Search results for: computational machine learning

Authors: Samuel Mwangi, Josephine K. Mule

Abstract:

Access control as a security technique regulates who or what can access resources. It is a fundamental concept in security that minimizes risks to the institutions that use access control. Regulating access to institutions of higher learning is key to ensure only authorized personnel and students are allowed into the institutions. The use of biometrics has been criticized due to the setup and maintenance costs, hygiene concerns, and trepidations regarding data privacy, among other apprehensions. Facial recognition is arguably a fast and accurate way of validating identity in order to guard protected areas. It guarantees that only authorized individuals gain access to secure locations while requiring far less personal information whilst providing an additional layer of security beyond keys, fobs, or identity cards. This exploratory study sought to investigate the use of facial recognition in controlling access in institutions of higher learning in Kenya. The sample population was drawn from both private and public higher learning institutions. The data is based on responses from staff and students. Questionnaires were used for data collection and follow up interviews conducted to understand responses from the questionnaires. 80% of the sampled population indicated that there were many security breaches by unauthorized people, with some resulting in terror attacks. These security breaches were attributed to stolen identity cases, where staff or student identity cards were stolen and used by criminals to access the institutions. These unauthorized accesses have resulted in losses to the institutions, including reputational damages. The findings indicate that security breaches are a major problem in institutions of higher learning in Kenya. Consequently, access control would be beneficial if employed to curb security breaches. We suggest the use of facial recognition technology, given its uniqueness in identifying users and its non-repudiation capabilities.

Keywords: facial recognition, access control, technology, learning

Procedia PDF Downloads 112

Authors: Natalia Sáez, Dina Shulfman

Abstract:

There is an important research gap regarding accessible pedagogical techniques for teaching foreign languages to adults with visual impairments. English as a foreign language (EFL), in particular, is needed in many countries to expand occupational opportunities and improve living standards. Within EFL research, teaching and learning prepositions have only recently gained momentum, considering that they constitute one of the most difficult structures to learn in a foreign language and are fundamental for communicating about spatial relations in the world, both on the physical and imaginary levels. Learning to use prepositions would not only facilitate communication when referring to the surrounding tangible environment but also when conveying ideas about abstract topics (e.g., justice, love, society), for which students’ sociocultural knowledge about space could play an important role. By potentiating visually impaired students’ ability to construe mental spatial imagery, this study made efforts to explore pedagogical techniques that cater to their strengths, helping them create new worlds by welcoming and expanding their sociocultural funds of knowledge as they learn to use English prepositions. Fifteen visually impaired adults living in Chile participated in the study. Their first language was Spanish, and they were learning English at the intermediate level of proficiency in an EFL workshop at La Biblioteca Central para Ciegos (The Central Library for the Blind). Within this workshop, a series of activities and interviews were designed and implemented with the intention of uncovering students’ spatial funds of knowledge when learning literal/physical uses of three English prepositions, namely “in,” “at,” and “on”. The activities and interviews also explored whether students used their original spatial funds of knowledge when learning metaphorical uses of these prepositions and if their use of spatial imagery changed throughout the learning activities. Over the course of approximately half a year, it soon became clear that the students construed mental images of space when learning both literal/physical and metaphorical uses of these prepositions. This research could inform a new approach to inclusive language education using pedagogical methods that are relevant and accessible to students with visual impairments.

Keywords: EFL, funds of knowledge, prepositions, spatial cognition, visually impaired students

Procedia PDF Downloads 64

Authors: Luyao Zhang, Tianyu Wu, Jiayi Li, Carlos-Gustavo Salas-Flores, Saad Lahrichi

Abstract:

Recent advances in AI have made algorithmic trading a central role in finance. However, current research and applications are disconnected information islands. We propose a generally applicable pipeline for designing, programming, and evaluating algorithmic trading of stock and crypto tokens. Moreover, we provide comparative case studies for four conventional algorithms, including moving average crossover, volume-weighted average price, sentiment analysis, and statistical arbitrage. Our study offers a systematic way to program and compare different trading strategies. Moreover, we implement our algorithms by object-oriented programming in Python3, which serves as open-source software for future academic research and applications.

Keywords: algorithmic trading, AI for finance, fintech, machine learning, moving average crossover, volume weighted average price, sentiment analysis, statistical arbitrage, pair trading, object-oriented programming, python3

Procedia PDF Downloads 126

Authors: Bowei Yuan, Shi Li, Liuyang Song, Huaqing Wang, Lingli Cui

Abstract:

Convolutional neural networks (CNN) have received extensive attention in the field of fault diagnosis. Many fault diagnosis methods use CNN for fault type identification. However, when the amount of raw data collected by sensors is massive, the neural network needs to perform a time-consuming classification task. In this paper, a mechanical fault diagnosis method based on vibration signal down-sampling and the improved one-dimensional convolutional neural network is proposed. Through the robust principal component analysis, the low-rank feature matrix of a large amount of raw data can be separated, and then down-sampling is realized to reduce the subsequent calculation amount. In the improved one-dimensional CNN, a smaller convolution kernel is used to reduce the number of parameters and computational complexity, and regularization is introduced before the fully connected layer to prevent overfitting. In addition, the multi-connected layers can better generalize classification results without cumbersome parameter adjustments. The effectiveness of the method is verified by monitoring the signal of the centrifugal pump test bench, and the average test accuracy is above 98%. When compared with the traditional deep belief network (DBN) and support vector machine (SVM) methods, this method has better performance.

Keywords: fault diagnosis, vibration signal down-sampling, 1D-CNN

Procedia PDF Downloads 114

Authors: Oladapo Tolulope Ibitoye

Abstract:

Neural networks have become prominent and widely engaged in algorithmic-based machine learning networks. They are perfect in solving day-to-day issues to a certain extent. Neural networks are computing systems with several interconnected nodes. One of the numerous areas of application of neural networks is object detection. This is a prominent area due to the coronavirus disease pandemic and the post-pandemic phases. Wearing a face mask in public slows the spread of the virus, according to experts’ submission. This calls for the development of a reliable and effective model for detecting face masks on people's faces during compliance checks. The existing neural network models for facemask detection are characterized by their black-box nature and large dataset requirement. The highlighted challenges have compromised the performance of the existing models. The proposed model utilized Faster R-CNN Model on Inception V3 backbone to reduce system complexity and dataset requirement. The model was trained and validated with very few datasets and evaluation results shows an overall accuracy of 96% regardless of skin tone.

Keywords: convolutional neural network, face detection, face mask, masked faces

Procedia PDF Downloads 52

Authors: Mohammad Hadi Mahmoodi, Soroor Zekrati

Abstract:

The aim of this study was to investigate the relationship between hemispheric dominance and intonation learning of Iranian EFL students. In order to gain this goal, 52 female students from three levels of beginner, elementary and intermediate in Paradise Institute, and 18 male university students at Bu-Ali Sina University constituted the sample. In order to assist students learn the correct way of applying intonation to their everyday speech, the study proposed an interactive approach and provided students with visual aid through which they were able to see the intonation pattern on computer screen using 'Speech Analyzer' software. This software was also used to record subjects’ voice and compare them with the original intonation pattern. Edinburg Handedness Questionnaire (EHD), which ranges from –100 for strong left-handedness to +100 for strong right-handedness was used to indicate the hemispheric dominance of each student. The result of an independent sample t-test indicated that girls learned intonation pattern better than boys, and that right brained students significantly outperformed the left brained ones. Using one-way ANOVA, a significant difference between three proficiency levels was also found. The posthoc Scheffer test showed that the exact difference was between intermediate and elementary, and intermediate and beginner levels, but no significant difference was observed between elementary and beginner levels. The findings of the study might provide researchers with some helpful implications and useful directions for future investigation into the domain of the relationship between mind and second language learning.

Keywords: intonation, hemispheric dominance, visual aid, language learning, second language learning

Procedia PDF Downloads 503

Authors: Xiao Liulingzi

Abstract:

It is important for using multi-sensory teaching in music learning. This article aims to provide knowledge in multi-sensory learning and teaching music in primary school. For primary school students, in addition to the training of basic knowledge and skills of music, students' sense of participation and creativity in music class are the key requirements, especially the flexibility and dynamics in music class, so that students can integrate into music and feel the music. The article explains the multi-sensory sense in music learning, the differences between multi-sensory music teaching and traditional music teaching, and music multi-sensory teaching in primary schools in China.

Keywords: multi-sensory, teaching practice, primary music classroom, China

Procedia PDF Downloads 106

Authors: M. Michael Gromiha, A. Mary Thangakani, Sandeep Kumar, D. Velmurugan

Abstract:

The main cause of several neurodegenerative diseases such as Alzhemier, Parkinson, and spongiform encephalopathies is formation of amyloid fibrils and plaques in proteins. We have analyzed different sets of proteins and peptides to understand the influence of sequence-based features on protein aggregation process. The comparison of 373 pairs of homologous mesophilic and thermophilic proteins showed that aggregation-prone regions (APRs) are present in both. But, the thermophilic protein monomers show greater ability to ‘stow away’ the APRs in their hydrophobic cores and protect them from solvent exposure. The comparison of amyloid forming and amorphous b-aggregating hexapeptides suggested distinct preferences for specific residues at the six positions as well as all possible combinations of nine residue pairs. The compositions of residues at different positions and residue pairs have been converted into energy potentials and utilized for distinguishing between amyloid forming and amorphous b-aggregating peptides. Our method could correctly identify the amyloid forming peptides at an accuracy of 95-100% in different datasets of peptides.

Keywords: aggregation, amyloids, thermophilic proteins, amino acid residues, machine learning techniques

Procedia PDF Downloads 595

Authors: Jodie Lee, Lorena Chan, Esther Tong

Abstract:

Hong Kong students face a unique learning environment. Starting from the 2010/2011 school year, The Education Bureau (EDB) of the Government of the Hong Kong Special Administrative Region implemented the fine-tuned Medium of Instruction (MOI) arrangements for secondary schools. Since then, secondary schools in Hong Kong have been given the flexibility to decide the most appropriate MOI arrangements for their schools and under the new academic structure for senior secondary education, particularly on the compulsory part of the mathematics curriculum. In 2019, Hong Kong Diploma of Secondary Education Examination (HKDSE), over 40% of school day candidates attempted the Mathematics Compulsory Part examination in the Chinese version while the rest took the English version. Moreover, only 14.38% of candidates sat for one of the extended Mathematics modules. This results in a serious of intricate issues to students’ learning in post-secondary education programmes. It is worth to note that when students further pursue to an higher education in Hong Kong or even oversea, they may facing substantial difficulties in transiting learning from learning mathematics in their mother tongue in Chinese-medium instruction (CMI) secondary schools to an English-medium learning environment. Some students understood the mathematics concepts were found to fail to fulfill the course requirements at college or university due to their learning experience in secondary study at CMI. They are particularly weak in comprehending the mathematics questions when they are doing their assessment or attempting the test/examination. A government funded project was conducted with the aims of providing integrated learning context and language support to students with a lower level of numeracy and/or with CMI learning experience. By introducing this “integrated concept + language mapping approach”, students can cope with the learning challenges in the compulsory English-medium mathematics and statistics subjects in their tertiary education. Ultimately, in the hope that students can enhance their mathematical ability, analytical skills, and numerical sense for their lifelong learning. The “Concept + Language Mapping “(CLM) approach was adopted and tried out in the bridging courses for students with a lower level of numeracy and/or with CMI learning experiences. At the beginning of each class, a pre-test was conducted, and class time was then devoted to introducing the concepts by CLM approach. For each concept, the key thematic items and their different semantic relations are presented using graphics and animations via the CLM approach. At the end of each class, a post-test was conducted. Quantitative data analysis was performed to study the effect on students’ learning via the CLM approach. Stakeholders' feedbacks were collected to estimate the effectiveness of the CLM approach in facilitating both content and language learning. The results based on both students’ and lecturers’ feedback indicated positive outcomes on adopting the CLM approach to enhance the mathematical ability and analytical skills of CMI students.

Keywords: mathematics, Concept+Language Mapping, level of numeracy, medium of instruction

Procedia PDF Downloads 69

Authors: Esther Pearl Palmer

Abstract:

Driven by the increased pressure on Higher Education Institutions (HEIs) to produce work-ready graduates for the modern world of work, this study reflects on triad teaching and learning practices to increase student engagement and employability. In the South African higher education context, the employability of graduates is imperative in strengthening the country’s economy and in increasing competitiveness. Within this context, the field of Human Resource Management (HRM) calls for innovative methods and approaches to teaching and learning and assessing the skills and competencies of graduates to render them employable. Digital competency in Human Resource Information Systems (HRIS) is an important component and prerequisite for employment in HRM. The purpose of this research is to reflect on the subject HRIS developed by lecturers at the Central University of Technology, Free State (CUT), with the intention to actively engage students in real-world learning activities and increase their employability. The Enrichment Triad Model (ETM) was used as theoretical framework to develop the subject as it supports a triad teaching and learning approach to education. It is, furthermore, an inter-structured model that supports collaboration between industry, academics and students. The study follows a mixed-method approach to reflect on the learning experiences of the industry, academics and students in the subject field over the past three years. This paper is a work in progress and seeks to broaden the scope of extant studies about student engagement in work-related learning to increase employability. Based on the ETM as theoretical framework and pedagogical practice, this paper proposes that following a triad teaching and learning approach will increase work-related skills of students. Findings from the study show that students, academics and industry alike regard educational opportunities that incorporate active learning experiences with the world of work enhances student engagement in learning and renders them more employable.

Keywords: digital competence, enriched triad model, human resource information systems, student engagement, triad pedagogy.

Procedia PDF Downloads 78

Authors: Zoja Raud, Valery Vodovozov

Abstract:

The paper focuses on the distance laboratory organisation for training the electrical engineering staff and students in the fields of electrical drive and power electronics. To support online knowledge acquisition and professional enhancement, new challenges in remote education based on an active learning approach with self-assessment have been emerged by the authors. Following the literature review and explanation of the improved assessment methodology, the concept and technological basis of the labs arrangement are presented. To decrease the gap between the distance study of the up-to-date equipment and other educational activities in electrical engineering, the improvements in the following-up the learners’ progress and feedback composition are introduced. An authoring methodology that helps to personalise knowledge acquisition and enlarge Web-based possibilities is described. Educational management based on self-assessment is discussed.

Keywords: advanced training, active learning, distance learning, electrical engineering, remote laboratory, self-assessment

Procedia PDF Downloads 313

Authors: Felix Oromena Egara, Moeketsi Mosia

Abstract:

The study aimed to evaluate the impact of blended learning on mathematics retention among secondary school students. Conducted in the Isoko North Local Government Area of Delta State, Nigeria, the research involved 1,235 senior class one (SS 1) students. Employing a non-equivalent control group pre-test-post-test quasi-experimental design, a sample of 70 students was selected from two secondary schools with ICT facilities through purposive sampling. Random allocation of students into experimental and control groups was achieved through balloting within each selected school. The investigation included three assessment points: pre-Mathematics Achievement Test (MAT), post-MAT, and post-post-MAT (retention), administered systematically by the researchers. Data collection utilized the established MAT instrument, which demonstrated a high reliability score of 0.86. Statistical analysis was conducted using the Statistical Package for Social Sciences (SPSS) version 28, with mean and standard deviation addressing study questions and analysis of covariance scrutinizing hypotheses at a significance level of .05. Results revealed significantly greater improvements in mathematics retention scores among students exposed to blended learning compared to those instructed through conventional methods. Moreover, noticeable differences in mean retention scores were observed, with male students in the blended learning group exhibiting notably higher performance. Based on these findings, recommendations were made, advocating for mathematics educators to integrate blended learning, particularly in geometry teaching, to enhance students’ retention of mathematical concepts.

Keywords: blended learning, flipped classroom model, secondary school students, station rotation model

Procedia PDF Downloads 24

Authors: Rafael Dias Silva

Abstract:

The school is a social institution that should promote learning situations that remain throughout life. Based on this, the teaching activities promoted in museum spaces can represent an educational strategy that contributes to the learning process in a more meaningful way. This article systematizes a series of elements that guide the use of these spaces for the scientific literacy of deaf students and as experiences of this nature are favorable for the school development through the concept of the circularity. The methodology for the didactic use of these spaces of non-formal education is one of the reflections developed in this study and how such environments can contribute to the learning in the classroom. To develop in the student the idea of ​​association making him create connections with the curricular proposal and notice how the proposed activity is articulated. It is in our interest that the experience lived in the museum be shared collaborating for the construction of a scientific literacy and cultural identity through the research.

Keywords: accessibility in museums, Brazilian sign language, deaf students, teacher training

Procedia PDF Downloads 218

Authors: Marcela De Oliveira, Marina P. Da Silva, Fernando C. G. Da Rocha, Jorge M. Santos, Jaime S. Cardoso, Paulo N. Lisboa-Filho

Abstract:

Multiple Sclerosis (MS) is an immune-mediated disease of the central nervous system characterized by neurodegeneration, inflammation, demyelination, and axonal loss. Magnetic resonance imaging (MRI), due to the richness in the information details provided, is the gold standard exam for diagnosis and follow-up of neurodegenerative diseases, such as MS. Brain atrophy, the gradual loss of brain volume, is quite extensive in multiple sclerosis, nearly 0.5-1.35% per year, far off the limits of normal aging. Thus, the brain volume quantification becomes an essential task for future analysis of the occurrence atrophy. The analysis of MRI has become a tedious and complex task for clinicians, who have to manually extract important information. This manual analysis is prone to errors and is time consuming due to various intra- and inter-operator variability. Nowadays, computerized methods for MRI segmentation have been extensively used to assist doctors in quantitative analyzes for disease diagnosis and monitoring. Thus, the purpose of this work was to evaluate the brain volume in MRI of MS patients. We used MRI scans with 30 slices of the five patients diagnosed with multiple sclerosis according to the McDonald criteria. The computational methods for the analysis of images were carried out in two steps: segmentation of the brain and brain volume quantification. The first image processing step was to perform brain extraction by skull stripping from the original image. In the skull stripper for MRI images of the brain, the algorithm registers a grayscale atlas image to the grayscale patient image. The associated brain mask is propagated using the registration transformation. Then this mask is eroded and used for a refined brain extraction based on level-sets (edge of the brain-skull border with dedicated expansion, curvature, and advection terms). In the second step, the brain volume quantification was performed by counting the voxels belonging to the segmentation mask and converted in cc. We observed an average brain volume of 1469.5 cc. We concluded that the automatic method applied in this work can be used for the brain extraction process and brain volume quantification in MRI. The development and use of computer programs can contribute to assist health professionals in the diagnosis and monitoring of patients with neurodegenerative diseases. In future works, we expect to implement more automated methods for the assessment of cerebral atrophy and brain lesions quantification, including machine-learning approaches. Acknowledgements: This work was supported by a grant from Brazilian agency Fundação de Amparo à Pesquisa do Estado de São Paulo (number 2019/16362-5).

Keywords: brain volume, magnetic resonance imaging, multiple sclerosis, skull stripper

Procedia PDF Downloads 130

Authors: Ju May Wen, Chun Hung Lin, Eric Zhi Feng Liu

Abstract:

Flow theory implies that people are persuaded by happiness. By focusing on an activity, people turn a blind eye to external factors. This study explores the influence of educational board games and fundamental Chinese language teaching on students’ learning motivation and flow experience. Fifty-three students studying Chinese language fundamental courses were used in the study. These students were divided into three groups: (1) flash card teaching group; (2) educational original board game teaching group; and (3) educational Chinese board game teaching group. Chinese language teaching was integrated with the educational board game titled ‘Transportation GO.’ The students were observed playing this game as the teacher collected quantitative and qualitative data. Quantitative data was collected from the learning motivation scale and flow experience scale. Qualitative data was collected through observing, recording, and visiting. The first result found that the three groups integrated with Chinese language teaching could maintain students’ high learning motivation and high flow experience. Second, there was no significant difference between the flow experience of the flash card group and the educational original board game group. Third, there was a significant difference in the flow experience and learning motivation of the educational Chinese board game group vs. the other groups. This study suggests that the experimental model can be applied to advanced Chinese language teaching. Apart from oral and literacy skills, the study of educational board games integrated with Chinese language teaching to enforce student writing skills will be continued.

Keywords: Chinese language instruction, educational board game, learning motivation, flow experience

Procedia PDF Downloads 165

Authors: Indri Mahadiraka Rumamby, R. R. Dwinanti Rika Marthanty, Jessica Sjah

Abstract:

Smoothed particle hydrodynamics (SPH) was originally created to simulate nonaxisymmetric phenomena in astrophysics. However, this method still has several shortcomings, namely the high computational cost required to model values with high resolution and problems with boundary conditions. The difficulty of modeling boundary conditions occurs because the SPH method is influenced by particle deficiency due to the integral of the kernel function being truncated by boundary conditions. This research aims to answer if SPH modeling with a focus on boundary layer interactions and continuous flow can produce quantifiably accurate values with low computational cost. This research will combine algorithms and coding in the main program of meandering river, continuous flow algorithm, and solid-fluid algorithm with the aim of obtaining quantitatively accurate results on solid-fluid interactions with the continuous flow on a meandering channel using the SPH method. This study uses the Fortran programming language for modeling the SPH (Smoothed Particle Hydrodynamics) numerical method; the model is conducted in the form of a U-shaped meandering open channel in 3D, where the channel walls are soil particles and uses a continuous flow with a limited number of particles.

Keywords: smoothed particle hydrodynamics, computational fluid dynamics, numerical simulation, fluid mechanics

Procedia PDF Downloads 110

Authors: Undiyaundeye Florence Atube, Ugar Innocent A.

Abstract:

Young children are active learners who use all their senses to build concepts and ideas from their experiences. The process of learning, the content and the outcomes, is vital for young children. They need time to explore whether they are satisfied with what is learnt. Of all levels of education, early childhood education is considered to be most critical for the social, emotional, cognitive and physical development. For this reason, the teachers for early years need to play a significant role in the teaching and learning process through the provision of a friendly environment in the school. A case study approach was used in this study. The information was gathered through various methods like class observation, field notes, documents analysis, group processes, and semi structured interviews. The group processes participants and interviewees were taken from some stakeholders such as parents, students, teachers, and head teachers from public schools, to have a broad and comprehensive analysis, informal interaction with different stakeholders and self-reflection was used to clarify aspects of varying issues and findings. The teachers’ roles in developing a child friendly environment in personal capacity to learning were found to improve a pupils learning ability. Prior to early child development education, learning experiences and pedagogical content knowledge played a vital role in engaging teachers in developing their thinking and teaching practice. Children can be helped to develop independent self-control and self-reliance with careful planning and development of the child’s experience with sensitive and appropriate interaction by the educator to propel eagerness to learn through the provision of a friendly environment.

Keywords: child friendly environment, early childhood, education and development, teaching, learning and the curriculum

Procedia PDF Downloads 358

Authors: Nir Nissim, Ran Yahalom, Tomer Lancewiki, Yuval Elovici, Boaz Lerner

Abstract:

Background: Attackers increasingly take advantage of innocent users who tend to use USB devices casually, assuming these devices benign when in fact they may carry an embedded malicious behavior or hidden malware. USB devices have many properties and capabilities that have become the subject of malicious operations. Many of the recent attacks targeting individuals, and especially organizations, utilize popular and widely used USB devices, such as mice, keyboards, flash drives, printers, and smartphones. However, current detection tools, techniques, and solutions generally fail to detect both the known and unknown attacks launched via USB devices. Significance: We propose USBWARE, a project that focuses on the vulnerabilities of USB devices and centers on the development of a comprehensive detection framework that relies upon a crucial attack repository. USBWARE will allow researchers and companies to better understand the vulnerabilities and attacks associated with USB devices as well as providing a comprehensive platform for developing detection solutions. Methodology: The framework of USBWARE is aimed at accurate detection of both known and unknown USB-based attacks by a process that efficiently enhances the framework's detection capabilities over time. The framework will integrate two main security approaches in order to enhance the detection of USB-based attacks associated with a variety of USB devices. The first approach is aimed at the detection of known attacks and their variants, whereas the second approach focuses on the detection of unknown attacks. USBWARE will consist of six independent but complimentary detection modules, each detecting attacks based on a different approach or discipline. These modules include novel ideas and algorithms inspired from or already developed within our team's domains of expertise, including cyber security, electrical and signal processing, machine learning, and computational biology. The establishment and maintenance of the USBWARE’s dynamic and up-to-date attack repository will strengthen the capabilities of the USBWARE detection framework. The attack repository’s infrastructure will enable researchers to record, document, create, and simulate existing and new USB-based attacks. This data will be used to maintain the detection framework’s updatability by incorporating knowledge regarding new attacks. Based on our experience in the cyber security domain, we aim to design the USBWARE framework so that it will have several characteristics that are crucial for this type of cyber-security detection solution. Specifically, the USBWARE framework should be: Novel, Multidisciplinary, Trusted, Lightweight, Extendable, Modular and Updatable and Adaptable. Major Findings: Based on our initial survey, we have already found more than 23 types of USB-based attacks, divided into six major categories. Our preliminary evaluation and proof of concepts showed that our detection modules can be used for efficient detection of several basic known USB attacks. Further research, development, and enhancements are required so that USBWARE will be capable to cover all of the major known USB attacks and to detect unknown attacks. Conclusion: USBWARE is a crucial detection framework that must be further enhanced and developed.

Keywords: USB, device, cyber security, attack, detection

Procedia PDF Downloads 378

Authors: Amira Potter

Abstract:

Since three years, ESPRIT has adopted project-based learning across its curricula. The philosophy behind this reform is to prepare its future engineers to become more operational once they integrate the workplace. It allows them to learn all the required skills expected from them by their future employers. This learner-centered method helps the students take responsibility for their own learning, solve real-world problems and carry out muli-faceted projects. Therefore, the teacher who used to be considered as the detainer of the knowledge has become more of a facilitator and a coach, encouraging their students’ learning process. This innovative way to English teaching has enabled the students to learn the English language differently. The target language is learnt cooperatively through group work, presentations, debating and many other communicative activities. The speaking skill in English language remains by far the most challenging skill for Tunisian students with an educational background based on Arabic as a first language and French as a second language. The student’s initial resistance to speak English in front of their classmates and the way they end up performing their work, shows the real progress they managed to achieve through PBL approach. The article will focus on the positive impact PBL has had on oral fluency among Esprit engineering students and how it has been achieved. It will also describe how speaking skill is taught and assessed at ESPRIT.

Keywords: cooperative, engineer, innovative, project-based learning

Procedia PDF Downloads 308

Authors: Guantao Bai

Abstract:

Public space is an indispensable and important component of the urban built environment. How to more accurately evaluate the usage characteristics of public space can help improve its spatial quality. Compared to traditional survey methods, computer vision technology based on deep learning has advantages such as dynamic observation and low cost. This study takes the public space of Shaping Park as an example and, based on deep learning computer vision technology, processes and analyzes the image data of the public space to obtain the spatial usage characteristics and spatiotemporal characteristics of the public space. Research has found that the spontaneous activity time in public spaces is relatively random with a relatively short average activity time, while social activities have a relatively stable activity time with a longer average activity time. Computer vision technology based on deep learning can effectively describe the spatial usage characteristics of the research area, making up for the shortcomings of traditional research methods and providing relevant support for creating a good public space.

Keywords: computer vision, deep learning, public spaces, using features

Procedia PDF Downloads 53

Authors: Maulik Parmar, Sumeet Sandhu

Abstract:

The online fashion industry experiences high product return rates. Many returns are because of size/fit mismatches -the size scale on labels can vary across brands, the size parameters may not capture all fit measurements, or the product may have manufacturing defects. Warehouse quality check of garment sizes can be semi-automated to improve speed and accuracy. This paper presents an approach for automatically measuring garment sizes from a single image of the garment -using Deep Learning to learn garment keypoints. The paper focuses on the waist size measurement of jeans and can be easily extended to other garment types and measurements. Experimental results show that this approach can greatly improve the speed and accuracy of today’s manual measurement process.

Keywords: convolutional neural networks, deep learning, distortion, garment measurements, image warping, keypoints

Procedia PDF Downloads 280

Authors: Recep Karadag

Abstract:

Natural dyeing had started since pre-historical times for dyeing of textile materials. The natural dyeing had continued to beginning of 20th century. At the end of 19th century some synthetic dyes were synthesized. Although development of dyeing technologies and methods, natural dyeing was not developed in recent years. Despite rapid advances of synthetic dyestuff industries, natural dye processes have not developed. Therefore natural dyeing was not competed against synthetic dyes. At the same time, it was very difficult that large quantities of coloured textile was dyed with natural dyes And it was very difficult to get reproducible results in the natural dyeing using classical and traditional processes. However, natural dyeing has used slightly in the textile handicraft up to now. It is very important view that re-using of natural dyes to create awareness in textiles in recent years. Natural dyes have got many awareness and sustainability properties. Natural dyes are more eco-friendly than synthetic dyes. A lot of natural dyes have got antioxidant, antibacterial, antimicrobial, antifungal and anti –UV properties. It had been known that were obtained limited numbers colours with natural dyes in the past. On the contrary, colour scale is too wide with natural dyes. Except fluorescent colours, numerous colours can be obtained with natural dyes. Fastnesses of dyed textiles with natural dyes are good that there are light, washing, rubbing, etc. The fastness values can be improved depend on dyeing processes. Thanks to these properties mass production can be made with natural dyes in textiles. Therefore fabric dyeing machine was designed. This machine is too suitable for natural dyeing and mass production. Also any dyeing machine can be modified for natural dyeing. Although dye extraction and dyeing are made separately in the traditional natural dyeing processes and these procedures are become by designed this machine. Firstly, colouring compounds are extracted from natural dye resources, then dyeing is made with extracted colouring compounds. The colouring compounds are moderately dissolved in water. Less water is used in the extraction of colouring compounds from dye resources and dyeing with this new technique on the contrary much quantity water needs to use for dissolve of the colouring compounds in the traditional dyeing. This dyeing technique is very useful method for mass productions with natural dyes in traditional natural dyeing that use less energy, less dye materials, less water, etc. than traditional natural dyeing techniques. In this work, cotton, silk, linen and wool fabrics were dyed with some natural dye plants by the technique. According to the analysis very good results were obtained by this new technique. These results are shown sustainability and awareness of natural dyes for textiles.

Keywords: antibacterial, antimicrobial, natural dyes, sustainability

Procedia PDF Downloads 503

Authors: Martin Dupuy, Solange Grunenwald, Pierre-Louis Colombo, Laurence Mahieu, Pomone Richard, Philippe Bartoli

Abstract:

Endonasal endoscopic trans-sphenoidal surgery for pituitary tumours has become a mainstay of treatment over the last two decades. Although it is generally accepted that there is no significant difference between endoscopic versus microscopic approach for surgical outcomes (endocrine and ophthalmologic status), nasal morbidity seems to the benefit of endoscopic procedures. Minimally invasive endoscopic surgery needs an operative learning curve to achieve surgeon’s efficiency. This learning curve is now well known for surgical outcomes and complications rate, however, few data are available for nasal morbidity. The aim of our series is to document operative experience and nasal quality of life after (NQOL) endoscopic trans-sphenoidal surgery. The prospective pituitary surgical cohort consisted of 525 consecutives patients referred to our Skull Base Diseases Department. Endoscopic procedures were performed by a single neurosurgeon using an uninostril approach. NQOL was evaluated using the Sino-Nasal Test (SNOT-22), the Anterior Base Nasal Inventory (ASBNI) and the Skull Base Inventory Score (SBIS). Data were collected before surgery during hospital stay and 3 months after the surgery. The seventy first patients were compared to the latest 70 patients. There was no significant difference between comparison score before versus after surgery for SNOT-22, ASBNI and SBIS during the single surgeon’s learning curve. Our series demonstrates that in our institution there is no statistically significant learning curve for NQOL after uninostril endoscopic pituitary surgery. A careful progression through sinonasal structures with very limited mucosal incision is associated with minimal morbidity and preserves nasal function. Conservative and minimal invasive approach could be achieved early during learning curve.

Keywords: pituitary surgery, quality of life, minimal invasive surgery, learning curve, pituitary tumours, skull base surgery, endoscopic surgery

Procedia PDF Downloads 106

Authors: Yishu Gong, Liangliang Yang, Jianyu Zhang, Zhengyu Chen, Sihong He, Xusheng Zhang, Wei Zhang

Abstract:

Alzheimer’s disease (AD) is a progressive neurodegenerative disorder that affects millions of people worldwide and is characterized by cognitive decline and behavioral changes. People living with Alzheimer’s disease often find it hard to complete routine tasks. However, there are limited objective assessments that aim to quantify the difficulty of certain tasks for AD patients compared to non-AD people. In this study, we propose to use speech emotion recognition (SER), especially the frustration level, as a potential biomarker for quantifying the difficulty patients experience when describing a picture. We build an SER model using data from the IEMOCAP dataset and apply the model to the DementiaBank data to detect the AD/non-AD group difference and perform longitudinal analysis to track the AD disease progression. Our results show that the frustration level detected from the SER model can possibly be used as a cost-effective tool for objective tracking of AD progression in addition to the Mini-Mental State Examination (MMSE) score.

Keywords: Alzheimer’s disease, speech emotion recognition, longitudinal biomarker, machine learning

Procedia PDF Downloads 95

Authors: H. M. Anitha, Anusha N. Rao

Abstract:

The current developments in technology and ideas have given entirely new dimensions to the field of research and education. New delivery methods are proposed which is an added feature to the engineering education. Particularly, more importance is given to new teaching practices such as Information and Communication Technologies (ICT). It is vital to adopt the new ICT methods which lead to the emergence of novel structure and mode of education. The flipped classroom, think pair share and peer instruction are the latest pedagogical methods which give students to learn the course. This involves students to watch video lectures outside the classroom and solve the problems at home. Students are engaged in group discussions in the classroom. These are the active learning methods wherein the students are involved diversely to learn the course. This paper gives a comprehensive study of past and present research which is going on with flipped classroom, thinks pair share activity and peer instruction.

Keywords: flipped classroom, think pair share, peer instruction, active learning

Procedia PDF Downloads 369

Authors: Kumar Vikas

Abstract:

Education is to be anticipated for Human resource development and then national development. However, in most of the developing countries, due to the inadequacy of resources it is almost unattainable to educate all of their citizens through on-campus teaching. Huge amount of money is necessary to establish the infrastructure for on-campus teaching which is out of the reach of the developing countries. In these circumstances, to educate their huge inhabitants the developing countries are to depend on open learning and distance education system. However, a question still stands: can the educators dissimulate knowledge to the learners smoothly through this new system of education? Some recent research shows that the graduates of the open and distance learning institutions in the developing countries are treated as second-grade graduates. This paper aims to identify the challenges or barriers in the development of distance and Open learning system in India and suggest possible alternatives may be followed to overcome the barriers.

Keywords: barriers, distance education, developing countries, motivation, alternative solutions

Procedia PDF Downloads 231

Authors: Thomas Monahan, Nicolas Gorius, Thanh Nguyen

Abstract:

Exoplanet atmospheric parameters retrieval is a complex, computationally intensive, inverse modeling problem in which an exoplanet’s atmospheric composition is extracted from an observed spectrum. Traditional Bayesian sampling methods require extensive time and computation, involving algorithms that compare large numbers of known atmospheric models to the input spectral data. Runtimes are directly proportional to the number of parameters under consideration. These increased power and runtime requirements are difficult to accommodate in space missions where model size, speed, and power consumption are of particular importance. The use of traditional Bayesian sampling methods, therefore, compromise model complexity or sampling accuracy. The Atmospheric Retrievals conditional Generative Adversarial Network (ARcGAN) is a deep convolutional generative adversarial network that improves on the previous model’s speed and accuracy. We demonstrate the efficacy of artificial intelligence to quickly and reliably predict atmospheric parameters and present it as a viable alternative to slow and computationally heavy Bayesian methods. In addition to its broad applicability across instruments and planetary types, ARcGAN has been designed to function on low power application-specific integrated circuits. The application of edge computing to atmospheric retrievals allows for real or near-real-time quantification of atmospheric constituents at the instrument level. Additionally, edge computing provides both high-performance and power-efficient computing for AI applications, both of which are critical for space missions. With the edge computing chip implementation, ArcGAN serves as a strong basis for the development of a similar machine-learning algorithm to reduce the downlinked data volume from the Compact Ultraviolet to Visible Imaging Spectrometer (CUVIS) onboard the DAVINCI mission to Venus.

Keywords: deep learning, generative adversarial network, edge computing, atmospheric parameters retrieval

Procedia PDF Downloads 155

Authors: Dongping Fang, Lian Duan, Xiaojing Yuan, Mike Xu, Allyn Klunder, Kevin Tan, Suiting Cao, Yeqing Ji

Abstract:

Accurate prediction of a medical condition with straight clinical evidence is a long-sought topic in the medical management and health insurance field. Although great progress has been made with machine learning algorithms, the medical community is still, to a certain degree, suspicious about the model's accuracy and interpretability. This paper presents an innovative hierarchical attention deep learning model to achieve good prediction and clear interpretability that can be easily understood by medical professionals. This deep learning model uses a hierarchical attention structure that matches naturally with the medical history data structure and reflects the member’s encounter (date of service) sequence. The model attention structure consists of 3 levels: (1) attention on the medical code types (diagnosis codes, procedure codes, lab test results, and prescription drugs), (2) attention on the sequential medical encounters within a type, (3) attention on the medical codes within an encounter and type. This model is applied to predict the occurrence of stage 3 chronic kidney disease (CKD3), using three years’ medical history of Medicare Advantage (MA) members from a top health insurance company. The model takes members’ medical events, both claims and electronic medical record (EMR) data, as input, makes a prediction of CKD3 and calculates the contribution from individual events to the predicted outcome. The model outcome can be easily explained with the clinical evidence identified by the model algorithm. Here are examples: Member A had 36 medical encounters in the past three years: multiple office visits, lab tests and medications. The model predicts member A has a high risk of CKD3 with the following well-contributed clinical events - multiple high ‘Creatinine in Serum or Plasma’ tests and multiple low kidneys functioning ‘Glomerular filtration rate’ tests. Among the abnormal lab tests, more recent results contributed more to the prediction. The model also indicates regular office visits, no abnormal findings of medical examinations, and taking proper medications decreased the CKD3 risk. Member B had 104 medical encounters in the past 3 years and was predicted to have a low risk of CKD3, because the model didn’t identify diagnoses, procedures, or medications related to kidney disease, and many lab test results, including ‘Glomerular filtration rate’ were within the normal range. The model accurately predicts members A and B and provides interpretable clinical evidence that is validated by clinicians. Without extra effort, the interpretation is generated directly from the model and presented together with the occurrence date. Our model uses the medical data in its most raw format without any further data aggregation, transformation, or mapping. This greatly simplifies the data preparation process, mitigates the chance for error and eliminates post-modeling work needed for traditional model explanation. To our knowledge, this is the first paper on an interpretable deep-learning model using a 3-level attention structure, sourcing both EMR and claim data, including all 4 types of medical data, on the entire Medicare population of a big insurance company, and more importantly, directly generating model interpretation to support user decision. In the future, we plan to enrich the model input by adding patients’ demographics and information from free-texted physician notes.

Keywords: deep learning, interpretability, attention, big data, medical conditions

Procedia PDF Downloads 82

Authors: Sandra Thompson, Paul Dervan

Abstract:

Ireland’s first Technological University (TU Dublin) was established on 1st January 2019, and its creation is an exciting new milestone in Irish Higher Education. TU Dublin is now Ireland’s biggest University supporting 29,000 students across three campuses with 3,500 staff. The University aspires to create work-ready graduates who are socially responsible, open-minded global thinkers who are ambitious to change the world for the better. As graduates, they will be enterprising and daring in all their endeavors, ready to play their part in transforming the future. Feedback from Irish employers and students coupled with evidence from other authoritative sources such as the World Economic Forum points to a need for greater focus on the development of students’ employability skills as they prepare for today’s work environment. Moreover, with an increased focus on Universal Design for Learning (UDL) and inclusiveness, there is recognition that students are more than a numeric grade value. Robust grading systems have been developed to track a student’s performance around discipline knowledge but there is little or no global consensus on a definition of transversal skills nor on a unified framework to assess transversal skills. Education and industry sectors are often assessing one or two skills, and some are developing their own frameworks to capture the learner’s achievement in this area. Technological University Dublin (TU Dublin) have discovered and implemented a framework to allow students to develop, assess and record their transversal skills using transformative learning theory. The model implemented is an adaptation of Student Transformative Learning Record - STLR which originated in the University of Central Oklahoma (UCO). The purpose of this paper therefore, is to examine the views of students, staff and employers in the context of deploying a Transformative Learning model within the University to assess transversal skills. It will examine the initial impact the transformative learning model is having socially, personally and on the University as an organization. Crucially also, to identify lessons learned from the deployment in order to assist other Universities and Higher Education Institutes who may be considering a focused adoption of Transformative Learning to meet the challenge of preparing students for today’s work environment.

Keywords: assessing transversal skills, higher education, transformative learning, students

Procedia PDF Downloads 116

Authors: Elias Nemer, Greg Vines

Abstract:

Time-frequency transformation and spectral representations of audio signals are commonly used in various machine learning applications. Training networks on frequency features such as the Mel-Spectrogram or Cochleogram have been proven more effective and convenient than training on-time samples. In practical realizations, these features are created on a different processor and/or pre-computed and stored on disk, requiring additional efforts and making it difficult to experiment with different features. In this paper, we provide a PyTorch framework for creating various spectral features as well as time-frequency transformation and time-domain filter-banks using the built-in trainable conv1d() layer. This allows computing these features on the fly as part of a larger network and enabling easier experimentation with various combinations and parameters. Our work extends the work in the literature developed for that end: First, by adding more of these features and also by allowing the possibility of either starting from initialized kernels or training them from random values. The code is written as a template of classes and scripts that users may integrate into their own PyTorch classes or simply use as is and add more layers for various applications.

Keywords: neural networks Mel-Spectrogram, chromagram, cochleogram, discrete Fourrier transform, PyTorch conv1d()

Procedia PDF Downloads 215