Search results for: online teaching and learning

Authors: B. Likar, K. Širok

Abstract:

The paper presents a new method for efficient innovation process management. Even though the innovation management methods, tools and knowledge are well established and documented in literature, most of the companies still do not manage it efficiently. Especially in SMEs the front end of innovation - problem identification, idea creation and selection - is often not optimally performed. Our eMIPS methodology represents a sort of "umbrella methodology"- a well-defined set of procedures, which can be dynamically adapted to the concrete case in a company. In daily practice, various methods (e.g. for problem identification and idea creation) can be applied, depending on the company's needs. It is based on the proactive involvement of the company's employees supported by the appropriate methodology and external experts. The presented phases are performed via a mixture of face-to-face activities (workshops) and online (eLearning) activities taking place in eLearning Moodle environment and using other e-communication channels. One part of the outcomes is an identified set of opportunities and concrete solutions ready for implementation. The other also very important result is connected to innovation competences for the participating employees related with concrete tools and methods for idea management. In addition, the employees get a strong experience for dynamic, efficient and solution oriented managing of the invention process. The eMIPS also represents a way of establishing or improving the innovation culture in the organization. The first results in a pilot company showed excellent results regarding the motivation of participants and also as to the results achieved.

Keywords: creativity, distance learning, front end, innovation, problem

Procedia PDF Downloads 325

Authors: Elham Azimzadeh, Hamidollah Hassanlouei, Hadi Nobari, Georgian Badicu, Jorge Pérez-Gómez, Luca Paolo Ardigò

Abstract:

Children with cerebral palsy (CP) have weak physical abilities and their limitations may have an effect on performing everyday motor activities. One of the most important and common debilitating factors in CP is the malfunction in the upper extremities to perform motor skills and there is strong evidence that task-specific training may lead to improve general upper limb function among this population. However, augmented feedback enhances the acquisition and learning of a motor task. Practice conditions may alter the difficulty, e.g., the reduced frequency of PG could be more challenging for this population to learn a motor task. So, the purpose of this study was to investigate the effect of physical guidance (PG) on learning a tracking task in children with cerebral palsy (CP). Twenty-five independently ambulant children with spastic hemiplegic CP aged 7-15 years were assigned randomly to five groups. After the pre-test, experimental groups participated in an intervention for eight sessions, 12 trials during each session. The 0% PG group received no PG; the 25% PG group received PG for three trials; the 50% PG group received PG for six trials; the 75% PG group received PG for nine trials; and the 100% PG group, received PG for all 12 trials. PG consisted of placing the experimenter's hand around the children's hand, guiding them to stay on track and complete the task. Learning was inferred by acquisition and delayed retention tests. The tests involved two blocks of 12 trials of the tracking task without any PG being performed by all participants. They were asked to make the movement as accurate as possible (i.e., fewer errors) and the number of total touches (errors) in 24 trials was calculated as the scores of the tests. The results showed that the higher frequency of PG led to more accurate performance during the practice phase. However, the group that received 75% PG had significantly better performance compared to the other groups in the retention phase. It is concluded that the optimal frequency of PG played a critical role in learning a tracking task in children with CP and likely this population may benefit from an optimal level of PG to get the appropriate amount of information confirming the challenge point framework (CPF), which state that too much or too little information will retard learning a motor skill. Therefore, an optimum level of PG may help these children to identify appropriate patterns of motor skill using extrinsic information they receive through PG and improve learning by activating the intrinsic feedback mechanisms.

Keywords: cerebral palsy, challenge point framework, motor learning, physical guidance, tracking task

Procedia PDF Downloads 66

Authors: Muhammad Ali

Abstract:

Cyber-attacks and anomaly detection on the Internet of Things (IoT) infrastructure is emerging concern in the domain of data-driven intrusion. Rapidly increasing IoT risk is now making headlines around the world. denial of service, malicious control, data type probing, malicious operation, DDos, scan, spying, and wrong setup are attacks and anomalies that can affect an IoT system failure. Everyone talks about cyber security, connectivity, smart devices, and real-time data extraction. IoT devices expose a wide variety of new cyber security attack vectors in network traffic. For further than IoT development, and mainly for smart and IoT applications, there is a necessity for intelligent processing and analysis of data. So, our approach is too secure. We train several machine learning models that have been compared to accurately predicting attacks and anomalies on IoT systems, considering IoT applications, with ANOVA-based feature selection with fewer prediction models to evaluate network traffic to help prevent IoT devices. The machine learning (ML) algorithms that have been used here are KNN, SVM, NB, D.T., and R.F., with the most satisfactory test accuracy with fast detection. The evaluation of ML metrics includes precision, recall, F1 score, FPR, NPV, G.M., MCC, and AUC & ROC. The Random Forest algorithm achieved the best results with less prediction time, with an accuracy of 99.98%.

Keywords: machine learning, analysis of variance, Internet of Thing, network security, intrusion detection

Procedia PDF Downloads 115

Authors: Xabier Olaz Moratinos

Abstract:

Drone navigation is critical, particularly during the initial phases, such as the initial ascension, where pilots may fail due to strong external interferences that could potentially lead to a crash. In this ongoing work, a drone has been successfully trained to perform an ascent of up to 6 meters at speeds with external disturbances pushing it up to 24 mph, with the DQN algorithm managing external forces affecting the system. It has been demonstrated that the system can control its height, position, and stability in all three axes (roll, pitch, and yaw) throughout the process. The learning process is carried out in the Gazebo simulator, which emulates interferences, while ROS is used to communicate with the agent.

Keywords: machine learning, DQN, Gazebo, navigation

Procedia PDF Downloads 71

Authors: Xiuying Wang, Changliang Li, Bo Xu

Abstract:

A fixed-length feature vector is required for many machine learning algorithms in NLP field. Word embeddings have been very successful at learning lexical information. However, they cannot capture the compositional meaning of sentences, which prevents them from a deeper understanding of language. In this paper, we introduce a novel hierarchical tree long short-term memory (HTLSTM) model that learns vector representations for sentences of arbitrary syntactic type and length. We propose to split one sentence into three hierarchies: short phrase, long phrase and full sentence level. The HTLSTM model gives our algorithm the potential to fully consider the hierarchical information and long-term dependencies of language. We design the experiments on both English and Chinese corpus to evaluate our model on sentiment analysis task. And the results show that our model outperforms several existing state of the art approaches significantly.

Keywords: deep learning, hierarchical tree long short-term memory, sentence representation, sentiment analysis

Procedia PDF Downloads 347

Authors: Malavika Sundararajan

Abstract:

This study introduces the use of mindfulness techniques in the classroom to make individuals aware of how the creative thinking process works, resulting in more constructive learning and application. Case observation method was utilized within a classroom setting in a graduate class in the Business School. It entailed, briefing the student participants about the use of a template called the dots and depths map, and having them complete it for themselves, compare it to their team members and reflect on the outputs. Finally, they were debriefed about the use of the template and its value to their learning and creative application process. The major finding is the increase in awareness levels of the participants following the use of the template, leading to a subsequent pursuit of diverse knowledge and acquisition of relevant information and not jumping to solutions directly, which increased their overall creative outputs for the given assignment. The significant value of this study is that it can be applied to any classroom on any subject as a powerful mindfulness tool which increases creative problem solving through constructive knowledge building.

Keywords: connecting dots, mindful awareness, constructive knowledge building, learning creatively

Procedia PDF Downloads 142

Authors: Panagiota A. Kotsoni, George S. Ypsilandis

Abstract:

Learning an L2 is a demanding process for all students and in particular for those with learning disabilities (LD) who demonstrate an inability to catch up with their classmates’ progress in a given period of time. This area of study, i.e. examining children with learning disabilities in L2 has not (yet) attracted the growing interest that is registered in L1 and thus remains comparatively neglected. It is this scientific field that this study wishes to contribute to. The longitudinal purpose of this study is to locate effective Supportive Feedback Strategies (SFS) and add to the quality of learning in second language vocabulary in both typically developing (TD) and LD children. Specifically, this study aims at investigating and comparing the performance of TD with LD children on two different types of SFSs related to vocabulary short and long-term retention. In this study two different SFSs have been examined to a total of ten (10) unknown vocabulary items. Both strategies provided morphosyntactic clarifications upon new contextualized vocabulary items. The traditional SFS (direct) provided the information only in one hypertext page with a selection on the relevant item. The experimental SFS (engaging) provided the exact same split information in three successive hypertext pages in the form of a hybrid dialogue asking from the subjects to move on to the next page by selecting the relevant link. It was hypothesized that this way the subjects would engage in their own learning process by actively asking for more information which would further lead to their better retention. The participants were fifty-two (52) foreign language learners (33 TD and 19 LD) aged from 9 to 12, attending an English language school at the level of A1 (CEFR). The design of the study followed a typical pre-post-post test procedure after an hour and after a week. The results indicated statistically significant group differences with TD children performing significantly better than the LD group in both short and long-term memory measurements and in both SFSs. As regards the effectiveness of one SFS over another the initial hypothesis was not supported by the evidence as the traditional SFS was more effective compared to the experimental one in both TD and LD children. This difference proved to be statistically significant only in the long-term memory measurement and only in the TD group. It may be concluded that the human brain seems to adapt to different SFS although it shows a small preference when information is provided in a direct manner.

Keywords: learning disabilities, memory, second/foreign language acquisition, supportive feedback

Procedia PDF Downloads 279

Authors: Misrak Assefa

Abstract:

The Amharic language is the second most widely spoken Semitic language in the world. There are several new overloaded on the web. Searching some useful documents from the web on a specific topic, which is written in the Amharic language, is a challenging task. Hence, document categorization is required for managing and filtering important information. In the classification of Amharic text news, there is still a gap in the domain of information that needs to be launch. This study attempts to design an automatic Amharic news classification using a supervised learning mechanism on four un-touch classes. To achieve this research, 4,182 news articles were used. Naive Bayes (NB) and Decision tree (j48) algorithms were used to classify the given Amharic dataset. In this paper, k-fold cross-validation is used to estimate the accuracy of the classifier. As a result, it shows those algorithms can be applicable in Amharic news categorization. The best average accuracy result is achieved by j48 decision tree and naïve Bayes is 95.2345 %, and 94.6245 % respectively using three categories. This research indicated that a typical decision tree algorithm is more applicable to Amharic news categorization.

Keywords: text categorization, supervised machine learning, naive Bayes, decision tree

Procedia PDF Downloads 199

Authors: Chad Goldsworthy, B. Rajeswari Matam

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%.

Keywords: convolutional neural networks, data imbalance, deep learning, focal loss, species classification, wildlife conservation

Procedia PDF Downloads 184

Authors: Kemal Efe Eseller, Göktuğ Yazici

Abstract:

Laser-induced breakdown spectroscopy (LIBS) is a rapid optical atomic emission spectroscopy which is used for material identification and analysis with the advantages of in-situ analysis, elimination of intensive sample preparation, and micro-destructive properties for the material to be tested. LIBS delivers short pulses of laser beams onto the material in order to create plasma by excitation of the material to a certain threshold. The plasma characteristics, which consist of wavelength value and intensity amplitude, depends on the material and the experiment’s environment. In the present work, medicine samples’ spectrum profiles were obtained via LIBS. Medicine samples’ datasets include two different concentrations for both paracetamol based medicines, namely Aferin and Parafon. The spectrum data of the samples were preprocessed via filling outliers based on quartiles, smoothing spectra to eliminate noise and normalizing both wavelength and intensity axis. Statistical information was obtained and principal component analysis (PCA) was incorporated to both the preprocessed and raw datasets. The machine learning models were set based on two different train-test splits, which were 70% training – 30% test and 80% training – 20% test. Cross-validation was preferred to protect the models against overfitting; thus the sample amount is small. The machine learning results of preprocessed and raw datasets were subjected to comparison for both splits. This is the first time that all supervised machine learning classification algorithms; consisting of Decision Trees, Discriminant, naïve Bayes, Support Vector Machines (SVM), k-NN(k-Nearest Neighbor) Ensemble Learning and Neural Network algorithms; were incorporated to LIBS data of paracetamol based pharmaceutical samples, and their different concentrations on preprocessed and raw dataset in order to observe the effect of preprocessing.

Keywords: machine learning, laser-induced breakdown spectroscopy, medicines, principal component analysis, preprocessing

Procedia PDF Downloads 84

Authors: Urvashi Kaushal

Abstract:

With the entry of multinationals in India, engineering students of Indian universities have opportunity to work with the best and the most innovative industries in the world, but in order to compete in the global job market, they require an added competence of communication skills in English. With work places turning global, competence in English can provide the Indian student the added advantage to begin his/her career in the international market. The present method of teaching English in any engineering college across Gujarat mostly concentrates on developing writing, and reading skills. Developing speech becomes a secondary topic owing to the old trend of lecturing in the class room and the huge strength of the class. This paper aims to highlight the importance of improving speaking skills of engineering students. It also insists that presentations can be used as a viable method to enhance the communication skills of these students. Presentations force students to plan, prepare, practice and perfect their communication skills which will enable them to get a foothold in the industry. The paper also discusses one such experiment carried out at the author’s institute and the response it received. Further, such experimental language learning approach is bound to have some limitations and obstacles. The paper suggests ways to overcome such limitations and strives to develop an interesting means of developing communication skills of the engineering students.

Keywords: engineering, English, presentation, communication skills

Procedia PDF Downloads 438

Authors: Bingchun Liu, Pei-Chann Chang, Natasha Huang, Dun Li

Abstract:

Machine Learning and Data Mining are the two important tools for extracting useful information and knowledge from large datasets. In machine learning, classification is a wildly used technique to predict qualitative variables and is generally preferred over regression from an operational point of view. Due to the enormous increase in air pollution in various countries especially China, Air Quality Classification has become one of the most important topics in air quality research and modelling. This study aims at introducing a hybrid classification model based on information theory and Support Vector Machine (SVM) using the air quality data of four cities in China namely Beijing, Guangzhou, Shanghai and Tianjin from Jan 1, 2014 to April 30, 2016. China's Ministry of Environmental Protection has classified the daily air quality into 6 levels namely Serious Pollution, Severe Pollution, Moderate Pollution, Light Pollution, Good and Excellent based on their respective Air Quality Index (AQI) values. Using the information theory, information gain (IG) is calculated and feature selection is done for both categorical features and continuous numeric features. Then SVM Machine Learning algorithm is implemented on the selected features with cross-validation. The final evaluation reveals that the IG and SVM hybrid model performs better than SVM (alone), Artificial Neural Network (ANN) and K-Nearest Neighbours (KNN) models in terms of accuracy as well as complexity.

Keywords: machine learning, air quality classification, air quality index, information gain, support vector machine, cross-validation

Procedia PDF Downloads 231

Authors: Olaf Visker, Arnout De Vries, Lambert Schomaker

Abstract:

Predictive policing refers to the usage of analytical techniques to identify potential criminal activity. It has been widely implemented by various police departments. Being a relatively new area of research, there are, to the author’s knowledge, no absolute tried, and true methods and they still exhibit a variety of potential problems. One of those problems is closely related to the lack of understanding of how acting on these prediction influence crime itself. The goal of law enforcement is ultimately crime reduction. As such, a policy needs to be established that best facilitates this goal. This research aims to find such a policy by using adversarial agent-based modeling in combination with modern reinforcement learning techniques. It is presented here that a baseline model for both law enforcement and criminal agents and compare their performance to their respective reinforcement models. The experiments show that our smart law enforcement model is capable of reducing crime by making more deliberate choices regarding the locations of potential criminal activity. Furthermore, it is shown that the smart criminal model presents behavior consistent with popular crime theories and outperforms the baseline model in terms of crimes committed and time to capture. It does, however, still suffer from the difficulties of capturing long term rewards and learning how to handle multiple opposing goals.

Keywords: adversarial, agent based modelling, predictive policing, reinforcement learning

Procedia PDF Downloads 145

Authors: Jonas Chikelue Ogbuefi

Abstract:

Science and Technology have a major impact on societal peace, it offers support to teaching and learning, cuts costs, and offers solutions to the current agitations and militancy in Nigeria today. Christianity, for instance, did not only change and form the western world in the past 2022 but still has a substantial role to play in society through liquid ecclesiology. This paper interrogated the impact of the theology of Science and Technology as a tool for peace sustainability through peace education in Nigeria. The method adopted is a historical and descriptive method of analysis. It was discovered that a larger number of Nigerian citizens lack almost all the basic things needed for the standard of living, such as Shelter, meaningful employment, and clothing, which is the root course of all agitations in Nigeria. Based on the above findings, the paper contends that the government alone cannot restore Peace in Nigeria. Hence the inability of the government to restore peace calls for all religious actors to be involved. The main thrust and recommendation of this paper are to challenge the religious actors to implement the Theology of Science and Technology as a tool for peace restoration and should network with both the government and the private sectors to make funds available to budding and existing entrepreneurs using Science and Technology as a tool for Peace and economic sustainability. This paper viewed the theology of Science and Technology as a tool for Peace and economic sustainability in Nigeria.

Keywords: theology, science, technology, peace education

Procedia PDF Downloads 79

Authors: Terefe Alemu

Abstract:

This study is intended to examine Ethiopia’s trade flow determinants and trade potential with G20 countries whether it was overtraded or there is/are trade potential by using trade gravity model. The sources of panel data used were IMF, WDI, United Nations population division, The Heritage Foundation, Washington's No. 1 think tank online website database, online distance calculator, and others for the duration of 2010 to 2019 for 10 consecutive years. The empirical data analyzing tool used was Random effect model (REM), which is effective in estimation of time-invariant data. The empirical data analyzed using STATA software result indicates that Ethiopia has a trade potential with seven countries of G20, whereas Ethiopia overtrade with 12 countries and EU region. The Ethiopia’s and G20 countries/region bilateral trade flow statistically significant/ p<0.05/determinants were the population of G20 countries, growth domestic products of G20 countries, growth domestic products of Ethiopia, geographical distance between Ethiopia and G20 countries. The top five G20 countries exported to Ethiopia were china, United State of America, European Union, India, and South Africa, whereas the top five G20 countries imported from Ethiopia were EU, China, United State of America, Saudi Arabia, and Germany, respectively. Finally, the policy implication were Ethiopia has to Keep the consistence of trade flow with overtraded countries and improve with under traded countries through trade policy revision, and secondly, focusing on the trade determinants to improve trade flow is recommended.

Keywords: trade gravity model, trade determinants, G20, international trade, trade potential

Procedia PDF Downloads 208

Authors: Syed Romat Ali Shah, Bilal Shoaib, Saleem Akhtar, Munib Ahmad, Shahan Sadiqui

Abstract:

Classification is a data mining technique, which is recognizedon Machine Learning (ML) algorithm. It is used to classifythe individual articlein a knownofinformation into a set of predefinemodules or group. Web mining is also a portion of that sympathetic of data mining methods. The main purpose of this paper to analysis and compare the performance of Naïve Bayse Algorithm, Decision Tree, K-Nearest Neighbor (KNN), Artificial Neural Network (ANN)and Support Vector Machine (SVM). This paper consists of different ML algorithm and their advantages and disadvantages and also define research issues.

Keywords: Data Mining, Web Mining, classification, ML Algorithms

Procedia PDF Downloads 293

Authors: Davoud Masoumi, Maryam Bourbour

Abstract:

By characterizing children’s actions in the scaffolding process, which is often undermined and ignored in the studies reviewed, this study aimed to examine children’s different (re)actions in relation to the teachers’ actions in a context where digital technologies are used. Over five months, 22 children aged 4-6 with five preschool teachers were video observed. The study brought in rich details of the children’s actions in relation to the teacher’s actions in the scaffolding process. The findings of the study reveal thirteen (re)actions, including Giving short response; Explaining; Participating in the activities; Examining; Smiling and laughing; Pointing and showing; Working together; Challenging each other; Problem-solving skills; Developing vocabulary; Choosing the activity; Expressing of the emotions; and Identifying the similarities and differences. Our findings expanded and deepened the understanding of the scaffolding process, which can contribute to the notion of scaffolding and help us to gain further understanding about scaffolding of children’s learning. Characterizing the children’s (re)action in relation to teacher’s scaffolding actions further can contribute to ongoing discussions about how teachers can scaffold children’s learning using digital technologies in the learning process.

Keywords: children’ (re)actions, scaffolding process, technologies, preschools

Procedia PDF Downloads 76

Authors: Daniel Bulanda, Janusz A. Starzyk, Adrian Horzyk

Abstract:

The electrocardiogram (ECG) is one of the most commonly used medical tests, essential for correct diagnosis and treatment of the patient. While ECG devices generate a huge amount of data, only a small part of them carries valuable medical information. To deal with this problem, many compression algorithms and filters have been developed over the past years. However, the rapid development of new machine learning techniques poses new challenges. To address this class of problems, we created the FlexPoints algorithm that searches for characteristic points on the ECG signal and ignores all other points that do not carry relevant medical information. The conducted experiments proved that the presented algorithm can significantly reduce the number of data points which represents ECG signal without losing valuable medical information. These sparse but essential characteristic points (flex points) can be a perfect input for some modern machine learning models, which works much better using flex points as an input instead of raw data or data compressed by many popular algorithms.

Keywords: characteristic points, electrocardiogram, ECG, machine learning, signal compression

Procedia PDF Downloads 159

Authors: F. Ghazalnaz Sharifonnasabi, Iman Makhdoom

Abstract:

Breast cancer is a serious health concern that affects many people around the world. According to a study published in the Breast journal, the global burden of breast cancer is expected to increase significantly over the next few decades. The number of deaths from breast cancer has been increasing over the years, but the age-standardized mortality rate has decreased in some countries. It’s important to be aware of the risk factors for breast cancer and to get regular check- ups to catch it early if it does occur. Machin learning techniques have been used to aid in the early detection and diagnosis of breast cancer. These techniques, that have been shown to be effective in predicting and diagnosing the disease, have become a research hotspot. In this study, we consider two deep learning approaches including: Multi-Layer Perceptron (MLP), and Convolutional Neural Network (CNN). We also considered the five-machine learning algorithm titled: Decision Tree (C4.5), Naïve Bayesian (NB), Support Vector Machine (SVM), K-Nearest Neighbors (KNN) Algorithm and XGBoost (eXtreme Gradient Boosting) on the Breast Cancer Wisconsin Diagnostic dataset. We have carried out the process of evaluating and comparing classifiers involving selecting appropriate metrics to evaluate classifier performance and selecting an appropriate tool to quantify this performance. The main purpose of the study is predicting and diagnosis breast cancer, applying the mentioned algorithms and also discovering of the most effective with respect to confusion matrix, accuracy and precision. It is realized that CNN outperformed all other classifiers and achieved the highest accuracy (0.982456). The work is implemented in the Anaconda environment based on Python programing language.

Keywords: breast cancer, multi-layer perceptron, Naïve Bayesian, SVM, decision tree, convolutional neural network, XGBoost, KNN

Procedia PDF Downloads 70

Authors: Jason D. Lin, Christine Sim

Abstract:

This paper examines the nature of transnational media flows in East Asia, specifically expounding on the popularity of Korean dramas in China and Taiwan. Situated in interdisciplinary academic work from cultural studies, media studies, and linguistics, this project locates the significance of certain genres and regions in determining why some are subject to flow while others remain within domestic borders. Moreover, transnational flows can take one of two routes –official translations and adaptations by media corporations and subtitles written by fans in online communities. The work of 'fan-subbing' has allowed for a more democratized showcase of what bilingual fans consume and are invested in sharing, rather than what major media companies deem relevant and monetizable. This reflects a culture of relatability driven by audiences rather than by corporate direction. Of course, a variety of technological, political, and economic factors play imperative roles in how both professional and fan-made subtitles flowed across borders and between nations. While fan-subbed media may be subject to criticism because of a lack of formal regulation, these limitations can, in some cases, be overcome by the agency afforded to audiences in the digital landscape. Finally, this paper offers a critical lens for deliberating the lasting impact of fan involvement on both professional practices and the flows of mainstream media throughout East Asia.

Keywords: audience studies, bilingual, cultural proximity, fan-subbing, online communities, subtitles

Procedia PDF Downloads 121

Authors: Ahmed Abdulla Ashlam, Atta Badii, Frederic Stahl

Abstract:

In recent years, SQL injection attacks have been identified as being prevalent against web applications. They affect network security and user data, which leads to a considerable loss of money and data every year. This paper presents the use of classification algorithms in machine learning using a method to classify the login data filtering inputs into "SQLi" or "Non-SQLi,” thus increasing the reliability and accuracy of results in terms of deciding whether an operation is an attack or a valid operation. A method Web-App auto-generated twin data structure replication. Shielding against SQLi attacks (WebAppShield) that verifies all users and prevents attackers (SQLi attacks) from entering and or accessing the database, which the machine learning module predicts as "Non-SQLi" has been developed. A special login form has been developed with a special instance of data validation; this verification process secures the web application from its early stages. The system has been tested and validated, up to 99% of SQLi attacks have been prevented.

Keywords: SQL injection, attacks, web application, accuracy, database

Procedia PDF Downloads 146

Authors: Kenneth Philip Jones

Abstract:

This dissertation investigates the potential of developing educational-based video games to motivate and engage African American males. The study employed a qualitative methodological approach by investigating African American males who are avid video game players and are currently enrolled at a college or university. The participants were individually and collectively video and audio recorded during the interviews and observations. Situated Learning theory analyzed how motivation and engagement can transfer from a video game to an educational context. The research aims to address the disparities in our educational systems when it comes to providing a culture, climate, and atmosphere that will enable the academic development of African American males. The primary objective of the findings is based on the participants’ responses and the data collected to provide recommendations to educators and scholars on how to address the issues that have demoralized African American males in education and provide a platform that will allow for equality in educational development and advancement.

Keywords: video games, motivation, behavioral, learning transfer

Procedia PDF Downloads 115

Authors: A. Degale Desta, Cheng Jian

Abstract:

Deep learning application in computer vision is rapidly advancing, giving it the ability to monitor the public and quickly identify potentially anomalous behaviour from crowd scenes. Therefore, the purpose of the current work is to improve the performance of safety of people in crowd events from panic behaviour through introducing the innovative idea of Aggregation of Ensembles (AOE), which makes use of the pre-trained ConvNets and a pool of classifiers to find anomalies in video data with packed scenes. According to the theory of algorithms that applied K-means, KNN, CNN, SVD, and Faster-CNN, YOLOv5 architectures learn different levels of semantic representation from crowd videos; the proposed approach leverages an ensemble of various fine-tuned convolutional neural networks (CNN), allowing for the extraction of enriched feature sets. In addition to the above algorithms, a long short-term memory neural network to forecast future feature values and a handmade feature that takes into consideration the peculiarities of the crowd to understand human behavior. On well-known datasets of panic situations, experiments are run to assess the effectiveness and precision of the suggested method. Results reveal that, compared to state-of-the-art methodologies, the system produces better and more promising results in terms of accuracy and processing speed.

Keywords: action recognition, computer vision, crowd detecting and tracking, deep learning

Procedia PDF Downloads 154

Authors: Ashish Jaiswal, Ashwin Ramesh Babu, Mohammad Zaki Zadeh, Fillia Makedon, Glenn Wylie

Abstract:

Functional magnetic resonance imaging (fMRI) is a neuroimaging technique that records neural activations in the brain by capturing the blood oxygen level in different regions based on the task performed by a subject. Given fMRI data, the problem of predicting the state of cognitive fatigue in a person has not been investigated to its full extent. This paper proposes tackling this issue as a multi-class classification problem by dividing the state of cognitive fatigue into six different levels, ranging from no-fatigue to extreme fatigue conditions. We built a spatio-temporal model that uses convolutional neural networks (CNN) for spatial feature extraction and a long short-term memory (LSTM) network for temporal modeling of 4D fMRI scans. We also applied a self-supervised method called MoCo (Momentum Contrast) to pre-train our model on a public dataset BOLD5000 and fine-tuned it on our labeled dataset to predict cognitive fatigue. Our novel dataset contains fMRI scans from Traumatic Brain Injury (TBI) patients and healthy controls (HCs) while performing a series of N-back cognitive tasks. This method establishes a state-of-the-art technique to analyze cognitive fatigue from fMRI data and beats previous approaches to solve this problem.

Keywords: fMRI, brain imaging, deep learning, self-supervised learning, contrastive learning, cognitive fatigue

Procedia PDF Downloads 183

Authors: Manik Sharma, Ganapathy Krishnamurthi

Abstract:

The cost of some drugs and medical treatments has risen in recent years, that many patients are having to go without. A classification project could make researchers more efficient. One of the more surprising reasons behind the cost is how long it takes to bring new treatments to market. Despite improvements in technology and science, research and development continues to lag. In fact, finding new treatment takes, on average, more than 10 years and costs hundreds of millions of dollars. If successful, we could dramatically improve the industry's ability to model cellular images according to their relevant biology. In turn, greatly decreasing the cost of treatments and ensure these treatments get to patients faster. This work aims at solving a part of this problem by creating a cellular image classification model which can decipher the genetic perturbations in cell (occurring naturally or artificially). Another interesting question addressed is what makes the deep-learning model decide in a particular fashion, which can further help in demystifying the mechanism of action of certain perturbations and paves a way towards the explainability of the deep-learning model.

Keywords: cellular images, genetic perturbations, deep-learning, explainability

Procedia PDF Downloads 103

Authors: Michal Pachocki

Abstract:

This study investigates the effects of mobility in the context of a different environment and work culture through analysing the learners perception of their international work experience. Since this kind of professional training abroad is becoming more popular in Europe, mainly due to the EU funding opportunities, it is of paramount importance to assess its long-term impact on educational and career paths of former students. Moreover, the tracer study aimed at defining what professional, social and intercultural competencies were gained or developed by the interns and to which extent those competences proved to be useful meeting the labor market requirements. Being a populous EU member state which actively modernizes its vocational education system (also with European funds), Poland can serve as an illustrative case study to investigate the above described research problems. However, the examined processes are most certainly universal, wherever mobility is included in the learning process. The target group of this research was the former mobility participants and the study was conducted using quantitative and qualitative methods, such as the online survey with over 2 600 questionnaires completed by the former mobility participants; -individual in-depth interviews (IDIs) with 20 Polish graduates already present in the labour market; - 5 focus group interviews (FGIs) with 60 current students of the Polish vocational schools, who have recently returned from the training abroad. As the adopted methodology included a data triangulation, the collected findings have also been supplemented with data obtained by the desk research (mainly contextual information and statistical summary of mobility implementation). The results of this research – to be presented in full scope within the conference presentation – include the participants’ perception of their work mobility. The vast majority of graduates agrees that such an experience has had a significant impact on their professional careers and claims that they would recommend training abroad to persons who are about to enter the labor market. Moreover, in their view, such form of practical training going beyond formal education provided them with an opportunity to try their hand in the world of work. This allowed them – as they accounted for them – to get acquainted with a work system and context different from the ones experienced in Poland. Although the work mobility becomes an important element of the learning process in the growing number of Polish schools, this study reveals that many sending institutions suffer from a lack of the coherent strategy for planning domestic and foreign training programmes. Nevertheless, the significant number of graduates claims that such a synergy improves the quality of provided training. Despite that, the research proved that the transnational mobilities exert an impact on their future careers and personal development. However, such impact is, in their opinion, dependant on other factors, such as length of the training period, the nature and extent of work, recruitment criteria and the quality of organizational arrangement and mentoring provided to learners. This may indicate the salience of the sending and receiving institutions organizational capacity to deal with mobility.

Keywords: learning mobility, transnational training, vocational education and training graduates, tracer study

Procedia PDF Downloads 94

Authors: Ayesha M. Facey

Abstract:

The evaluation sought to determine the factors associated with the high failure rate among students taking a first-year introductory statistics course. By utilizing Tyler’s Objective Based Model, the main objectives were: to assess the effectiveness of the lecturer’s teaching strategies; to determine the proportion of students who attends lectures and tutorials frequently and to determine the impact of infrequent attendance on performance; to determine how the assigned activities assisted in students understanding of the course content; to ascertain the possible issues being faced by students in understanding the course material and obtain possible solutions to the challenges and to determine whether the learning outcomes have been achieved based on an assessment of the second in-course examination. A quantitative survey research strategy was employed and the study population was students enrolled in semester one of the academic year 2015/2016. A convenience sampling approach was employed resulting in a sample of 98 students. Primary data was collected using self-administered questionnaires over a one-week period. Secondary data was obtained from the results of the second in-course examination. Data were entered and analyzed in SPSS version 22 and both univariate and bivariate analyses were conducted on the information obtained from the questionnaires. Univariate analyses provided description of the sample through means, standard deviations and percentages while bivariate analyses were done using Spearman’s Rho correlation coefficient and Chi-square analyses. For secondary data, an item analysis was performed to obtain the reliability of the examination questions, difficulty index and discriminant index. The examination results also provided information on the weak areas of the students and highlighted the learning outcomes that were not achieved. Findings revealed that students were more likely to participate in lectures than tutorials and that attendance was high for both lectures and tutorials. There was a significant relationship between participation in lectures and performance on examination. However, a high proportion of students has been absent from three or more tutorials as well as lectures. A higher proportion of students indicated that they completed the assignments obtained from the lectures sometimes while they rarely completed tutorial worksheets. Students who were more likely to complete their assignments were significantly more likely to perform well on their examination. Additionally, students faced a number of challenges in understanding the course content and the topics of probability, binomial distribution and normal distribution were the most challenging. The item analysis also highlighted these topics as problem areas. Problems doing mathematics and application and analyses were their major challenges faced by students and most students indicated that some of the challenges could be alleviated if additional examples were worked in lectures and they were given more time to solve questions. Analysis of the examination results showed that a number of learning outcomes were not achieved for a number of topics. Based on the findings recommendations were made that suggested adjustments to grade allocations, delivery of lectures and methods of assessment.

Keywords: evaluation, item analysis, Tyler’s objective based model, university statistics

Procedia PDF Downloads 183

Authors: Revoti Prasad Bora, Nikita Katyal, Saurabh Yadav

Abstract:

Pre-processing plays an important role in various image processing applications. Most of the time due to the similar nature of images, a particular pre-processing or a set of pre-processing steps are sufficient to produce the desired results. However, in the education domain, there is a wide variety of images in various aspects like images with line-based diagrams, chemical formulas, mathematical equations, etc. Hence a single pre-processing or a set of pre-processing steps may not yield good results. Therefore, a Deep Learning based approach for dynamically selecting a relevant pre-processing technique for each image is proposed. The proposed method works as a classifier to detect hidden patterns in the images and predicts the relevant pre-processing technique needed for the image. This approach experimented for an image similarity matching problem but it can be adapted to other use cases too. Experimental results showed significant improvement in average similarity ranking with the proposed method as opposed to static pre-processing techniques.

Keywords: deep-learning, classification, pre-processing, computer vision, image processing, educational data mining

Procedia PDF Downloads 154

Authors: Mario Gianni, Manuel A. Ruiz Garcia, Fiora Pirri

Abstract:

In this work, we present a Bayesian non-parametric approach to model the motion control of ATVs. The motion control model is based on a Dirichlet Process-Gaussian Process (DP-GP) mixture model. The DP-GP mixture model provides a flexible representation of patterns of control manoeuvres along trajectories of different lengths and discretizations. The model also estimates the number of patterns, sufficient for modeling the dynamics of the ATV.

Keywords: Dirichlet processes, gaussian mixture models, learning motion patterns, tracked robots for urban search and rescue

Procedia PDF Downloads 444

Authors: Willy Mbenza, Sho Kenjiro

Abstract:

Increasing efforts are directed towards a better understanding and foreknowledge of extreme precipitation likelihood, given the adverse effects associated with their occurrence. This knowledge plays a crucial role in long-term planning and the formulation of effective emergency response. However, predicting extreme events reliably presents a challenge to conventional empirical/statistics due to the involvement of numerous variables spanning different time and space scales. In the recent time, Machine Learning has emerged as a promising tool for predicting the dynamics of extreme precipitation. ML techniques enables the consideration of both local and regional physical variables that have a strong influence on the likelihood of extreme precipitation. These variables encompasses factors such as air temperature, soil moisture, specific humidity, aerosol concentration, among others. In this study, we develop an ML model that incorporates both local and regional variables while establishing a robust relationship between physical variables and precipitation during the downscaling process. Furthermore, the model provides valuable information on the frequency and duration of a given intensity of precipitation.

Keywords: machine learning (ML), predictions, rainfall events, regional variables

Procedia PDF Downloads 82