyzing complex matrices, such as blood glucose levels.

Keywords: machine learning, signal processing, near-infrared spectroscopy, support vector machine, neural network

Procedia PDF Downloads 69
7053 Improving Music Appreciation and Narrative Abilities of Students with Intellectual Disabilities through a College Service-Learning Model

Authors: Shan-Ken Chien

Abstract:

This research aims to share the application of the Music and Narrative Curriculum developed through a college community service-learning course to a special education classroom in a local secondary school. The development of the Music and Narrative Curriculum stems from the music appreciation courses that the author has taught at the university. The curriculum structure consists of three instructional phases, each with three core literacy. This study will show the implementation of an eighteen-week general music education course, including classroom training on the university campus and four intervention music lessons in a special education classroom. Students who participated in the Music and Narrative Curriculum came from two different parts. One is twenty-five college students enrolling in Music Literacy and Community Service-Learning, and the other one is nine junior high school students with intellectual disabilities (ID) in a special education classroom. This study measures two parts. One is the effectiveness of the Music and Narrative Curriculum in applying four interventions in music lessons in a special education classroom, and the other is measuring college students' service-learning experiences and growth outcomes.

Keywords: college service-learning, general music education, music literacy, narrative skills, students with special needs

Procedia PDF Downloads 57
7052 The Role of Blended Modality in Enhancing Active Learning Strategies in Higher Education: A Case Study of a Hybrid Course of Oral Production and Listening of French

Authors: Tharwat N. Hijjawi

Abstract:

Learning oral skills in an Arabic speaking environment is challenging. A blended course (material, activities, and individual/ group work tasks …) was implemented in a module of level B1 for undergraduate students of French as a foreign language in order to increase their opportunities to practice listening and speaking skills. This research investigates the influence of this modality on enhancing active learning and examines the effectiveness of provided strategies. Moreover, it aims at discovering how it allows teacher to flip the traditional classroom and create a learner-centered framework. Which approaches were integrated to motivate students and urge them to search, analyze, criticize, create and accomplish projects? What was the perception of students? This paper is based on the qualitative findings of a questionnaire and a focus group interview with learners. Despite the doubled time and effort both “teacher” and “student” needed, results revealed that the NTIC allowed a shift into a learning paradigm where learners were the “chiefs” of the process. Tasks and collaborative projects required higher intellectual capacities from them. Learners appreciated this experience and developed new life-long learning competencies at many levels: social, affective, ethical and cognitive. To conclude, they defined themselves as motivated young researchers, motivators and critical thinkers.

Keywords: active learning, critical thinking, inverted classroom, learning paradigm, problem-based

Procedia PDF Downloads 252
7051 “Teacher, You’re on Mute!”: Teachers as Cultivators of Trans-Literacies

Authors: Efleda Preclaro Tolentino

Abstract:

Research indicates that an educator’s belief system is reflected in the way they structure the learning environment. Their values and belief system have the potential to positively impact school readiness through an understanding of children’s development and the creation of a stable, motivating environment. Based on the premise that the social environment influences the development of social skills, knowledge construct, and shared values of young children, this study examined verbal and nonverbal exchanges between early childhood teachers and their preschool students within the context of remote learning. Using the qualitative method of data collection, the study determined the nature of interactions between preschoolers and their teachers within a remote learning environment at a preschool in Southeast Asia that utilized the Mother Tongue-based Multilingual Education (MTBMLE) Approach. From the lens of sociocultural theory, the study investigated preschoolers’ use of literacies to convey meaning and to interact within a remote learning environment. Using a Strengths Perspective, the study revealed the creativity and resourcefulness of preschoolers in expressing themselves through trans-literacies that were made possible by the use of online mode of learning within cultural and subcultural norms. The study likewise examined how social skills acquired by young children were transmitted (verbally or nonverbally) in their interactions with peers during Zoom meetings. By examining the dynamics of social exchanges between teachers and children, the findings of the study underscore the importance of providing support for preschool students as they apply acquired values and shared practices within a remote learning environment. The potential of distance learning in the early years will be explored, specifically in supporting young children’s language and literacy development. At the same time, the study examines the role of teachers as cultivators of trans-literacies. The teachers’ skillful use of technology in facilitating young children’s learning, as well as in supporting interactions with families, will be examined. The findings of this study will explore the potential of distance learning in early childhood education to establish continuity in learning, supporting young children’s social and emotional transitions, and nurturing trans-literacies that transcend prevailing definitions of learning contexts. The implications of teachers and parents working collaboratively to support student learning will be examined. The importance of preparing teachers to be resourceful, adaptable, and innovative to ensure that learning takes place across a variety of modes and settings will be discussed.

Keywords: transliteracy, preschoolers, remote learning, strengths perspective

Procedia PDF Downloads 69
7050 DNA Based Identification of Insect Vectors for Zoonotic Diseases From District Faisalabad, Pakistan

Authors: Zain Ul Abdin, Mirza Aizaz Asim, Rao Sohail Ahmad Khan, Luqman Amrao, Fiaz Hussain, Hasooba Hira, Saqi Kosar Abbas

Abstract:

The success of Integrated vector management programmes mainly depends on the correct identification of insect vector species involved in vector borne diseases. Based on molecular data the most important insect species involved as vectors for Zoonotic diseases in Pakistan were identified. The precise and accurate identification of such type of organism is only possible through molecular based techniques like “DNA barcoding”. Morphological species identification in insects at any life stage, is very challenging, therefore, DNA barcoding was used as a tool for rapid and accurate species identification in a wide variety of taxa across the globe and parallel studies revealed that DNA barcoding data can be effectively used in resolving taxonomic ambiguities, detection of cryptic diversity, invasion biology, description of new species etc. A comprehensive survey was carried out for the collection of insects (both adult and immature stages) in district Faisalabad, Pakistan and their DNA was extracted and mitochondrial cytochrome oxidase subunit I (COI-59) barcode sequences was used for molecular identification of immature and adult life stage.This preliminary research work opens new frontiers for developing sustainable insect vectors management programmes for saving lives of mankind from fatal diseases.

Keywords: zoonotic diseases, cytochrome oxidase, and insect vectors, CO1

Procedia PDF Downloads 146
7049 An Experiment with Science Popularization in Rural Schools of Sehore District in Madhya Pradesh, India

Authors: Peeyush Verma, Anil Kumar, Anju Rawlley, Chanchal Mehra

Abstract:

India's school-going population is largely served by an educational system that is, in most rural parts, stuck with methods that emphasize rote learning, endless examinations, and monotonous classroom activities. Rural government schools are generally seen as having poor infrastructure, poor support system and low motivation for teaching as well as learning. It was experienced during the survey of this project that there is lesser motivation of rural boys and girls to attend their schools and still less likely chances to study science, tabooed as “difficult”. An experiment was conducted with the help of Rural Knowledge Network Project through Department of Science and Technology, Govt of India in five remote villages of Sehore District in Madhya Pradesh (India) during 2012-2015. These schools are located about 50-70 Km away from Bhopal, the capital of Madhya Pradesh and can distinctively qualify as average rural schools. Three tier methodology was adapted to unfold the experiment. In first tier randomly selected boys and girls from these schools were taken to a daylong visit to the Regional Science Centre located in Bhopal. In second tier, randomly selected half of those who visited earlier were again taken to the Science Centre to make models of Science. And in third tier, all the boys and girls studying science were exposed to video lectures and study material through web. The results have shown an interesting face towards learning science among youths in rural schools through peer learning or incremental learning. The students who had little or no interest in learning science became good learners and queries started pouring in from the neighbourhood village as well as a few parents requested to take their wards in the project to learn science. The paper presented is a case study of the experiment conducted in five rural schools of Sehore District. It reflects upon the methodology of developing awareness and interest among students and finally engaging them in popularising science through peer-to-peer learning using incremental learning elements. The students, who had a poor perception about science initially, had changed their attitude towards learning science during the project period. The results of this case, however, cannot be generalised unless replicated in the same setting elsewhere.

Keywords: popularisation of science, science temper, incremental learning, peer-to-peer learning

Procedia PDF Downloads 295
7048 Seismic Retrofits – A Catalyst for Minimizing the Building Sector’s Carbon Footprint

Authors: Juliane Spaak

Abstract:

A life-cycle assessment was performed, looking at seven retrofit projects in New Zealand using LCAQuickV3.5. The study found that retrofits save up to 80% of embodied carbon emissions for the structural elements compared to a new building. In other words, it is only a 20% carbon investment to transform and extend a building’s life. In addition, the systems were evaluated by looking at environmental impacts over the design life of these buildings and resilience using FEMA P58 and PACT software. With the increasing interest in Zero Carbon targets, significant changes in the building and construction sector are required. Emissions for buildings arise from both embodied carbon and operations. Based on the significant advancements in building energy technology, the focus is moving more toward embodied carbon, a large portion of which is associated with the structure. Since older buildings make up most of the real estate stock of our cities around the world, their reuse through structural retrofit and wider refurbishment plays an important role in extending the life of a building’s embodied carbon. New Zealand’s building owners and engineers have learned a lot about seismic issues following a decade of significant earthquakes. Recent earthquakes have brought to light the necessity to move away from constructing code-minimum structures that are designed for life safety but are frequently ‘disposable’ after a moderate earthquake event, especially in relation to a structure’s ability to minimize damage. This means weaker buildings sit as ‘carbon liabilities’, with considerably more carbon likely to be expended remediating damage after a shake. Renovating and retrofitting older assets plays a big part in reducing the carbon profile of the buildings sector, as breathing new life into a building’s structure is vastly more sustainable than the highest quality ‘green’ new builds, which are inherently more carbon-intensive. The demolition of viable older buildings (often including heritage buildings) is increasingly at odds with society’s desire for a lower carbon economy. Bringing seismic resilience and carbon best practice together in decision-making can open the door to commercially attractive outcomes, with retrofits that include structural and sustainability upgrades transforming the asset’s revenue generation. Across the global real estate market, tenants are increasingly demanding the buildings they occupy be resilient and aligned with their own climate targets. The relationship between seismic performance and ‘sustainable design’ has yet to fully mature, yet in a wider context is of profound consequence. A whole-of-life carbon perspective on a building means designing for the likely natural hazards within the asset’s expected lifespan, be that earthquake, storms, damage, bushfires, fires, and so on, ¬with financial mitigation (e.g., insurance) part, but not all, of the picture.

Keywords: retrofit, sustainability, earthquake, reuse, carbon, resilient

Procedia PDF Downloads 56
7047 Artificial Intelligence as a Policy Response to Teaching and Learning Issues in Education in Ghana

Authors: Joshua Osondu

Abstract:

This research explores how Artificial Intelligence (AI) can be utilized as a policy response to address teaching and learning (TL) issues in education in Ghana. The dual (AI and human) instructor model is used as a theoretical framework to examine how AI can be employed to improve teaching and learning processes and to equip learners with the necessary skills in the emerging AI society. A qualitative research design was employed to assess the impact of AI on various TL issues, such as teacher workloads, a lack of qualified educators, low academic performance, unequal access to education and educational resources, a lack of participation in learning, and poor access and participation based on gender, place of origin, and disability. The study concludes that AI can be an effective policy response to TL issues in Ghana, as it has the potential to increase students’ participation in learning, increase access to quality education, reduce teacher workloads, and provide more personalized instruction. The findings of this study are significant for filling in the gaps in AI research in Ghana and other developing countries and for motivating the government and educational institutions to implement AI in TL, as this would ensure quality, access, and participation in education and help Ghana industrialize.

Keywords: artificial intelligence, teacher, learner, students, policy response

Procedia PDF Downloads 74
7046 Isolation, Characterization and Myogenic Differentiation of Synovial Mesenchymal Stem Cells

Authors: Fatma Y. Meligy

Abstract:

Objectives: The objectives of this study aimed to isolate and characterize mesenchymal stem cells (MSCs) derived from synovial membrane. Then to assess the potentiality of myogenic differentiation of these isolated MSCs. Methods: The MSCs were isolated from synovial membrane by digestion method. Three adult rats were used. The 5 -azacytidine was added to the cultured cells for one day. The isolated cells and treated cells are assessed using immunoflouresence, flowcytometry, PCR and real time PCR. Results: The isolated stem cells showed morphological aspect of stem cells they showed strong positivity to CD44 and CD90 in immunoflouresence while in CD34 and CD45 showed negative reaction. The treated cells with 5-azacytidine was shown to have positive reaction for desmin. Flowcytometric analysis showed that synovial MSCs had strong positive percentage for CD44(%98)and CD90 (%97) and low percentage for CD34 & CD45 while the treated cells showed positive percentage for myogenic marker myogenin (85%). As regard the PCR and Real time PCR, the treated cells showed positive reaction to the desmin primer. Conclusion: The adult MSCs were isolated successfully from synovial membrane and characterized with stem cell markers. The isolated cells could be differentiated in vitro into myogenic cells. These differentiated cells could be used in auto-replacement of diseased or traumatized muscle cells as a regenerative therapy for muscle disorders and trauma.

Keywords: mesenchymal stem cells, synovial membrane, myogenic differentiation

Procedia PDF Downloads 291
7045 Correlation between Clinical Measurements of Static Foot Posture in Young Adults

Authors: Phornchanok Motantasut, Torkamol Hunsawong, Lugkana Mato, Wanida Donpunha

Abstract:

Identifying abnormal foot posture is important for prescribing appropriate management in patients with lower limb disorders and chronic non-specific low back pain. The normalized navicular height truncated (NNHt) and the foot posture index-6 (FPI-6) have been recommended as the common, simple, valid, and reliable static measures for clinical application. The NNHt is a single plane measure while the FPI-6 is a triple plane measure. At present, there is inadequate information about the correlation between the NNHt and the FPI-6 for categorizing foot posture that leads to a difficulty of choosing the appropriate assessment. Therefore, the present study aimed to determine the correlation between the NNHt and the FPI-6 measures in adult participants with asymptomatic feet. Methods: A cross-sectional descriptive study was conducted in 47 asymptomatic individuals (23 males and 24 females) aged 28.89 ± 7.67 years with body mass index 21.73 ± 1.76 kg/m². The right foot was measured twice by the experienced rater using the NNHt and the FPI-6. A sequence of the measures was randomly arranged for each participant with a 10-minute rest between the tests. The Pearson’s correlation coefficient (r) was used to determine the relationship between the measures. Results: The mean NNHt score was 0.23 ± 0.04 (ranged from 0.15 to 0.36) and the mean FPI-6 score was 4.42 ± 4.36 (ranged from -6 to +11). The Pearson’s correlation coefficient among the NNHt score and the FPI-6 score was -0.872 (p < 0.01). Conclusion: The present finding demonstrates the strong correlation between the NNHt and FPI-6 in adult feet and implies that both measures could be substituted for each other in identifying foot posture.

Keywords: foot posture index, foot type, measurement of foot posture, navicular height

Procedia PDF Downloads 119
7044 University Students' Perceptions of Effective Teaching

Authors: Christine K. Ormsbee, Jeremy S. Robinson

Abstract:

Teacher quality is important for United States universities. It impacts student achievement, program and degree progress, and even retention. While course instructors are still the primary designers and deliverers of instruction in U.S. higher education classrooms, students have become better and more vocal consumers of instruction. They are capable of identifying what instructors do that facilitates their learning or, conversely, what instructors do that makes learning more difficult. Instructors can use students as resources as they design and implement their courses. Students have become more aware of their own learning preferences and processes and can articulate those. While it is not necessarily possible or likely that an instructor can address the widely varying differences in learning preferences represented by a large class of students, it is possible for them to employ general instructional supports that help students understand clearly the instructor's study expectations, identify critical content, efficiently commit content to memory, and develop new skills. Those learning supports include reading guides, test study guides, and other instructor-developed tasks that organize learning for students, hold them accountable for the content, and prepare them to use that material in simulated and real situations. When U.S. university teaching and learning support staff work with instructors to help them identify areas of their teaching to improve, a key part of that assistance includes talking to the instructor member's students. Students are asked to explain what the instructor does that helps them learn, what the instructor does that impedes their learning, and what they wish the instructor would do. Not surprisingly, students are very specific in what they see as helpful learning supports for them. Moreover, they also identify impediments to their success, viewing those as the instructor creating unnecessary barriers to learning. A qualitative survey was developed to provide undergraduate students the opportunity to identify instructor behaviors and/or practices that they thought helped students learn and those behaviors and practices that were perceived as hindrances to student success. That information is used to help instructors implement more student-focused learning supports that facilitate student achievement. In this session, data shared from the survey will focus on supportive instructor behaviors identified by undergraduate students in an institution located in the southwest United States and those behaviors that students perceive as creating unnecessary barriers to their academic success.

Keywords: effective teaching, pedagogy, student engagement, instructional design

Procedia PDF Downloads 65
7043 Learning outside the Box by Using Memory Techniques Skill: Case Study in Indonesia Memory Sports Council

Authors: Muhammad Fajar Suardi, Fathimatufzzahra, Dela Isnaini Sendra

Abstract:

Learning is an activity that has been used to do, especially for a student or academics. But a handful of people have not been using and maximizing their brains work and some also do not know a good brain work time in capturing the lessons, so that knowledge is absorbed is also less than the maximum. Indonesia Memory Sports Council (IMSC) is an institution which is engaged in the performance of the brain and the development of effective learning methods by using several techniques that can be used in considering the lessons and knowledge to grasp well, including: loci method, substitution method, and chain method. This study aims to determine the techniques and benefits of using the method given in learning and memorization by applying memory techniques taught by Indonesia Memory Sports Council (IMSC) to students and the difference if not using this method. This research uses quantitative research with survey method addressed to students of Indonesian Memory Sports Council (IMSC). The results of this study indicate that learn, understand and remember the lesson using the techniques of memory which is taught in Indonesia Memory Sport Council is very effective and faster to absorb the lesson than learning without using the techniques of memory, and this affects the academic achievement of students in each educational institution.

Keywords: chain method, Indonesia memory sports council, loci method, substitution method

Procedia PDF Downloads 270
7042 Project-Based Learning Application: Applying Systems Thinking Concepts to Assure Continuous Improvement

Authors: Kimberley Kennedy

Abstract:

The major findings of this study discuss the importance of understanding and applying Systems thinking concepts to ensure an effective Project-Based Learning environment. A pilot project study of a major pedagogical change was conducted over a five year period with the goal to give students real world, hands-on learning experiences and the opportunity to apply what they had learned over the past two years of their business program. The first two weeks of the fifteen week semester utilized teaching methods of lectures, guest speakers and design thinking workshops to prepare students for the project work. For the remaining thirteen weeks of the semester, the students worked with actual business owners and clients on projects and challenges. The first three years of the five year study focused on student feedback to ensure a quality learning experience and continuous improvement process was developed. The final two years of the study, examined the conceptual understanding and perception of learning and teaching by faculty using Project-Based Learning pedagogy as compared to lectures and more traditional teaching methods was performed. Relevant literature was reviewed and data collected from program faculty participants who completed pre-and post-semester interviews and surveys over a two year period. Systems thinking concepts were applied to better understand the challenges for faculty using Project-Based Learning pedagogy as compared to more traditional teaching methods. Factors such as instructor and student fatigue, motivation, quality of work and enthusiasm were explored to better understand how to provide faculty with effective support and resources when using Project-Based Learning pedagogy as the main teaching method. This study provides value by presenting generalizable, foundational knowledge by offering suggestions for practical solutions to assure student and teacher engagement in Project-Based Learning courses.

Keywords: continuous improvement, project-based learning, systems thinking, teacher engagement

Procedia PDF Downloads 106
7041 Language Development and Learning about Violence

Authors: Karen V. Lee

Abstract:

The background and significance of this study involves research about a music teacher discovering how language development and learning can help her overcome harmful and lasting consequences from sexual violence. Education about intervention resources from language development that helps her cope with consequences influencing her career as teacher. Basic methodology involves the qualitative method of research as theoretical framework where the author is drawn into a deep storied reflection about political issues surrounding teachers who need to overcome social, psychological, and health risk behaviors from violence. Sub-themes involve available education from learning resources to ensure teachers receive social, emotional, physical, spiritual, and intervention resources that evoke visceral, emotional responses from the audience. Major findings share how language development and learning provide helpful resources to victims of violence. It is hoped the research dramatizes an episodic yet incomplete story that highlights the circumstances surrounding the protagonist’s life. In conclusion, the research has a reflexive storied framework that embraces harmful and lasting consequences from sexual violence. The reflexive story of the sensory experience critically seeks verisimilitude by evoking lifelike and believable feelings from others. Thus, the scholarly importance of using language development and learning for intervention resources can provide transformative aspects that contribute to social change. Overall, the circumstance surrounding the story about sexual violence is not uncommon in society. Language development and learning supports the moral mission to help teachers overcome sexual violence that socially impacts their professional lives as victims.

Keywords: intervention, language development and learning, sexual violence, story

Procedia PDF Downloads 319
7040 Machine Learning Model Applied for SCM Processes to Efficiently Determine Its Impacts on the Environment

Authors: Elena Puica

Abstract:

This paper aims to investigate the impact of Supply Chain Management (SCM) on the environment by applying a Machine Learning model while pointing out the efficiency of the technology used. The Machine Learning model was used to derive the efficiency and optimization of technology used in SCM and the environmental impact of SCM processes. The model applied is a predictive classification model and was trained firstly to determine which stage of the SCM has more outputs and secondly to demonstrate the efficiency of using advanced technology in SCM instead of recuring to traditional SCM. The outputs are the emissions generated in the environment, the consumption from different steps in the life cycle, the resulting pollutants/wastes emitted, and all the releases to air, land, and water. This manuscript presents an innovative approach to applying advanced technology in SCM and simultaneously studies the efficiency of technology and the SCM's impact on the environment. Identifying the conceptual relationships between SCM practices and their impact on the environment is a new contribution to the research. The authors can take a forward step in developing recent studies in SCM and its effects on the environment by applying technology.

Keywords: machine-learning model in SCM, SCM processes, SCM and the environmental impact, technology in SCM

Procedia PDF Downloads 99
7039 A Comparative Study of Malware Detection Techniques Using Machine Learning Methods

Authors: Cristina Vatamanu, Doina Cosovan, Dragos Gavrilut, Henri Luchian

Abstract:

In the past few years, the amount of malicious software increased exponentially and, therefore, machine learning algorithms became instrumental in identifying clean and malware files through semi-automated classification. When working with very large datasets, the major challenge is to reach both a very high malware detection rate and a very low false positive rate. Another challenge is to minimize the time needed for the machine learning algorithm to do so. This paper presents a comparative study between different machine learning techniques such as linear classifiers, ensembles, decision trees or various hybrids thereof. The training dataset consists of approximately 2 million clean files and 200.000 infected files, which is a realistic quantitative mixture. The paper investigates the above mentioned methods with respect to both their performance (detection rate and false positive rate) and their practicability.

Keywords: ensembles, false positives, feature selection, one side class algorithm

Procedia PDF Downloads 273
7038 Instance Selection for MI-Support Vector Machines

Authors: Amy M. Kwon

Abstract:

Support vector machine (SVM) is a well-known algorithm in machine learning due to its superior performance, and it also functions well in multiple-instance (MI) problems. Our study proposes a schematic algorithm to select instances based on Hausdorff distance, which can be adapted to SVMs as input vectors under the MI setting. Based on experiments on five benchmark datasets, our strategy for adapting representation outperformed in comparison with original approach. In addition, task execution times (TETs) were reduced by more than 80% based on MissSVM. Hence, it is noteworthy to consider this representation adaptation to SVMs under MI-setting.

Keywords: support vector machine, Margin, Hausdorff distance, representation selection, multiple-instance learning, machine learning

Procedia PDF Downloads 14
7037 Instruct Students Effective Ways to Reach an Advanced Level after Graduation

Authors: Huynh Tan Hoi

Abstract:

Considered as one of the hardest languages in the world, Japanese is still the language that many young people choose to learn. Today, with the development of technology, learning foreign languages in general and Japanese language, in particular, is not an impossible barrier. Learning materials are not only from paper books, songs but also through software programs of smartphones or computers. Especially, students who begin to explore effective skills to study this language need to access modern technologies to improve their learning much better. When using the software, some students may feel embarrassed and challenged, but everything would go smoothly after a few days. After completing the course, students will get more knowledge, achieve a higher knowledge such as N2 or N1 Japanese Language Proficiency Test Certificate. In this research paper, 35 students who are studying at Ho Chi Minh City FPT University were asked to complete the questionnaire at the beginning of July up to August of 2018. Through this research, we realize that with the guidance of lecturers, the necessity of using modern software and some effective methods are indispensable in term of improving quality of teaching and learning process.

Keywords: higher knowledge, Japanese, methods, software, students

Procedia PDF Downloads 201
7036 An Assessment of Digital Platforms, Student Online Learning, Teaching Pedagogies, Research and Training at Kenya College of Accounting University

Authors: Jasmine Renner, Alice Njuguna

Abstract:

The booming technological revolution is driving a change in the mode of delivery systems especially for e-learning and distance learning in higher education. The report and findings of the study; an assessment of digital platforms, student online learning, teaching pedagogies, research and training at Kenya College of Accounting University (hereinafter 'KCA') was undertaken as a joint collaboration project between the Carnegie African Diaspora Fellowship and input from the staff, students and faculty at KCA University. The participants in this assessment/research met for selected days during a six-week period during which, one-one consultations, surveys, questionnaires, foci groups, training, and seminars were conducted to ascertain 'online learning and teaching, curriculum development, research and training at KCA.' The project was organized into an eight-week project workflow with each week culminating in project activities designed to assess digital online teaching and learning at KCA. The project also included the training of distance learning instructors at KCA and the evaluation of KCA’s distance platforms and programs. Additionally, through a curriculum audit and redesign, the project sought to enhance the curriculum development activities related to of distance learning at KCA. The findings of this assessment/research represent the systematic deliberate process of gathering, analyzing and using data collected from DL students, DL staff and lecturers and a librarian personnel in charge of online learning resources and access at KCA. We engaged in one-on-one interviews and discussions with staff, students, and faculty and collated the findings to inform practices that are effective in the ongoing design and development of eLearning earning at KCA University. Overall findings of the project led to the following recommendations. First, there is a need to address infrastructural challenges that led to poor internet connectivity for online learning, training needs and content development for faculty and staff. Second, there is a need to manage cultural impediments within KCA; for example fears of vital change from one platform to another for effectiveness and Institutional goodwill as a vital promise of effective online learning. Third, at a practical and short-term level, the following recommendations based on systematic findings of the research conducted were as follows: there is a need for the following to be adopted at KCA University to promote the effective adoption of online learning: a) an eLearning compatible faculty lab, b) revision of policy to include an eLearn strategy or strategic management, c) faculty and staff recognitions engaged in the process of training for the adoption and implementation of eLearning and d) adequate website resources on eLearning. The report and findings represent a comprehensive approach to a systematic assessment of online teaching and learning, research and training at KCA.

Keywords: e-learning, digital platforms, student online learning, online teaching pedagogies

Procedia PDF Downloads 170
7035 Implementation of the Quality Management System and Development of Organizational Learning: Case of Three Small and Medium-Sized Enterprises in Morocco

Authors: Abdelghani Boudiaf

Abstract:

The profusion of studies relating to the concept of organizational learning shows the importance that has been given to this concept in the management sciences. A few years ago, companies leaned towards ISO 9001 certification; this requires the implementation of the quality management system (QMS). In order for this objective to be achieved, companies must have a set of skills, which pushes them to develop learning through continuous training. The results of empirical research have shown that implementation of the QMS in the company promotes the development of learning. It should also be noted that several types of learning are developed in this sense. Given the nature of skills development is normative in the context of the quality demarche, companies are obliged to qualify and improve the skills of their human resources. Continuous training is the keystone to develop the necessary learning. To carry out continuous training, companies need to be able to identify their real needs by developing training plans based on well-defined engineering. The training process goes obviously through several stages. Initially, training has a general aspect, that is to say, it focuses on topics and actions of a general nature. Subsequently, this is done in a more targeted and more precise way to accompany the evolution of the QMS and also to make the changes decided each time (change of working method, change of practices, change of objectives, change of mentality, etc.). To answer our problematic we opted for the method of qualitative research. It should be noted that the case study method crosses several data collection techniques to explain and understand a phenomenon. Three cases of companies were studied as part of this research work using different data collection techniques related to this method.

Keywords: changing mentalities, continuing training, organizational learning, quality management system, skills development

Procedia PDF Downloads 94
7034 Evaluating and Supporting Student Engagement in Online Learning

Authors: Maria Hopkins

Abstract:

Research on student engagement is founded on a desire to improve the quality of online instruction in both course design and delivery. A high level of student engagement is associated with a wide range of educational practices including purposeful student-faculty contact, peer to peer contact, active and collaborative learning, and positive factors such as student satisfaction, persistence, achievement, and learning. By encouraging student engagement, institutions of higher education can have a positive impact on student success that leads to retention and degree completion. The current research presents the results of an online student engagement survey which support faculty teaching practices to maximize the learning experience for online students. The ‘Indicators of Engaged Learning Online’ provide a framework that measures level of student engagement. Social constructivism and collaborative learning form the theoretical basis of the framework. Social constructivist pedagogy acknowledges the social nature of knowledge and its creation in the minds of individual learners. Some important themes that flow from social constructivism involve the importance of collaboration among instructors and students, active learning vs passive consumption of information, a learning environment that is learner and learning centered, which promotes multiple perspectives, and the use of social tools in the online environment to construct knowledge. The results of the survey indicated themes that emphasized the importance of: Interaction among peers and faculty (collaboration); Timely feedback on assignment/assessments; Faculty participation and visibility; Relevance and real-world application (in terms of assignments, activities, and assessments); and Motivation/interest (the need for faculty to motivate students especially those that may not have an interest in the coursework per se). The qualitative aspect of this student engagement study revealed what instructors did well that made students feel engaged in the course, but also what instructors did not do well, which could inform recommendations to faculty when expectations for teaching a course are reviewed. Furthermore, this research provides evidence for the connection between higher student engagement and persistence and retention in online programs, which supports our rationale for encouraging student engagement, especially in the online environment because attrition rates are higher than in the face-to-face environment.

Keywords: instructional design, learning effectiveness, online learning, student engagement

Procedia PDF Downloads 276
7033 A Learning Effects Research Applied a Mobile Guide System with Augmented Reality for Education Center

Authors: Y. L. Chang, Y. H. Huang

Abstract:

This study designed a mobile guide system that integrates the design principles of guidance and interpretation with augmented reality (AR) as an auxiliary tool for National Taiwan Science Education Center guidance and explored the learning performance of participants who were divided into two visiting groups: AR-guided mode and non-guided mode (without carrying any auxiliary devices). The study included 96 college students as participants and employed a quasi-experimental research design. This study evaluated the learning performance of education center students aided with different guided modes, including their flow experience, activity involvement, learning effects, as well as their attitude and acceptance of using the guide systems. The results showed that (a) the AR guide promoted visitors’ flow experience; (b) the AR-guidance activity involvement and flow experience having a significant positive effect; (c) most of the visitors of mobile guide system with AR elicited a positive response and acceptance attitude. These results confirm the necessity of human–computer–context interaction. Future research can continue exploring the advantages of enhanced learning effectiveness, activity involvement, and flow experience through application of the results of this study.

Keywords: augmented reality, mobile guide system, informal learning, flow experience, activity involvement

Procedia PDF Downloads 210
7032 Noise Reduction in Web Data: A Learning Approach Based on Dynamic User Interests

Authors: Julius Onyancha, Valentina Plekhanova

Abstract:

One of the significant issues facing web users is the amount of noise in web data which hinders the process of finding useful information in relation to their dynamic interests. Current research works consider noise as any data that does not form part of the main web page and propose noise web data reduction tools which mainly focus on eliminating noise in relation to the content and layout of web data. This paper argues that not all data that form part of the main web page is of a user interest and not all noise data is actually noise to a given user. Therefore, learning of noise web data allocated to the user requests ensures not only reduction of noisiness level in a web user profile, but also a decrease in the loss of useful information hence improves the quality of a web user profile. Noise Web Data Learning (NWDL) tool/algorithm capable of learning noise web data in web user profile is proposed. The proposed work considers elimination of noise data in relation to dynamic user interest. In order to validate the performance of the proposed work, an experimental design setup is presented. The results obtained are compared with the current algorithms applied in noise web data reduction process. The experimental results show that the proposed work considers the dynamic change of user interest prior to elimination of noise data. The proposed work contributes towards improving the quality of a web user profile by reducing the amount of useful information eliminated as noise.

Keywords: web log data, web user profile, user interest, noise web data learning, machine learning

Procedia PDF Downloads 245
7031 Deep Learning Based, End-to-End Metaphor Detection in Greek with Recurrent and Convolutional Neural Networks

Authors: Konstantinos Perifanos, Eirini Florou, Dionysis Goutsos

Abstract:

This paper presents and benchmarks a number of end-to-end Deep Learning based models for metaphor detection in Greek. We combine Convolutional Neural Networks and Recurrent Neural Networks with representation learning to bear on the metaphor detection problem for the Greek language. The models presented achieve exceptional accuracy scores, significantly improving the previous state-of-the-art results, which had already achieved accuracy 0.82. Furthermore, no special preprocessing, feature engineering or linguistic knowledge is used in this work. The methods presented achieve accuracy of 0.92 and F-score 0.92 with Convolutional Neural Networks (CNNs) and bidirectional Long Short Term Memory networks (LSTMs). Comparable results of 0.91 accuracy and 0.91 F-score are also achieved with bidirectional Gated Recurrent Units (GRUs) and Convolutional Recurrent Neural Nets (CRNNs). The models are trained and evaluated only on the basis of training tuples, the related sentences and their labels. The outcome is a state-of-the-art collection of metaphor detection models, trained on limited labelled resources, which can be extended to other languages and similar tasks.

Keywords: metaphor detection, deep learning, representation learning, embeddings

Procedia PDF Downloads 131
7030 Face Tracking and Recognition Using Deep Learning Approach

Authors: Degale Desta, Cheng Jian

Abstract:

The most important factor in identifying a person is their face. Even identical twins have their own distinct faces. As a result, identification and face recognition are needed to tell one person from another. A face recognition system is a verification tool used to establish a person's identity using biometrics. Nowadays, face recognition is a common technique used in a variety of applications, including home security systems, criminal identification, and phone unlock systems. This system is more secure because it only requires a facial image instead of other dependencies like a key or card. Face detection and face identification are the two phases that typically make up a human recognition system.The idea behind designing and creating a face recognition system using deep learning with Azure ML Python's OpenCV is explained in this paper. Face recognition is a task that can be accomplished using deep learning, and given the accuracy of this method, it appears to be a suitable approach. To show how accurate the suggested face recognition system is, experimental results are given in 98.46% accuracy using Fast-RCNN Performance of algorithms under different training conditions.

Keywords: deep learning, face recognition, identification, fast-RCNN

Procedia PDF Downloads 117
7029 The Effect of Cooperative Learning on Academic Achievement of Grade Nine Students in Mathematics: The Case of Mettu Secondary and Preparatory School

Authors: Diriba Gemechu, Lamessa Abebe

Abstract:

The aim of this study was to examine the effect of cooperative learning method on student’s academic achievement and on the achievement level over a usual method in teaching different topics of mathematics. The study also examines the perceptions of students towards cooperative learning. Cooperative learning is the instructional strategy in which pairs or small groups of students with different levels of ability work together to accomplish a shared goal. The aim of this cooperation is for students to maximize their own and each other learning, with members striving for joint benefit. The teacher’s role changes from wise on the wise to guide on the side. Cooperative learning due to its influential aspects is the most prevalent teaching-learning technique in the modern world. Therefore the study was conducted in order to examine the effect of cooperative learning on the academic achievement of grade 9 students in Mathematics in case of Mettu secondary school. Two sample sections are randomly selected by which one section served randomly as an experimental and the other as a comparison group. Data gathering instruments are achievement tests and questionnaires. A treatment of STAD method of cooperative learning was provided to the experimental group while the usual method is used in the comparison group. The experiment lasted for one semester. To determine the effect of cooperative learning on the student’s academic achievement, the significance of difference between the scores of groups at 0.05 levels was tested by applying t test. The effect size was calculated to see the strength of the treatment. The student’s perceptions about the method were tested by percentiles of the questionnaires. During data analysis, each group was divided into high and low achievers on basis of their previous Mathematics result. Data analysis revealed that both the experimental and comparison groups were almost equal in Mathematics at the beginning of the experiment. The experimental group out scored significantly than comparison group on posttest. Additionally, the comparison of mean posttest scores of high achievers indicates significant difference between the two groups. The same is true for low achiever students of both groups on posttest. Hence, the result of the study indicates the effectiveness of the method for Mathematics topics as compared to usual method of teaching.

Keywords: academic achievement, comparison group, cooperative learning, experimental group

Procedia PDF Downloads 233
7028 Virtual Player for Learning by Observation to Assist Karate Training

Authors: Kazumoto Tanaka

Abstract:

It is well known that sport skill learning is facilitated by video observation of players’ actions in sports. The optimal viewpoint for the observation of actions depends on sport scenes. On the other hand, it is impossible to change viewpoint for the observation in general, because most videos are filmed from fixed points. The study has tackled the problem and focused on karate match as a first step. The study developed a method for observing karate player’s actions from any point of view by using 3D-CG model (i.e. virtual player) obtained from video images, and verified the effectiveness of the method on karate match.

Keywords: computer graphics, karate training, learning by observation, motion capture, virtual player

Procedia PDF Downloads 258
7027 Design and Implementation a Platform for Adaptive Online Learning Based on Fuzzy Logic

Authors: Budoor Al Abid

Abstract:

Educational systems are increasingly provided as open online services, providing guidance and support for individual learners. To adapt the learning systems, a proper evaluation must be made. This paper builds the evaluation model Fuzzy C Means Adaptive System (FCMAS) based on data mining techniques to assess the difficulty of the questions. The following steps are implemented; first using a dataset from an online international learning system called (slepemapy.cz) the dataset contains over 1300000 records with 9 features for students, questions and answers information with feedback evaluation. Next, a normalization process as preprocessing step was applied. Then FCM clustering algorithms are used to adaptive the difficulty of the questions. The result is three cluster labeled data depending on the higher Wight (easy, Intermediate, difficult). The FCM algorithm gives a label to all the questions one by one. Then Random Forest (RF) Classifier model is constructed on the clustered dataset uses 70% of the dataset for training and 30% for testing; the result of the model is a 99.9% accuracy rate. This approach improves the Adaptive E-learning system because it depends on the student behavior and gives accurate results in the evaluation process more than the evaluation system that depends on feedback only.

Keywords: machine learning, adaptive, fuzzy logic, data mining

Procedia PDF Downloads 173
7026 Post-Processing Method for Performance Improvement of Aerial Image Parcel Segmentation

Authors: Donghee Noh, Seonhyeong Kim, Junhwan Choi, Heegon Kim, Sooho Jung, Keunho Park

Abstract:

In this paper, we describe an image post-processing method to enhance the performance of the parcel segmentation method using deep learning-based aerial images conducted in previous studies. The study results were evaluated using a confusion matrix, IoU, Precision, Recall, and F1-Score. In the case of the confusion matrix, it was observed that the false positive value, which is the result of misclassification, was greatly reduced as a result of image post-processing. The average IoU was 0.9688 in the image post-processing, which is higher than the deep learning result of 0.8362, and the F1-Score was also 0.9822 in the image post-processing, which was higher than the deep learning result of 0.8850. As a result of the experiment, it was found that the proposed technique positively complements the deep learning results in segmenting the parcel of interest.

Keywords: aerial image, image process, machine vision, open field smart farm, segmentation

Procedia PDF Downloads 61
7025 Effect of E-Governance and E-Learning Platform on Access to University Education by Public Servants in Nigeria

Authors: Nwamaka Patricia Ibeme, Musa Zakari

Abstract:

E-learning is made more effective because; it is enable student to students to easily interact, share, and collaborate across time and space with the help of e-governance platform. Zoom and the Microsoft classroom team can invite students from all around the world to join a conversation on a certain subject simultaneously. E-governance may be able to work on problem solving skills, as well as brainstorming and developing ideas. As a result of the shared experiences and knowledge, students are able to express themselves and reflect on their own learning." For students, e-governance facilities provide greater opportunity for students to build critical (higher order) thinking abilities through constructive learning methods. Students' critical thinking abilities may improve with more time spent in an online classroom. Students' inventiveness can be enhanced through the use of computer-based instruction. Discover multimedia tools and produce products in the styles that are easily available through games, Compact Disks, and television. The use of e-learning has increased both teaching and learning quality by combining student autonomy, capacity, and creativity over time in developed countries." Teachers are catalysts for the integration of technology through Information and Communication Technology, and e-learning supports teaching by simplifying access to course content." Creating an Information and Communication Technology class will be much easier if educational institutions provide teachers with the assistance, equipment, and resources they need. The study adopted survey research design. The populations of the study are Students and staff. The study adopted a simple random sampling technique to select a representative population. Both primary and secondary method of data collection was used to obtain the data. A chi-square statistical technique was used to analyze. Finding from the study revealed that e-learning has increase accesses to universities educational by public servants in Nigeria. Public servants in Nigeria have utilized e-learning and Online Distance Learning (ODL) programme to into various degree programmes. Finding also shows that E-learning plays an important role in teaching because it is oriented toward the use of information and communication technologies that have become a part of the everyday life and day-to-day business. E-learning contributes to traditional teaching methods and provides many advantages to society and citizens. The study recommends that the e-learning tools and internet facilities should be upgrade to foster any network challenges in the online facilitation and lecture delivery system.

Keywords: E-governance, E-learning, online distance learning, university education public servants, Nigeria

Procedia PDF Downloads 51