Abstract: The use of technology has benefited society in more ways than one ever thought possible. Unfortunately, as society’s knowledge of technology has advanced, so has its knowledge of ways to use technology to manipulate others. This has led to a simultaneous advancement in the world of fraud. Machine learning techniques can offer a possible solution to help decrease these advancements. This research explores how the use of various machine learning techniques can aid in detecting fraudulent activity across two different types of fraudulent datasets, and the accuracy, precision, recall, and F1 were recorded for each method. Each machine learning model was also tested across five different training and testing splits in order to discover which split and technique would lead to the most optimal results.
Abstract: Problem: Senior citizens have been facing a challenging reality as a result of strict public health measures designed to protect people from the COVID-19 outbreak. These include the risk of social isolation due to the inability of the elderly to integrate with technology. Never before have Information and Communication Technology (ICT) skills become essential for their everyday life. Although third-age ICT education and lifelong learning are widely supported by universities and governments, there is a lack of literature on which teaching strategy/methodology to adopt in an entirely online ICT course aimed at third-age learners. This contribution aims to present an application of the Think-Pair-Share (TPS) learning method in an ICT third-age virtual classroom with an intergenerational approach to conducting online group labs and review activities. Research Question: Is collaborative learning suitable and effective, in terms of student engagement and learning outcomes, in an online ICT course for the elderly? Methods: In the TPS strategy a problem is posed by the teacher, students have time to think about it individually, and then they work in pairs (or small groups) to solve the problem and share their ideas with the entire class. We performed four experiments in the ICT course of the University of the Third Age of Genova (University of Genova, Italy) on the Microsoft Teams platform. The study cohort consisted of 26 students over the age of 45. Data were collected through online questionnaires. Two have been proposed, one at the end of the first activity and another at the end of the course. They consisted of five and three close-ended questions, respectively. The answers were on a Likert scale (from 1 to 4) except two questions (which asked the number of correct answers given individually and in groups) and the field for free comments/suggestions. Results: Groups achieve better results than individual students (with scores greater than one order of magnitude) and most students found TPS helpful to work in groups and interact with their peers. Insights: From these early results, it appears that TPS is suitable for an online third-age ICT classroom and useful for promoting discussion and active learning. Despite this, our work has several limitations. First of all, the results highlight the need for more data to be able to perform a statistical analysis in order to determine the effectiveness of this methodology in terms of student engagement and learning outcomes as future direction.
Abstract: The adoption of modern lightweight virtualization often comes with new threats and network vulnerabilities. This paper seeks to assess this with a different approach studying the behavior of a testbed built with tools such as Kernel-based Virtual Machine (KVM), LinuX Containers (LXC) and Docker, by performing stress tests within a platform where students experiment simultaneously with cyber-attacks, and thus observe the impact on the campus network and also find the best solution for cyber-security learning. Interesting outcomes can be found in the literature comparing these technologies. It is, however, difficult to find results of the effects on the global network where experiments are carried out. Our work shows that other physical hosts and the faculty network were impacted while performing these trials. The problems found are discussed, as well as security solutions and the adoption of new network policies.
Abstract: This systematic literature review sought to explore the dimensions of diversity that can affect classroom learning. This review is significant as it can aid educators in reaching more of their diverse student population and creating supportive classrooms for teachers and students. For this study, peer-reviewed articles were found and compiled using Google Scholar. Key terms used in the search include student individuality, classroom equality, student development, teacher development, and teacher individuality. Relevant educational standards such as Common Core and Partnership for the 21st Century were also included as part of this review. Student and teacher individuality and equality is discussed as well as methods to grow both within educational settings. Embracing student and teacher individuality was found to be key as it may affect how each person interacts with given information. One method to grow individuality and equality in educational settings included drafting and employing revised teaching standards which include various Common Core and US State standards. Another was to use educational theories such as constructivism, cognitive learning, and Experiential Learning Theory. However, barriers to growing individuality, such as not acknowledging differences in a population’s dimensions of diversity, still exist. Studies found preserving the dimensions of diversity owned by both teachers and students yielded more positive and beneficial classroom experiences.
Abstract: This work describes a system that uses electromyography (EMG) signals obtained from muscle sensors and an Artificial Neural Network (ANN) for signal classification and pattern recognition that is used to control a small unmanned aerial vehicle using specific arm movements. The main objective of this endeavor is the development of an intelligent interface that allows the user to control the flight of a drone beyond direct manual control. The sensor used were the MyoWare Muscle sensor which contains two EMG electrodes used to collect signals from the posterior (extensor) and anterior (flexor) forearm, and the bicep. The collection of the raw signals from each sensor was performed using an Arduino Uno. Data processing algorithms were developed with the purpose of classifying the signals generated by the arm’s muscles when performing specific movements, namely: flexing, resting, and motion of the arm. With these arm motions roll control of the drone was achieved. MATLAB software was utilized to condition the signals and prepare them for the classification. To generate the input vector for the ANN and perform the classification, the root mean square and the standard deviation were processed for the signals from each electrode. The neuromuscular information was trained using an ANN with a single 10 neurons hidden layer to categorize the four targets. The result of the classification shows that an accuracy of 97.5% was obtained. Afterwards, classification results are used to generate the appropriate control signals from the computer to the drone through a Wi-Fi network connection. These procedures were successfully tested, where the drone responded successfully in real time to the commanded inputs.
Abstract: Machine learning has evolved from an area of academic research to a real-world applied field. This change comes with challenges, gaps and differences exist between common practices in academic environments and the ones in production environments. Following continuous integration, development and delivery practices in software engineering, similar trends have happened in machine learning (ML) systems, called MLOps. In this paper we propose a framework that helps to streamline and introduce best practices that facilitate the ML lifecycle in an industrial setting. This framework can be used as a template that can be customized to implement various machine learning experiments. The proposed framework is modular and can be recomposed to be adapted to various use cases (e.g. data versioning, remote training on Cloud). The framework inherits practices from DevOps and introduces other practices that are unique to the machine learning system (e.g.data versioning). Our MLOps practices automate the entire machine learning lifecycle, bridge the gap between development and operation.
Abstract: This project is a study of learning activities of creating experience from actual work performance to enhance career skills and technological usage abilities for uses in advertising career work performance for undergraduate students who enroll in the Creative Strategies for Advertising Course. The instructional model consisted of two learning approaches: (1) simulation-based learning, which is the learning with the use of simulations of working in various sections of creative advertisement work with their own work process and steps as well as the virtual technology learning in advertising companies; and (2) project-based learning, which is the learning that the learners engage in actual work performance based on the process of creating and producing creative advertisement works to be present on new media channels. The results of learning management showed that the effects on the students in various aspects were as follows: (1) the students had experience in the advertising process at the higher level; and (2) the students had work performance skills from the actual work performance that enabled them to possess the abilities to create and present their own work; also, they had created more efficient work outcomes and disseminated them on new media channels at a better level.
Abstract: Due to the COVID-19 pandemic, its impacts on education all over the world, and the problems arising from the use of traditional methods in education during the pandemic, it was necessary to apply alternative solutions to achieve educational goals. In this regard, electronic content production through screen recording became popular among many teachers. However, the production of screen-recorded videos requires special technical and pedagogical considerations. The purpose of this study was to extract and present the technical and pedagogical considerations for producing screen-recorded videos to provide a useful and comprehensive guideline for e-content producers. This study was applied research, the design was descriptive, and data collection has been done using qualitative method. In order to collect the data, 524 previously produced screen-recorded videos were evaluated by using an open-ended questionnaire. After collecting the data, they were categorized, and finally, 83 items as technical and pedagogical considerations in the form of 5 domains were determined. By applying such considerations, it is expected to decrease producing and editing time, increase the technical and pedagogical quality, and finally facilitate and enhance the processes of teaching and learning.
Abstract: Early detection of anomalies in data centers is important to reduce downtimes and the costs of periodic maintenance. However, there is little research on this topic and even fewer on the fusion of sensor data for the detection of abnormal events. The goal of this paper is to propose a method for anomaly detection in data centers by combining sensor data (temperature, humidity, power) and deep learning models. The model described in the paper uses one autoencoder per sensor to reconstruct the inputs. The auto-encoders contain Long-Short Term Memory (LSTM) layers and are trained using the normal samples of the relevant sensors selected by correlation analysis. The difference signal between the input and its reconstruction is then used to classify the samples using feature extraction and a random forest classifier. The data measured by the sensors of a data center between January 2019 and May 2020 are used to train the model, while the data between June 2020 and May 2021 are used to assess it. Performances of the model are assessed a posteriori through F1-score by comparing detected anomalies with the data center’s history. The proposed model outperforms the state-of-the-art reconstruction method, which uses only one autoencoder taking multivariate sequences and detects an anomaly with a threshold on the reconstruction error, with an F1-score of 83.60% compared to 24.16%.
Abstract: Deep reinforcement learning (deep RL) algorithms leverage the symbolic power of complex controllers by automating it by mapping sensory inputs to low-level actions. Deep RL eliminates the complex robot dynamics with minimal engineering. Deep RL provides high-risk involvement by directly implementing it in real-world scenarios and also high sensitivity towards hyperparameters. Tuning of hyperparameters on a pneumatic quadruped robot becomes very expensive through trial-and-error learning. This paper presents an automated learning control for a pneumatic quadruped robot using sample efficient deep Q learning, enabling minimal tuning and very few trials to learn the neural network. Long training hours may degrade the pneumatic cylinder due to jerk actions originated through stochastic weights. We applied this method to the pneumatic quadruped robot, which resulted in a hopping gait. In our process, we eliminated the use of a simulator and acquired a stable gait. This approach evolves so that the resultant gait matures more sturdy towards any stochastic changes in the environment. We further show that our algorithm performed very well as compared to programmed gait using robot dynamics.
Abstract: This study aims to reveal migrant women English instructors' workplace learning experiences in Canadian post-secondary institutions in Ontario. Migrant women English instructors in higher education are an understudied group of teachers. This study employs a qualitative research paradigm. Mezirow’s Transformative Learning Theory is an essential lens for the researcher to explain, analyze, and interpret the research data. It is a collaborative research project. The researcher and participants cooperatively create photographic or other artwork data responding to the research questions. Photovoice and arts-informed data collection methodology are the main methods. Research participants engage in the study as co-researchers and inquire about their own workplace learning experiences, actively utilizing their critical self-reflective and dialogic skills. Co-researchers individually select the forms of artwork they prefer to engage with to represent their transformative workplace learning experiences about the Canadian workplace cultures that they underwent while working with colleagues and administrators in the workplace. Once the co-researchers generate their cultural artifacts as research data, they collaboratively interpret their artworks with the researcher and other volunteer co-researchers. Co-researchers jointly investigate the themes emerging from the artworks. They also interpret the meanings of their own and others’ workplace learning experiences embedded in the artworks through interactive one-on-one or group interviews. The following are the research questions that the migrant women English instructor participants examine and answer: (1) What have they learned about their workplace culture and how do they explain their learning experiences? (2) How transformative have their learning experiences been at work? (3) How have their colleagues and administrators influenced their transformative learning? (4) What kind of support have they received? What supports have been valuable to them and what changes would they like to see? (5) What have their learning experiences transformed? (6) What has this arts-informed research process transformed? The study findings implicate English language instructor support currently practiced in post-secondary English language programs in Ontario, Canada, especially for migrant women English instructors. This research is a doctoral empirical study in progress. This study has the urgency to address the research problem that few studies have investigated migrant English instructors’ professional learning and support issues in the workplace, precisely that of English instructors working with adult learners in Canada. While appropriate social and professional support for migrant English instructors is required throughout the country, the present workplace realities in Ontario's English language programs need to be heard soon. For that purpose, the conceptualization of this study is crucial. It makes the investigation of under-represented instructors’ under-researched social phenomena, workplace learning and support, viable and rigorous. This paper demonstrates the robust theorization of English instructors’ workplace experiences using Mezirow’s Transformative Learning Theory in the English language teacher education field.
Abstract: t-SNE is an embedding method that the data science community has widely used. It helps two main tasks: to display results by coloring items according to the item class or feature value; and for forensic, giving a first overview of the dataset distribution. Two interesting characteristics of t-SNE are the structure preservation property and the answer to the crowding problem, where all neighbors in high dimensional space cannot be represented correctly in low dimensional space. t-SNE preserves the local neighborhood, and similar items are nicely spaced by adjusting to the local density. These two characteristics produce a meaningful representation, where the cluster area is proportional to its size in number, and relationships between clusters are materialized by closeness on the embedding. This algorithm is non-parametric. The transformation from a high to low dimensional space is described but not learned. Two initializations of the algorithm would lead to two different embedding. In a forensic approach, analysts would like to compare two or more datasets using their embedding. A naive approach would be to embed all datasets together. However, this process is costly as the complexity of t-SNE is quadratic, and would be infeasible for too many datasets. Another approach would be to learn a parametric model over an embedding built with a subset of data. While this approach is highly scalable, points could be mapped at the same exact position, making them indistinguishable. This type of model would be unable to adapt to new outliers nor concept drift. This paper presents a methodology to reuse an embedding to create a new one, where cluster positions are preserved. The optimization process minimizes two costs, one relative to the embedding shape and the second relative to the support embedding’ match. The embedding with the support process can be repeated more than once, with the newly obtained embedding. The successive embedding can be used to study the impact of one variable over the dataset distribution or monitor changes over time. This method has the same complexity as t-SNE per embedding, and memory requirements are only doubled. For a dataset of n elements sorted and split into k subsets, the total embedding complexity would be reduced from O(n2) to O(n2/k), and the memory requirement from n2 to 2(n/k)2 which enables computation on recent laptops. The method showed promising results on a real-world dataset, allowing to observe the birth, evolution and death of clusters. The proposed approach facilitates identifying significant trends and changes, which empowers the monitoring high dimensional datasets’ dynamics.
Abstract: Currently the most prevalent deep learning methods require a large amount of data for training, whereas few-shot learning tries to learn a model from limited data without extensive retraining. In this paper, we present a loss function based on triplet loss for solving few-shot problem using metric based learning. Instead of setting the margin distance in triplet loss as a constant number empirically, we propose an adaptive margin distance strategy to obtain the appropriate margin distance automatically. We implement the strategy in the deep siamese network for deep metric embedding, by utilizing an optimization approach by penalizing the worst case and rewarding the best. Our experiments on image recognition and co-segmentation model demonstrate that using our proposed triplet loss with adaptive margin distance can significantly improve the performance.
Abstract: Analysis of the human microbiome using metagenomic
sequencing data has demonstrated high ability in discriminating
various human diseases. Raw metagenomic sequencing data require
multiple complex and computationally heavy bioinformatics steps
prior to data analysis. Such data contain millions of short sequences
read from the fragmented DNA sequences and stored as fastq files.
Conventional processing pipelines consist in multiple steps including
quality control, filtering, alignment of sequences against genomic
catalogs (genes, species, taxonomic levels, functional pathways,
etc.). These pipelines are complex to use, time consuming and
rely on a large number of parameters that often provide variability
and impact the estimation of the microbiome elements. Training
Deep Neural Networks directly from raw sequencing data is a
promising approach to bypass some of the challenges associated with
mainstream bioinformatics pipelines. Most of these methods use the
concept of word and sentence embeddings that create a meaningful
and numerical representation of DNA sequences, while extracting
features and reducing the dimensionality of the data. In this paper
we present an end-to-end approach that classifies patients into disease
groups directly from raw metagenomic reads: metagenome2vec. This
approach is composed of four steps (i) generating a vocabulary of
k-mers and learning their numerical embeddings; (ii) learning DNA
sequence (read) embeddings; (iii) identifying the genome from which
the sequence is most likely to come and (iv) training a multiple
instance learning classifier which predicts the phenotype based on
the vector representation of the raw data. An attention mechanism
is applied in the network so that the model can be interpreted,
assigning a weight to the influence of the prediction for each genome.
Using two public real-life data-sets as well a simulated one, we
demonstrated that this original approach reaches high performance,
comparable with the state-of-the-art methods applied directly on
processed data though mainstream bioinformatics workflows. These
results are encouraging for this proof of concept work. We believe
that with further dedication, the DNN models have the potential to
surpass mainstream bioinformatics workflows in disease classification
tasks.
Abstract: Clustering is an unsupervised learning technique for aggregating data objects into meaningful classes so that intra cluster similarity is maximized and inter cluster similarity is minimized in data mining. However, no single clustering algorithm proves to be the most effective in producing the best result. As a result, a new challenging technique known as the cluster ensemble approach has blossomed in order to determine the solution to this problem. For the cluster analysis issue, this new technique is a successful approach. The cluster ensemble's main goal is to combine similar clustering solutions in a way that achieves the precision while also improving the quality of individual data clustering. Because of the massive and rapid creation of new approaches in the field of data mining, the ongoing interest in inventing novel algorithms necessitates a thorough examination of current techniques and future innovation. This paper presents a comparative analysis of various cluster ensemble approaches, including their methodologies, formal working process, and standard accuracy and error rates. As a result, the society of clustering practitioners will benefit from this exploratory and clear research, which will aid in determining the most appropriate solution to the problem at hand.
Abstract: This paper aimed at discussing how to urge middle and high school Arab students in Israel to be aware of the importance of and investing in learning mathematics. In the first phase of the study, three questionnaires were passed to two nine-grade classes, one on Awareness, one on Awakeness and one on Learning. One of the two classes was an outstanding class from a public school (PUBS) of 31 students, and the other a heterogeneous class from a private school (PRIS) with 31 students. The Learning questionnaire which was administrated to the Awareness and Awareness topics was passed to PRIS and the Awareness and Awareness Questionnaires were passed to the PUBS class After two months we passed the post-questionnaire to both classes to validate the long-term impact of the study. The findings of the study show that awakeness and awareness processes have an effect on the math learning process, on its context in students' daily lives and their growing interest in learning math.
Abstract: There has been considerable growth in online learning. Researchers continue to explore the impact various methods of delivery. Podcasting is a popular method for sharing information. The purpose of this study was to examine the impact of student motivation and the perception of the acquisition of knowledge in an online environment of a skill-based class. 25 students in a school psychology graduate class completed a pretest and posttest examining podcast use and familiarity. In addition, at the completion of the course they were administered a modified version of the Instructional Materials Motivation Survey. The four subscales were examined (attention, relevance, confidence, and satisfaction). Results indicated that students are motivated, they perceive podcasts as positive instructional tools, and students are successful in acquiring the needed information. Additional benefits of using podcasts and recommendations in school psychology training are discussed.
Abstract: Lesson study is used as an instructional technique to promote both student and faculty learning. However, little is known about the usefulness of learning communities in supporting results of lesson study on the self-efficacy and development for tenure-track faculty. This study investigated the impact of participation in a lesson study learning community on 34 new faculty members at a mid-size Midwestern University, specifically regarding implementing lesson study evaluations by new faculty on their reported self-efficacy. Results indicate that participation in a lesson study learning community significantly increased faculty members’ lesson study self-efficacy as well as grant and manuscript production over one academic year. Suggestions for future lesson study around faculty learning communities are discussed.
Abstract: Estimating the 6D pose of objects is a core step for robot bin-picking tasks. The problem is that various objects are usually randomly stacked with heavy occlusion in real applications. In this work, we propose a method to regress 6D poses by predicting three points for each object in the 3D point cloud through deep learning. To solve the ambiguity of symmetric pose, we propose a labeling method to help the network converge better. Based on the predicted pose, an iterative method is employed for pose optimization. In real-world experiments, our method outperforms the classical approach in both precision and recall.
Abstract: Distance learning provides a flexible approach to education, enabling busy learners to complete their coursework at their own pace, on their own schedule, and from a convenient location. This flexibility combined with a series of other issues; make the benefits of lifelong distance learning numerous. The purpose of the paper is to investigate whether distance education can contribute to the improvement of adult skills in Greece, highlighting in this way the necessity of the lifelong distance learning. To investigate this goal, a questionnaire is constructed and analyzed based on responses from 3,016 attendees of lifelong distance learning programs in the e-learning of the National and Kapodistrian University of Athens in Greece. In order to do so, a series of relationships is examined including the effects of a) the gender, b) the previous educational level, c) the current employment status, and d) the method used in the distance learning program, on the development of new general, technical, administrative, social, cultural, entrepreneurial and green skills. The basic conclusions that emerge after using a binary logistic framework are that the following factors are critical in order to develop new skills: the gender, the education level and the educational method used in the lifelong distance learning program. The skills more significantly affected by those factors are the acquiring new skills in general, as well as acquiring general, language and cultural, entrepreneurial and green skills, while for technical and social skills only gender and educational method play a crucial role. Moreover, routine skills and social skills are not affected by the four factors included in the analysis.