Abstract: We as humans use words with accompanying visual and facial cues to communicate effectively. Classifying facial emotion using computer vision methodologies has been an active research area in the computer vision field. In this paper, we propose a simple method for facial expression recognition that enhances accuracy. We tested our method on the FER-2013 dataset that contains static images. Instead of using Histogram equalization to preprocess the dataset, we used Unsharp Mask to emphasize texture and details and sharpened the edges. We also used ImageDataGenerator from Keras library for data augmentation. Then we used Convolutional Neural Networks (CNN) model to classify the images into 7 different facial expressions, yielding an accuracy of 69.46% on the test set. Our results show that using image preprocessing such as the sharpening technique for a CNN model can improve the performance, even when the CNN model is relatively simple.
Abstract: In the last 20 years, Knowledge Based Engineering (KBE) has shown its advantages in product development in different engineering areas such as automation, mechanical, civil and aerospace engineering in terms of digital design automation and cost reduction by automating repetitive design tasks through capturing, integrating, utilising and reusing the existing knowledge required in various aspects of the product design. However, in primary design stages, the descriptive information of a product is discrete and unorganized while knowledge is in various forms instead of pure data. Thus, it is crucial to have an integrated product model which can represent the entire product information and its associated knowledge at the beginning of the product design. One of the shortcomings of the existing product models is a lack of required knowledge representation in various aspects of product design and its mapping to an interoperable schema. To overcome the limitation of the existing product model and methodologies, two key factors are considered. First, the product model must have well-defined classes that can represent the entire product information and its associated knowledge. Second, the product model needs to be represented in an interoperable schema to ensure a steady data exchange between different product modelling platforms and CAD software. This paper introduced a method to provide a general product model as a generative representation of a product, which consists of the geometry information and non-geometry information, through a product modelling framework. The proposed method for capturing the knowledge from the designers through a knowledge file provides a simple and efficient way of collecting and transferring knowledge. Further, the knowledge schema provides a clear view and format on the data that needed to be gathered in order to achieve a unified knowledge exchange between different platforms. This study used a game-based platform to make product modelling environment accessible for non-engineers. Further the paper goes on to test use case based on the proposed game-based product modelling environment to validate the effectiveness among non-engineers.
Abstract: For security purposes, it is important to detect passwords entered by unauthorized users. With traditional alphanumeric passwords, if the content of a password is acquired and correctly entered by an intruder, it is impossible to differentiate the password entered by the intruder from those entered by the authorized user because the password entries contain precisely the same character set. However, no two entries for the gesture-based passwords, even those entered by the person who created the password, will be identical. There are always variations between entries, such as the shape and length of each stroke, the location of each stroke, and the speed of drawing. It is possible that passwords entered by the unauthorized user contain higher levels of variations when compared with those entered by the authorized user (the creator). The difference in the levels of variations may provide cues to detect unauthorized entries. To test this hypothesis, we designed an empirical study, collected and analyzed the data with the help of machine-learning algorithms. The results of the study are significant.
Abstract: Learning to request in a foreign language is a key ability within pragmatics language teaching. This paper examines how requests are taught in English Unlimited Book 3 (Cambridge University Press), an EFL textbook series employed by King Abdulaziz University in Jeddah, Saudi Arabia to teach advanced foundation year students English. The focus of analysis is the evaluation of the request linguistic strategies present in the textbook, frequency of the use of these strategies, and the contextual information provided on the use of these linguistic forms. The researcher collected all the linguistic forms which consisted of the request speech act and divided them into levels employing the CCSARP request coding manual. Findings demonstrated that simple and commonly employed request strategies are introduced. Looking closely at the exercises throughout the chapters, it was noticeable that the book exclusively employed the most direct form of requesting (the imperative) when giving learners instructions: e.g. listen, write, ask, answer, read, look, complete, choose, talk, think, etc. The book also made use of some other request strategies such as ‘hedged performatives’ and ‘query preparatory’. However, it was also found that many strategies were not dealt with in the book, specifically strategies with combined functions (e.g. possibility, ability). On a sociopragmatic level, a strong focus was found to exist on standard situations in which relations between the requester and requestee are clear. In general, contextual information was communicated implicitly only. The textbook did not seem to differentiate between formal and informal request contexts (register) which might consequently impel students to overgeneralize. The paper closes with some recommendations for textbook and curriculum designers. Findings are also contrasted with previous results from similar body of research on EFL requests.
Abstract: Neural networks are appealing for many applications since they are able to learn complex non-linear relationships between input and output data. As the number of neurons and layers in a neural network increase, it is possible to represent more complex relationships with automatically extracted features. Nowadays Deep Neural Networks (DNNs) are widely used in Computer Vision problems such as; classification, object detection, segmentation image editing etc. In this work, Facial Emotion Recognition task is performed by proposed Convolutional Neural Network (CNN)-based DNN architecture using FER2013 Dataset. Moreover, the effects of different hyperparameters (activation function, kernel size, initializer, batch size and network size) are investigated and ablation study results for Pooling Layer, Dropout and Batch Normalization are presented.
Abstract: Research in predictive maintenance modeling has improved in the recent years to predict failures and needed maintenance with high accuracy, saving cost and improving manufacturing efficiency. However, classic prediction models provide little valuable insight towards the most important features contributing to the failure. By analyzing and quantifying feature importance in predictive maintenance models, cost saving can be optimized based on business goals. First, multiple classifiers are evaluated with cross-validation to predict the multi-class of failures. Second, predictive performance with features provided by different feature selection algorithms are further analyzed. Third, features selected by different algorithms are ranked and combined based on their predictive power. Finally, linear explainer SHAP (SHapley Additive exPlanations) is applied to interpret classifier behavior and provide further insight towards the specific roles of features in both local predictions and global model behavior. The results of the experiments suggest that certain features play dominant roles in predictive models while others have significantly less impact on the overall performance. Moreover, for multi-class prediction of machine failures, the most important features vary with type of machine failures. The results may lead to improved productivity and cost saving by prioritizing sensor deployment, data collection, and data processing of more important features over less importance features.
Abstract: Network security is role of the ICT environment
because malicious users are continually growing that realm of
education, business, and then related with ICT. The network security
contravention is typically described and examined centrally based
on a security event management system. The firewalls, Intrusion
Detection System (IDS), and Intrusion Prevention System are
becoming essential to monitor or prevent of potential violations,
incidents attack, and imminent threats. In this system, the firewall
rules are set only for where the system policies are needed. Dataset
deployed in this system are derived from the testbed environment. The
traffic as in DoS and PortScan traffics are applied in the testbed with
firewall and IDS implementation. The network traffics are classified
as normal or attacks in the existing testbed environment based on
six machine learning classification methods applied in the system.
It is required to be tested to get datasets and applied for DoS and
PortScan. The dataset is based on CICIDS2017 and some features
have been added. This system tested 26 features from the applied
dataset. The system is to reduce false positive rates and to improve
accuracy in the implemented testbed design. The system also proves
good performance by selecting important features and comparing
existing a dataset by machine learning classifiers.
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: Maneuver decision-making plays a critical role in high-performance intelligent driving. This paper proposes a risk assessment-based decision-making network (RADMN) to address the problem of driving strategy for the commercial vehicle. RADMN integrates two networks, aiming at identifying the risk degree of collision and rollover and providing decisions to ensure the effectiveness and reliability of driving strategy. In the risk assessment module, risk degrees of the backward collision, forward collision and rollover are quantified for hazard recognition. In the decision module, a deep reinforcement learning based on multi-objective optimization (DRL-MOO) algorithm is designed, which comprehensively considers the risk degree and motion states of each traffic participant. To evaluate the performance of the proposed framework, Prescan/Simulink joint simulation was conducted in highway scenarios. Experimental results validate the effectiveness and reliability of the proposed RADMN. The output driving strategy can guarantee the safety and provide key technical support for the realization of autonomous driving of commercial vehicles.
Abstract: Inclusion of any design project in an undergraduate electrical and electronic engineering curriculum and producing creative ideas in the final year capstone design projects have received numerous comments at the Board of Accreditation for Engineering and Technical Education (BAETE) several times by the mentors and visiting program evaluator team members at different public and private universities in Bangladesh. To eradicate this deficiency which is needed for getting the program accreditation, a thorough change was required in the Department of Electrical and Electronic Engineering (EEE) for its BSc in EEE program at Southeast University, Dhaka, Bangladesh. We suggested making changes in the course curriculum titles and contents, emphasizing to include capstone design projects, question setting, examining students through other standard methods, selecting and retaining Outcome-Based Education (OBE)-oriented engineering faculty members, improving laboratories through purchasing new equipment and software as well as developing new experiments for each laboratory courses, and engaging the students to practical designs in various courses and final year projects. This paper reports on capstone design project course objectives, course outcomes, mapping with the program outcomes, cognitive domain of learning, assessment schemes, guidelines, suggestions and recommendations for supervision processes, assessment strategy, and rubric setting, etc. It is expected that this will substantially improve the capstone design projects offering, supervision, and assessment in the undergraduate EEE program to fulfill the arduous requirements of BAETE accreditation based on OBE.
Abstract: The use of deep learning for species identification in camera trap images has revolutionised our ability to study, conserve and monitor species in a highly efficient and unobtrusive manner, with state-of-the-art models achieving accuracies surpassing the accuracy of manual human classification. The high imbalance of camera trap datasets, however, results in poor accuracies for minority (rare or endangered) species due to their relative insignificance to the overall model accuracy. This paper investigates the use of Focal Loss, in comparison to the traditional Cross Entropy Loss function, to improve the identification of minority species in the “255 Bird Species” dataset from Kaggle. The results show that, although Focal Loss slightly decreased the accuracy of the majority species, it was able to increase the F1-score by 0.06 and improve the identification of the bottom two, five and ten (minority) species by 37.5%, 15.7% and 10.8%, respectively, as well as resulting in an improved overall accuracy of 2.96%.
Abstract: The success of education is dependent on evolution and adaptation, while the traditional system has worked before, one type of education evolved with the digital age is virtual education that has influenced efficiency in today’s learning environments. Virtual learning has indeed proved its efficiency to overcome the drawbacks of the physical environment such as time, facilities, location, etc., but despite what it had accomplished, the educational system over all is not adequate for being a productive system yet. Earning a degree is not anymore enough to obtain a career job; it is simply missing the skills and creativity. There are always two sides of a coin; a college degree or a specialized certificate, each has its own merits, but having both can put you on a successful IT career path. For many of job-seeking individuals across world to have a clear meaningful goal for work and education and positively contribute the community, a productive correlation and cooperation among employers, universities alongside with the individual technical skills is a must for generations to come. Fortunately, the proposed research “Entrepreneur Universal Education System” is an evolution to meet the needs of both employers and students, in addition to gaining vital and real-world experience in the chosen fields is easier than ever. The new vision is to empower the education to improve organizations’ needs which means improving the world as its primary goal, adopting universal skills of effective thinking, effective action, effective relationships, preparing the students through real-world accomplishment and encouraging them to better serve their organization and their communities faster and more efficiently.
Abstract: Many people know ‘Mathematics needs practice!’ statement or similar ones from their mathematics lessons. It seems important to practice when learning mathematics. At the same time, it also seems important to practice how to learn mathematics. This paper places neuroscientific-radiological findings on “practicing” while learning mathematics in a context of mathematics education. To accomplish this, we use a literature-based discussion of our case study on practice. We want to describe neuroscientific-radiological findings in the context of mathematics education and point out stimulating connections between both perspectives. From a connective perspective we expect incentives that lead discussions in future research in the field of mathematics education.
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.
Abstract: With the rapid development of deep learning, neural network and deep learning algorithms play a significant role in various practical applications. Due to the high accuracy and good performance, Convolutional Neural Networks (CNNs) especially have become a research hot spot in the past few years. However, the size of the networks becomes increasingly large scale due to the demands of the practical applications, which poses a significant challenge to construct a high-performance implementation of deep learning neural networks. Meanwhile, many of these application scenarios also have strict requirements on the performance and low-power consumption of hardware devices. Therefore, it is particularly critical to choose a moderate computing platform for hardware acceleration of CNNs. This article aimed to survey the recent advance in Field Programmable Gate Array (FPGA)-based acceleration of CNNs. Various designs and implementations of the accelerator based on FPGA under different devices and network models are overviewed, and the versions of Graphic Processing Units (GPUs), Application Specific Integrated Circuits (ASICs) and Digital Signal Processors (DSPs) are compared to present our own critical analysis and comments. Finally, we give a discussion on different perspectives of these acceleration and optimization methods on FPGA platforms to further explore the opportunities and challenges for future research. More helpfully, we give a prospect for future development of the FPGA-based accelerator.
Abstract: Interest in (STEM) Science Technology Engineering
Mathematics education especially Computer Science education has
seen a drastic increase across the country. This fuels effort towards
recruiting and admitting a diverse population of students. Thus the
changing conditions in terms of the student population, diversity
and the expected teaching and learning outcomes give the platform
for use of Innovative Teaching models and technologies. It is
necessary that these methods adapted should also concentrate on
raising quality of such innovations and have positive impact on
student learning. Light-Weight Team is an Active Learning Pedagogy,
which is considered to be low-stake activity and has very little or
no direct impact on student grades. Emotion plays a major role in
student’s motivation to learning. In this work we use the student
feedback data with emotion classification using surveys at a public
research institution in the United States. We use Actionable Pattern
Discovery method for this purpose. Actionable patterns are patterns
that provide suggestions in the form of rules to help the user achieve
better outcomes. The proposed method provides meaningful insight
in terms of changes that can be incorporated in the Light-Weight team
activities, resources utilized in the course. The results suggest how
to enhance student emotions to a more positive state, in particular
focuses on the emotions ‘Trust’ and ‘Joy’.
Abstract: In this paper, we proposed an AI Tutor using ontology and natural language process techniques to generate a computer science domain knowledge graph and answer users’ questions based on the knowledge graph. We define eight types of relation to extract relationships between entities according to the computer science domain text. The AI tutor is separated into two agents: learning agent and Question-Answer (QA) agent and developed on JADE (a multi-agent system) platform. The learning agent is responsible for reading text to extract information and generate a corresponding knowledge graph by defined patterns. The QA agent can understand the users’ questions and answer humans’ questions based on the knowledge graph generated by the learning agent.
Abstract: Nowadays, dialogue systems increasingly become the
way for humans to access many computer systems. So, humans
can interact with computers in natural language. A dialogue
system consists of three parts: understanding what humans say in
natural language, managing dialogue, and generating responses in
natural language. In this paper, we survey deep learning based
methods for dialogue management, response generation and dialogue
evaluation. Specifically, these methods are based on neural network,
long short-term memory network, deep reinforcement learning,
pre-training and generative adversarial network. We compare these
methods and point out the further research directions.
Abstract: Thanks to the development of online technology and social networks, people are able to communicate as well as learn. WhatsApp is a popular social network which is growingly gaining popularity. This app can be used for communication as well as education. It can be used for instructor-learner, learner-learner, and learner-content interactions; however, very little knowledge is available on these potentials of WhatsApp. The current study was undertaken to investigate university students’ perceptions of WhatsApp used as a tool for instructor-learner dialogue, learner-content dialogue, and learner-learner dialogue. The study adopted a survey approach and distributed the questionnaire developed by Google Forms to 54 (11 males and 43 females) university students. The obtained data were analyzed using SPSS version 20. The result of data analysis indicates that students have positive attitudes towards WhatsApp as a tool for Instructor-Learner Dialogue: it easy to reach the lecturer (4.07), the instructor gives me valuable feedback on my assignment (4.02), the instructor is supportive during course discussion and offers continuous support with the class (4.00). Learner-Content Dialogue: WhatsApp allows me to academically engage with lecturers anytime, anywhere (4.00), it helps to send graphics such as pictures or charts directly to the students (3.98), it also provides out of class, extra learning materials and homework (3.96), and Learner-Learner Dialogue: WhatsApp is a good tool for sharing knowledge with others (4.09), WhatsApp allows me to academically engage with peers anytime, anywhere (4.07), and we can interact with others through the use of group discussion (4.02). It was also found that there are significant positive correlations between students’ perceptions of Instructor-Learner Dialogue (ILD), Learner-Content Dialogue (LCD), Learner-Learner Dialogue (LLD) and WhatsApp Application in classroom. The findings of the study have implications for lectures, policy makers and curriculum developers.
Abstract: Over the past 20 years, internet has seen continual advancement and with the advent of online technology, various types of web-based games have been developed. Games are frequently being used among different age groups from baby boomers to generation Z. Games are not only used for entertainment but also utilized as a learning approach transmitting education to a level that is more interesting and effective for students. One of the popular web-based education games is Kahoot with growing popularity and usage, which is being used in different fields of studies. However, little knowledge is available on university students’ perception of Kahoot environment and application for learning subjects. Hence, the objective of the current study is to investigate students’ perceptions of Kahoot application and environment as a learning tool. The study employed a survey approach by distributing Google Forms –created questionnaire, with high level of reliability index, to 62 students (11 males and 51 females). The findings show that students have positive attitudes towards Kahoot application and its environment for learning. Regarding Kahoot application, it was indicated that activities created using Kahoot are more interesting for students, Kahoot is useful for collaborative learning, and Kahoot enhances interest in learning lesson. In terms of Kahoot environment, it was found that using this application through mobile is easy for students, its design is simple and useful, Kahoot-created activities can easily be shared, and the application can easily be used on any platform. The findings of the study have implications for instructors, policymakers and curriculum developers.