Search results for: adaptive deep learning

Authors: Wiem Ben Khalifa, Dalila Souilem, Mahmoud Neji

Abstract:

The evolutions of Social Web and Semantic Web lead us to ask ourselves about the way of supporting the personalization of learning by means of intelligent filtering of educational resources published in the digital networks. We recommend personalized courses of learning articulated around a first educational course defined upstream. Resuming the context and the stakes in the personalization, we also suggest anchoring the personalization of learning in a community of interest within a group of learners enrolled in the same training. This reflection is supported by the display of an active and semantic system of learning dedicated to the constitution of personalized to measure courses and in the due time.

Keywords: Semantic Web, semantic system, ontology, evaluation, e-learning

Procedia PDF Downloads 334

Authors: Chithra A. V., Somoshree Datta, Sandeep Nithyanandan

Abstract:

Sign Language Recognition (SLR) is the process of interpreting and translating sign language into spoken or written language using technological systems. It involves recognizing hand gestures, facial expressions, and body movements that makeup sign language communication. The primary goal of SLR is to facilitate communication between hearing- and speech-impaired communities and those who do not understand sign language. Due to the increased awareness and greater recognition of the rights and needs of the hearing- and speech-impaired community, sign language recognition has gained significant importance over the past 10 years. Technological advancements in the fields of Artificial Intelligence and Machine Learning have made it more practical and feasible to create accurate SLR systems. This paper presents a distinct approach to SLR by framing it as a video classification problem using Deep Learning (DL), whereby a combination of Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) has been used. This research targets the integration of sign language recognition into healthcare settings, aiming to improve communication between medical professionals and patients with hearing impairments. The spatial features from each video frame are extracted using a CNN, which captures essential elements such as hand shapes, movements, and facial expressions. These features are then fed into an RNN network that learns the temporal dependencies and patterns inherent in sign language sequences. The INCLUDE dataset has been enhanced with more videos from the healthcare domain and the model is evaluated on the same. Our model achieves 91% accuracy, representing state-of-the-art performance in this domain. The results highlight the effectiveness of treating SLR as a video classification task with the CNN-RNN architecture. This approach not only improves recognition accuracy but also offers a scalable solution for real-time SLR applications, significantly advancing the field of accessible communication technologies.

Keywords: sign language recognition, deep learning, convolution neural network, recurrent neural network

Procedia PDF Downloads 27

Authors: Sitthichai Laisema, Panita Wannapiroon

Abstract:

This study is a research and development which is intended to: 1) design ubiquitous collaborative learning activities with virtual teams using CPS processes to develop creative thinking and collaboration skills, and 2) assess the suitability of the ubiquitous collaborative learning activities. Its methods are divided into 2 phases. Phase 1 is the design of ubiquitous collaborative learning activities with virtual teams using CPS processes, phase 2 is the assessment of the suitability of the learning activities. The samples used in this study are 5 professionals in the field of learning activity design, ubiquitous learning, information technology, creative thinking, and collaboration skills. The results showed that ubiquitous collaborative learning activities with virtual teams using CPS processes to develop creative thinking and collaboration skills consist of 3 main steps which are: 1) preparation before learning, 2) learning activities processing and 3) performance appraisal. The result of the learning activities suitability assessment from the professionals is in the highest level.

Keywords: ubiquitous learning, collaborative learning, virtual team, creative problem solving

Procedia PDF Downloads 514

Authors: Golnush Masghati-Amoli, Paul Chin

Abstract:

Over the past recent years, with the rapid increases in data availability and computing power, Machine Learning (ML) techniques have been called on in a range of different industries for their strong predictive capability. However, the use of Machine Learning in commercial banking has been limited due to a special challenge imposed by numerous regulations that require lenders to be able to explain their analytic models, not only to regulators but often to consumers. In other words, although Machine Leaning techniques enable better prediction with a higher level of accuracy, in comparison with other industries, they are adopted less frequently in commercial banking especially for scoring purposes. This is due to the fact that Machine Learning techniques are often considered as a black box and fail to provide information on why a certain risk score is given to a customer. In order to bridge this gap between the explain-ability and performance of Machine Learning techniques, a Hybrid Model is developed at Dun and Bradstreet that is focused on blending Machine Learning algorithms with traditional approaches such as scorecards. The Hybrid Model maximizes efficiency of traditional scorecards by merging its practical benefits, such as explain-ability and the ability to input domain knowledge, with the deep insights of Machine Learning techniques which can uncover patterns scorecard approaches cannot. First, through development of Machine Learning models, engineered features and latent variables and feature interactions that demonstrate high information value in the prediction of customer risk are identified. Then, these features are employed to introduce observed non-linear relationships between the explanatory and dependent variables into traditional scorecards. Moreover, instead of directly computing the Weight of Evidence (WoE) from good and bad data points, the Hybrid Model tries to match the score distribution generated by a Machine Learning algorithm, which ends up providing an estimate of the WoE for each bin. This capability helps to build powerful scorecards with sparse cases that cannot be achieved with traditional approaches. The proposed Hybrid Model is tested on different portfolios where a significant gap is observed between the performance of traditional scorecards and Machine Learning models. The result of analysis shows that Hybrid Model can improve the performance of traditional scorecards by introducing non-linear relationships between explanatory and target variables from Machine Learning models into traditional scorecards. Also, it is observed that in some scenarios the Hybrid Model can be almost as predictive as the Machine Learning techniques while being as transparent as traditional scorecards. Therefore, it is concluded that, with the use of Hybrid Model, Machine Learning algorithms can be used in the commercial banking industry without being concerned with difficulties in explaining the models for regulatory purposes.

Keywords: machine learning algorithms, scorecard, commercial banking, consumer risk, feature engineering

Procedia PDF Downloads 134

Authors: Kaushik Sathupadi, Sandesh Achar

Abstract:

Human action recognition modeling is a critical task in machine learning. These systems require better techniques for recognizing body parts and selecting optimal features based on vision sensors to identify complex action patterns efficiently. Still, there is a considerable gap and challenges between images and videos, such as brightness, motion variation, and random clutters. This paper proposes a robust approach for classifying human actions over cloud-based image data. First, we apply pre-processing and detection, human and outer shape detection techniques. Next, we extract valuable information in terms of cues. We extract two distinct features: fuzzy local binary patterns and sequence representation. Then, we applied a greedy, randomized adaptive search procedure for data optimization and dimension reduction, and for classification, we used a random forest. We tested our model on two benchmark datasets, AAMAZ and the KTH Multi-view football datasets. Our HMR framework significantly outperforms the other state-of-the-art approaches and achieves a better recognition rate of 91% and 89.6% over the AAMAZ and KTH multi-view football datasets, respectively.

Keywords: computer vision, human motion analysis, random forest, machine learning

Procedia PDF Downloads 36

Authors: Pimploi Tirastittam, Sawanath Treesathon, Amornrath Ongkawat

Abstract:

Learning Management System (LMS) is the system which uses to manage the learning in order to grouping the content and learning activity between the lecturer and learner including online examination and evaluation. Nowadays, it is the borderless learning era so the learning activities can be accessed from everywhere in the world and also anytime via the information technology and media. The learner can easily access to the knowledge so the different in time and distance is not a constraint for learning anymore. The learning pattern which was used in this research is the integration of the in-class learning and online learning via internet and will be able to monitor the progress by the Learning management system which will create the fast response and accessible learning process via the social media. In order to increase the capability and freedom of the learner, the system can show the current and history of the learning document, video conference and also has the chat room for the learner and lecturer to interact to each other. So the objectives of the “The Design and Applied of Learning Management System via Social Media on Internet: Case Study of Operating System for Business Subject” are to expand the opportunity of learning and to increase the efficiency of learning as well as increase the communication channel between lecturer and student. The data of this research was collect from 30 users of the system which are students who enroll in the subject. And the result of the research is in the “Very Good” which is conformed to the hypothesis.

Keywords: Learning Management System, social media, Operating System, information technology

Procedia PDF Downloads 356

Authors: R. W. C. Devindi, S. M. Buddika Harshanath

Abstract:

E-learning is a widely used technology for learning in the modern world. With the pandemic situation the popularity of using e-learning has been increased in a larger capacity. The e-learning educational systems require software resources as well as hardware usually but it is hard for most of the education institutions to afford those resources. Also with the massive user load e-learning has to broaden the server side resources as well. Therefore, in the present cloud computing was implemented in order to make the e – learning systems more efficient. The researcher has analyzed the quality of the e-learning systems on the perception of the learners and the teachers with the aid of hypothesis and has given the analyzed results and the discussion in this report. Therefore, the future research will be able to get some steps to increase the quality of the online learning systems furthermore. In the case of e-learning, quality assurance and cost effectiveness are essential. A complex quality assurance system is used in the stated project. There are no well-defined standard evaluation measures in this field. As a result, accurately assessing the e-learning system's overall quality is challenging. The researcher has done the analysis with the aid of standard methods and software.

Keywords: LMS–learning management system, SPSS–statistical package for social sciences (software), eigen value, hypothesis

Procedia PDF Downloads 107

Authors: Rachel Buchanan, Rebecca LaRiviere

Abstract:

Context: The ongoing effects of colonialism continue to be experienced through paternalistic policies and funding processes that cause disjuncture between and across Indigenous early childhood programming on-reserve and in urban and Northern settings in Canada. While various educational organizations and social service providers have risen to address these challenges in the short, medium and long term, there continues to be a lack in nation-wide cohesive, culturally grounded, and meaningful early learning programming for Indigenous children in Canada. Indigenous-centered early learning programs tend to face one of two scaling dilemmas: their program goals are too prescriptive to enable the program to be meaningfully replicated in different cultural/ community settings, or their program goals are too broad to be meaningfully adapted to the unique cultural and contextual needs and desires of Indigenous communities (the “franchise approach”). There are over 600 First Nations communities in Canada representing more than 50 Nations and languages. Consequently, Indigenous early learning programming cannot be applied with a universal or “one size fits all” approach. Sustainable and comprehensive programming must be responsive to each community context, building upon existing strengths and assets to avoid program duplication and irrelevance. Thesis: Community-driven and culturally adapted early childhood programming is critical but cannot be achieved on a large scale within traditional program models that are constrained by prescriptive overarching program goals. Principles, rather than goals, are an effective way to navigate and evaluate complex and dynamic systems. Principles guide an intervention to be adaptable, flexible and scalable. The Martin Family Initiative (MFI) ’s Early Years program engages a principles-based approach to programming. As will be discussed in this paper, this approach enables the program to catalyze existing community-based strengths and organizational assets toward bridging gaps across and disjuncture between Indigenous early learning programs, as well as to scale programming in sustainable, context-responsive and dynamic ways. This paper argues that using a principles-driven and adaptive scaling approach, the Early Years model establishes important learnings for culturally adapted Indigenous early learning programming in Canada. Methodology: The Early Years has leveraged this approach to develop an array of programming with partner organizations and communities across the country. The Early Years began as a singular pilot project in one First Nation. In just three years, it has expanded to five different regions and community organizations. In each context, the program supports the partner organization through different means and to different ends, the extent to which is determined in partnership with each community-based organization: in some cases, this means supporting the organization to build home visiting programming from the ground-up; in others, it means offering organization-specific culturally adapted early learning resources to support the programming that already exists in communities. Principles underpin but do not define the practices of the program in each of these relationships. This paper will explore numerous examples of principles-based adaptability with the context of the Early Years, concluding that the program model offers theadaptability and dynamism necessary to respond to unique and ever-evolving community contexts and needs of Indigenous children today.

Keywords: culturally adapted programming, indigenous early learning, principles-based approach, program scaling

Procedia PDF Downloads 186

Authors: Dajana Gašo-Sokač, Valentina Bušić

Abstract:

Deep eutectic solvents (DES) are liquids composed of two or three safe, inexpensive components, often interconnected by noncovalent hydrogen bonds which produce eutectic mixture whose melting point is lower than that of each component. No data in literature have been found on the quaternization reaction in DES. The use of DES have several advantages: they are environmentally benign and biodegradable, easy for purification and simple for preparation. An environmentally sustainable method for preparing quaternary salts of izonicotinamide and substituted 2-bromoacetophenones was demonstrated here using choline chloride-based DES. The quaternization reaction was carried out by three synthetic approaches: conventional method, microwave and ultrasonic irradiation. We showed that the highest yields were obtained by the microwave method.

Keywords: deep eutectic solvents, izonicotinamide salts, microwave synthesis, ultrasonic irradiation

Procedia PDF Downloads 130

Authors: Lidia Dzierzbicka-Glowacka, Anna Lemieszek, Mariusz Figiela

Abstract:

In 2010-2011, the research on zooplankton was conducted in the southern part of the Baltic Sea to determine seasonal variability in changes occurring throughout the zooplankton in 2010 and 2011, both in the region of Gdańsk Deep, and in the western part of Gdańsk Bay. The research in the sea showed that the taxonomic composition of holoplankton in the southern part of the Baltic Sea was similar to that recorded in this region for many years. The maximum values of abundance and biomass of zooplankton both in the Deep and the Bay of Gdańsk were observed in the summer season. Copepoda dominated in the composition of zooplankton for almost the entire study period, while rotifers occurred in larger numbers only in the summer 2010 in the Gdańsk Deep as well as in May and July 2010 in the western part of Gdańsk Bay, and meroplankton – in April 2011.

Keywords: Baltic Sea, composition, Gdańsk Bay, zooplankton

Procedia PDF Downloads 433

Authors: Swarna Pundir, Prabuddha Hans

Abstract:

As AI has already stepped into the daily life of human society, one cannot be ignorant about the data it collects and used it to provide a quality of services depending up on the individuals’ choices. It also helps in giving option for making decision Vs choice selection with a calculation based on the history of our search criteria. Over the past decade or so, the way Artificial Intelligence (AI) has impacted society is undoubtedly large.AI has changed the way we shop, the way we entertain and challenge ourselves, the way information is handled, and has automated some sections of our life. We have answered as to what AI is, but not why one may see it as useful. AI is useful because it is capable of learning and predicting outcomes, using Machine Learning (ML) and Deep Learning (DL) with the help of Artificial Neural Networks (ANN). AI can also be a system that can act like humans. One of the major impacts be Joblessness through automation via AI which is seen mostly in manufacturing sectors, especially in the routine manual and blue-collar occupations and those without a college degree. It raises some serious concerns about AI in regards of less employment, ethics in making moral decisions, Individuals privacy, human judgement’s, natural emotions, biased decisions, discrimination. So, the question is if an error occurs who will be responsible, or it will be just waved off as a “Machine Error”, with no one taking the responsibility of any wrongdoing, it is essential to form some rules for using the AI where both machines and humans are involved.

Keywords: AI, ML, DL, ANN

Procedia PDF Downloads 97

Authors: Henni Mansour Abdelwaheb

Abstract:

This study discusses the design of a bounded position/force feedback controller developed to ensure position and force tracking for bilateral teleoperation arms operating with variable delay, and actuator saturation. Also, an adaptive robust Radial Basis Function (RBF) neural network is used to estimate the environment torque. The parameters of the environment torque are then sent from the slave site to the master site as a non-power signal to avoid passivity problems. Moreover, a nonlinear function is applied to each controller term as a smooth saturation function, providing a bounded control signal and preserving the system’s actuators. Lastly, the Lyapunov approach demonstrates the global stability of the controlled system, and numerical experiment results further confirm the validity of the presented strategy.

Keywords: teleoperation manipulators system, time-varying delay, actuator saturation, adaptive robust rbf neural network approximation, uncertainties

Procedia PDF Downloads 75

Authors: Farzad Hosseini Hossein Abadi, Cristina Prieto Sierra, Cesar Álvarez Díaz

Abstract:

Predicting streamflow accurately in flashy catchments prone to floods is a major research and operational challenge in hydrological modeling. Recent advancements in deep learning, particularly Long Short-Term Memory (LSTM) networks, have shown to be promising in achieving accurate hydrological predictions at daily and hourly time scales. In this work, a multi-timescale LSTM (MTS-LSTM) network was applied to the context of regional hydrological predictions at an hourly time scale in flashy catchments. The case study includes 40 catchments allocated in the Basque Country, north of Spain. We explore the impact of hyperparameters on the performance of streamflow predictions given by regional deep learning models through systematic hyperparameter tuning - where optimal regional values for different catchments are identified. The results show that predictions are highly accurate, with Nash-Sutcliffe (NSE) and Kling-Gupta (KGE) metrics values as high as 0.98 and 0.97, respectively. A principal component analysis reveals that a hyperparameter related to the length of the input sequence contributes most significantly to the prediction performance. The findings suggest that input sequence lengths have a crucial impact on the model prediction performance. Moreover, employing catchment-scale analysis reveals distinct sequence lengths for individual basins, highlighting the necessity of customizing this hyperparameter based on each catchment’s characteristics. This aligns with well known “uniqueness of the place” paradigm. In prior research, tuning the length of the input sequence of LSTMs has received limited focus in the field of streamflow prediction. Initially it was set to 365 days to capture a full annual water cycle. Later, performing limited systematic hyper-tuning using grid search, revealed a modification to 270 days. However, despite the significance of this hyperparameter in hydrological predictions, usually studies have overlooked its tuning and fixed it to 365 days. This study, employing a simultaneous systematic hyperparameter tuning approach, emphasizes the critical role of input sequence length as an influential hyperparameter in configuring LSTMs for regional streamflow prediction. Proper tuning of this hyperparameter is essential for achieving accurate hourly predictions using deep learning models.

Keywords: LSTMs, streamflow, hyperparameters, hydrology

Procedia PDF Downloads 69

Authors: Xu Jie

Abstract:

As a key network security method, cryptographic services must fully cope with problems such as the wide variety of cryptographic algorithms, high concurrency requirements, random job crossovers, and instantaneous surges in workloads. Its complexity and dynamics also make it difficult for traditional static security policies to cope with the ever-changing situation. Cyber Threats and Environment. Traditional resource scheduling algorithms are inadequate when facing complex decision-making problems in dynamic environments. A network cryptographic resource allocation algorithm based on reinforcement learning is proposed, aiming to optimize task energy consumption, migration cost, and fitness of differentiated services (including user, data, and task security) by modeling the multi-job collaborative cryptographic service scheduling problem as a multi-objective optimized job flow scheduling problem and using a multi-agent reinforcement learning method, efficient scheduling and optimal configuration of cryptographic service resources are achieved. By introducing reinforcement learning, resource allocation strategies can be adjusted in real-time in a dynamic environment, improving resource utilization and achieving load balancing. Experimental results show that this algorithm has significant advantages in path planning length, system delay and network load balancing and effectively solves the problem of complex resource scheduling in cryptographic services.

Keywords: cloud computing, cryptography on-demand service, reinforcement learning, workflow scheduling

Procedia PDF Downloads 12

Authors: Farhad Shafiepour Motlagh, Narges Salehi

Abstract:

Purpose: The purpose of this study was to support student strategies for virtual learning in the learning management system. Methodology: The research method was based on grounded theory. The statistical population included all the articles of the ten years 2022-2010, and the sampling method was purposeful to the extent of theoretical saturation (n=31 ). Data collection was done by referring to the authoritative scientific databases of Emerald, Springer, Elsevier, Google Scholar, Sage Publication, and Science Direct. For data analysis, open coding, axial coding, and selective coding were used. Results: The results showed that causal conditions include cognitive empowerment (comprehension, analysis, composition), emotional empowerment (learning motivation, involvement in the learning system, enthusiasm for learning), psychomotor empowerment (learning to master, internalizing learning skills, creativity in learning). Conclusion: Supporting students requires their empowerment in three dimensions: cognitive, emotional empowerment, and psychomotor empowerment. In such a way that by introducing them to enter the learning management system, the capacities of the system, the toolkit of learning in the system, improve the motivation to learn in them, and in such a case, by learning more in the learning management system, they will reach mastery learning.

Keywords: student support, virtual education, learning management system, electronic

Procedia PDF Downloads 307

Authors: Chris Landorf, Stephen Ward

Abstract:

This paper addresses a virtual environment approach to work integrated learning for students in construction-related disciplines. The virtual approach provides a safe and pedagogically rigorous environment where students can apply theoretical knowledge in a simulated real-world context. The paper describes the development of a 4-dimensional digital construction environment and associated learning activities funded by the Australian Office for Learning and Teaching. The environment was trialled with over 1,300 students and evaluated through questionnaires, observational studies and coursework analysis. Results demonstrate a positive impact on students’ technical learning and collaboration skills, but there is need for further research in relation to critical thinking skills and work-readiness.

Keywords: architectural education, construction industry, digital learning environments, immersive learning

Procedia PDF Downloads 410

Authors: Agastya Pratap Singh

Abstract:

This review paper examines the emerging applications of generative adversarial networks (GANs) in the fields of image recognition and anomaly detection. With the rapid growth of digital image data, the need for efficient and accurate methodologies to identify and classify images has become increasingly critical. GANs, known for their ability to generate realistic data, have gained significant attention for their potential to enhance traditional image recognition systems and improve anomaly detection performance. The paper systematically analyzes various GAN architectures and their modifications tailored for image recognition tasks, highlighting their strengths and limitations. Additionally, it delves into the effectiveness of GANs in detecting anomalies in diverse datasets, including medical imaging, industrial inspection, and surveillance. The review also discusses the challenges faced in training GANs, such as mode collapse and stability issues, and presents recent advancements aimed at overcoming these obstacles.

Keywords: generative adversarial networks, image recognition, anomaly detection, synthetic data generation, deep learning, computer vision, unsupervised learning, pattern recognition, model evaluation, machine learning applications

Procedia PDF Downloads 25

Authors: Albert Bou, Sebastian Dittert, Gianni de Fabritiis

Abstract:

Advancing reinforcement learning (RL) requires tools that are flexible enough to easily prototype new methods while avoiding impractically slow experimental turnaround times. To match the first requirement, the most popular RL libraries advocate for highly modular agent composability, which facilitates experimentation and development. To solve challenging environments within reasonable time frames, scaling RL to large sampling and computing resources has proved a successful strategy. However, this capability has been so far difficult to combine with modularity. In this work, we explore design choices to allow agent composability both at a local and distributed level of execution. We propose a versatile approach that allows the definition of RL agents at different scales through independent, reusable components. We demonstrate experimentally that our design choices allow us to reproduce classical benchmarks, explore multiple distributed architectures, and solve novel and complex environments while giving full control to the user in the agent definition and training scheme definition. We believe this work can provide useful insights to the next generation of RL libraries.

Keywords: deep reinforcement learning, Python, PyTorch, distributed training, modularity, library

Procedia PDF Downloads 83

Authors: Jonathan Sohn

Abstract:

Deep neural networks (DNNs) have shown state-of-the-art performance for many applications, including computer vision, natural language processing, and speech recognition. Recently, adversarial attacks have been studied in the context of deep neural networks, which aim to alter the results of deep neural networks by modifying the inputs slightly. For example, an adversarial attack on a DNN used for object detection can cause the DNN to miss certain objects. As a result, the reliability of DNNs is undermined by their lack of robustness against adversarial attacks, raising concerns about their use in safety-critical applications such as autonomous driving. In this paper, we focus on studying the adversarial attacks and defenses on DNNs for image classification. There are two types of adversarial attacks studied which are fast gradient sign method (FGSM) attack and projected gradient descent (PGD) attack. A DNN forms decision boundaries that separate the input images into different categories. The adversarial attack slightly alters the image to move over the decision boundary, causing the DNN to misclassify the image. FGSM attack obtains the gradient with respect to the image and updates the image once based on the gradients to cross the decision boundary. PGD attack, instead of taking one big step, repeatedly modifies the input image with multiple small steps. There is also another type of attack called the target attack. This adversarial attack is designed to make the machine classify an image to a class chosen by the attacker. We can defend against adversarial attacks by incorporating adversarial examples in training. Specifically, instead of training the neural network with clean examples, we can explicitly let the neural network learn from the adversarial examples. In our experiments, the digit recognition accuracy on the MNIST dataset drops from 97.81% to 39.50% and 34.01% when the DNN is attacked by FGSM and PGD attacks, respectively. If we utilize FGSM training as a defense method, the classification accuracy greatly improves from 39.50% to 92.31% for FGSM attacks and from 34.01% to 75.63% for PGD attacks. To further improve the classification accuracy under adversarial attacks, we can also use a stronger PGD training method. PGD training improves the accuracy by 2.7% under FGSM attacks and 18.4% under PGD attacks over FGSM training. It is worth mentioning that both FGSM and PGD training do not affect the accuracy of clean images. In summary, we find that PGD attacks can greatly degrade the performance of DNNs, and PGD training is a very effective way to defend against such attacks. PGD attacks and defence are overall significantly more effective than FGSM methods.

Keywords: deep neural network, adversarial attack, adversarial defense, adversarial machine learning

Procedia PDF Downloads 195

Authors: B. R. Campomanes-Alvarez, P. Quiros, B. Fernandez

Abstract:

Automatic Speech Recognition (ASR) is a machine-based process of decoding and transcribing oral speech. A typical ASR system receives acoustic input from a speaker or an audio file, analyzes it using algorithms, and produces an output in the form of a text. Some speech recognition systems use Hidden Markov Models (HMMs) to deal with the temporal variability of speech and Gaussian Mixture Models (GMMs) to determine how well each state of each HMM fits a short window of frames of coefficients that represents the acoustic input. Another way to evaluate the fit is to use a feed-forward neural network that takes several frames of coefficients as input and produces posterior probabilities over HMM states as output. Deep neural networks (DNNs) that have many hidden layers and are trained using new methods have been shown to outperform GMMs on a variety of speech recognition systems. Acoustic models for state-of-the-art ASR systems are usually training on massive amounts of data. However, audio files with their corresponding transcriptions can be difficult to obtain, especially in the Spanish language. Hence, in the case of these low-resource scenarios, building an ASR model is considered as a complex task due to the lack of labeled data, resulting in an under-trained system. Semi-supervised learning approaches arise as necessary tasks given the high cost of transcribing audio data. The main goal of this proposal is to develop a procedure based on acoustic semi-supervised learning for Spanish ASR systems by using DNNs. This semi-supervised learning approach consists of: (a) Training a seed ASR model with a DNN using a set of audios and their respective transcriptions. A DNN with a one-hidden-layer network was initialized; increasing the number of hidden layers in training, to a five. A refinement, which consisted of the weight matrix plus bias term and a Stochastic Gradient Descent (SGD) training were also performed. The objective function was the cross-entropy criterion. (b) Decoding/testing a set of unlabeled data with the obtained seed model. (c) Selecting a suitable subset of the validated data to retrain the seed model, thereby improving its performance on the target test set. To choose the most precise transcriptions, three confidence scores or metrics, regarding the lattice concept (based on the graph cost, the acoustic cost and a combination of both), was performed as selection technique. The performance of the ASR system will be calculated by means of the Word Error Rate (WER). The test dataset was renewed in order to extract the new transcriptions added to the training dataset. Some experiments were carried out in order to select the best ASR results. A comparison between a GMM-based model without retraining and the DNN proposed system was also made under the same conditions. Results showed that the semi-supervised ASR-model based on DNNs outperformed the GMM-model, in terms of WER, in all tested cases. The best result obtained an improvement of 6% relative WER. Hence, these promising results suggest that the proposed technique could be suitable for building ASR models in low-resource environments.

Keywords: automatic speech recognition, deep neural networks, machine learning, semi-supervised learning

Procedia PDF Downloads 339

Authors: Fatemeh Keivanifard

Abstract:

E-learning is becoming increasingly prominent in higher education, with universities increasing provision and more students signing up. This paper examines factors that predict students' attitudes to adapt e-learning at the Khuzestan province Iran. Understanding the nature of these factors may assist these universities in promoting the use of information and communication technology in teaching and learning. The main focus of the paper is on the university students, whose decision supports effective implementation of e-learning. Data was collected through a survey of 300 post graduate students at the University of dezful, shooshtar and chamran in Khuzestan. The technology adoption model put forward by Davis is utilized in this study. Two more independent variables are added to the original model, namely, the pressure to act and resources availability. The results show that there are five factors that can be used in modeling students' attitudes to adapt e-learning. These factors are intention toward e-learning, perceived usefulness of e-learning, perceived ease of e-learning use, pressure to use e-learning, and the availability of resources needed to use e-learning.

Keywords: e-learning, intention, ease of use, pressure to use, usefulness

Procedia PDF Downloads 368

Authors: Jurijs Salijevs, Katrina Bolocko

Abstract:

The integration of artificial intelligence and neural networks has significantly changed full-body imaging and high-resolution 3D mapping systems, and this paper reviews research in these areas. With an emphasis on their use in the early identification of melanoma and other disorders, the goal is to give a wide perspective on the current status and potential future of these medical imaging technologies. Authors also examine methodologies such as machine learning and deep learning, seeking to identify efficient procedures that enhance diagnostic capabilities through the analysis of 3D body scans. This work aims to encourage further research and technological development to harness the full potential of AI in disease diagnosis.

Keywords: artificial intelligence, neural networks, 3D scan, body scan, 3D mapping system, healthcare

Procedia PDF Downloads 103

Authors: Rami Faraj, Cezary Graczykowski, Błażej Popławski, Grzegorz Mikułowski, Rafał Wiszowaty

Abstract:

Progress in the field of sensors, electronics and computing results in more and more often applications of adaptive techniques for dynamic response mitigation. When it comes to systems excited with mechanical impacts, the control system has to take into account the significant limitations of actuators responsible for system adaptation. The paper provides a comprehensive discussion of the problem of appropriate design and implementation of adaptation techniques and mechanisms. Two case studies are presented in order to compare completely different adaptation schemes. The first example concerns a double-chamber pneumatic shock absorber with a fast piezo-electric valve and parameters corresponding to the suspension of a small unmanned aerial vehicle, whereas the second considered system is a safety air cushion applied for evacuation of people from heights during a fire. For both systems, it is possible to ensure adaptive performance, but a realization of the system’s adaptation is completely different. The reason for this is technical limitations corresponding to specific types of shock-absorbing devices and their parameters. Impact mitigation using a pneumatic shock absorber corresponds to much higher pressures and small mass flow rates, which can be achieved with minimal change of valve opening. In turn, mass flow rates in safety air cushions relate to gas release areas counted in thousands of sq. cm. Because of these facts, both shock-absorbing systems are controlled based on completely different approaches. Pneumatic shock-absorber takes advantage of real-time control with valve opening recalculated at least every millisecond. In contrast, safety air cushion is controlled using the semi-passive technique, where adaptation is provided using prediction of the entire impact mitigation process. Similarities of both approaches, including applied models, algorithms and equipment, are discussed. The entire study is supported by numerical simulations and experimental tests, which prove the effectiveness of both adaptive impact mitigation techniques.

Keywords: adaptive control, adaptive system, impact mitigation, pneumatic system, shock-absorber

Procedia PDF Downloads 90

Authors: Ramezani M., Neitzert T.

Abstract:

This paper investigates mechanical properties and formability of the AZ61 magnesium alloy at high temperatures. Tensile tests were performed at elevated temperatures of up to 400ºC. The results showed that as temperature increases, yield strength and ultimate tensile strength decrease significantly, while the material experiences an increase in ductility (maximum elongation before break). A finite element model has been developed to further investigate the formability of the AZ61 alloy by deep drawing a square cup. Effects of different process parameters such as punch and die geometry, forming speed and temperature as well as blank-holder force on deep drawability of the AZ61 alloy were studied and optimum values for these parameters are achieved which can be used as a design guide for deep drawing of this alloy.

Keywords: AZ61, formability, magnesium, mechanical properties

Procedia PDF Downloads 579

Authors: Yuta Nakano, Kozo Kajiwara, Atsushi Hori, Takeshi Fujita

Abstract:

In association with the wave of electric vehicles (EV), low energy consumption systems have become more and more important. One of the key technologies to realize low energy consumption is a dynamic vision sensor (DVS), or we can call it an event sensor, neuromorphic vision sensor and so on. This sensor has several features, such as high temporal resolution, which can achieve 1 Mframe/s, and a high dynamic range (120 DB). However, the point that can contribute to low energy consumption the most is its sparsity; to be more specific, this sensor only captures the pixels that have intensity change. In other words, there is no signal in the area that does not have any intensity change. That is to say, this sensor is more energy efficient than conventional sensors such as RGB cameras because we can remove redundant data. On the other side of the advantages, it is difficult to handle the data because the data format is completely different from RGB image; for example, acquired signals are asynchronous and sparse, and each signal is composed of x-y coordinate, polarity (two values: +1 or -1) and time stamp, it does not include intensity such as RGB values. Therefore, as we cannot use existing algorithms straightforwardly, we have to design a new processing algorithm to cope with DVS data. In order to solve difficulties caused by data format differences, most of the prior arts make a frame data and feed it to deep learning such as Convolutional Neural Networks (CNN) for object detection and recognition purposes. However, even though we can feed the data, it is still difficult to achieve good performance due to a lack of intensity information. Although polarity is often used as intensity instead of RGB pixel value, it is apparent that polarity information is not rich enough. Considering this context, we proposed to use the timestamp information as a data representation that is fed to deep learning. Concretely, at first, we also make frame data divided by a certain time period, then give intensity value in response to the timestamp in each frame; for example, a high value is given on a recent signal. We expected that this data representation could capture the features, especially of moving objects, because timestamp represents the movement direction and speed. By using this proposal method, we made our own dataset by DVS fixed on a parked car to develop an application for a surveillance system that can detect persons around the car. We think DVS is one of the ideal sensors for surveillance purposes because this sensor can run for a long time with low energy consumption in a NOT dynamic situation. For comparison purposes, we reproduced state of the art method as a benchmark, which makes frames the same as us and feeds polarity information to CNN. Then, we measured the object detection performances of the benchmark and ours on the same dataset. As a result, our method achieved a maximum of 7 points greater than the benchmark in the F1 score.

Keywords: event camera, dynamic vision sensor, deep learning, data representation, object recognition, low energy consumption

Procedia PDF Downloads 97

Authors: John Zanetich

Abstract:

This paper uses a pragmatic research approach to investigate the relationships between Active Development of Tacit Knowledge (ADTK), social media (Facebook) and classroom learning communities. This paper investigates the use of learning communities and social media as the context and means for changing tacit knowledge to explicit and presents a dynamic model of the development of a classroom learning community. The goal of this study is to identify the point that explicit knowledge is converted to tacit knowledge and to test a way to quantify the exchange using social media and learning communities.

Keywords: tacit knowledge, knowledge management, college programs, experiential learning, learning communities

Procedia PDF Downloads 361

Authors: Muhammad Saleem

Abstract:

Background: The teaching of sports sciences encompasses a broad spectrum of disciplines, including biomechanics, physiology, psychology, and coaching. Effective pedagogical techniques are crucial in imparting both theoretical knowledge and practical skills necessary for students to excel in the field. The impact of these techniques on students’ learning outcomes, engagement, and professional preparedness remains a vital area of study. Objective: This study aims to evaluate the effectiveness of various pedagogical techniques used in the teaching of sports sciences. It seeks to identify which methods most significantly enhance student learning, retention, engagement, and practical application of knowledge. Methods: A mixed-methods approach was employed, including both quantitative and qualitative analyses. The study involved a comparative analysis of traditional lecture-based teaching, experiential learning, problem-based learning (PBL), and technology-enhanced learning (TEL). Data were collected through surveys, interviews, and academic performance assessments from students enrolled in sports sciences programs at multiple universities. Statistical analysis was used to evaluate academic performance, while thematic analysis was applied to qualitative data to capture student experiences and perceptions. Results: The findings indicate that experiential learning and PBL significantly improve students' understanding and retention of complex sports science concepts compared to traditional lectures. TEL was found to enhance engagement and provide students with flexible learning opportunities, but its impact on deep learning varied depending on the quality of the digital resources. Overall, a combination of experiential learning, PBL, and TEL was identified as the most effective pedagogical approach, leading to higher student satisfaction and better preparedness for real-world applications. Conclusion: The study underscores the importance of adopting diverse and student-centered pedagogical techniques in the teaching of sports sciences. While traditional lectures remain useful for foundational knowledge, integrating experiential learning, PBL, and TEL can substantially improve student outcomes. These findings suggest that educators should consider a blended approach to pedagogy to maximize the effectiveness of sports science education.

Keywords: sport sciences, pedagogical techniques, health and physical education, problem-based learning, student engagement

Procedia PDF Downloads 24

Authors: Javier Muro, Anja Linstadter, Florian Manner, Lisa Schwarz, Stephan Wollauer, Paul Magdon, Gohar Ghazaryan, Olena Dubovyk

Abstract:

Monitoring the trade-off between biomass production and biodiversity in grasslands is critical to evaluate the effects of management practices across environmental gradients. New generations of remote sensing sensors and machine learning approaches can model grasslands’ characteristics with varying accuracies. However, studies often fail to cover a sufficiently broad range of environmental conditions, and evidence suggests that prediction models might be case specific. In this study, biomass production and biodiversity indices (species richness and Fishers’ α) are modeled in 150 grassland plots for three sites across Germany. These sites represent a North-South gradient and are characterized by distinct soil types, topographic properties, climatic conditions, and management intensities. Predictors used are derived from Sentinel-1 & 2 and a set of topoedaphic variables. The transferability of the models is tested by training and validating at different sites. The performance of feed-forward deep neural networks (DNN) is compared to a random forest algorithm. While biomass predictions across gradients and sites were acceptable (r2 0.5), predictions of biodiversity indices were poor (r2 0.14). DNN showed higher generalization capacity than random forest when predicting biomass across gradients and sites (relative root mean squared error of 0.5 for DNN vs. 0.85 for random forest). DNN also achieved high performance when using the Sentinel-2 surface reflectance data rather than different combinations of spectral indices, Sentinel-1 data, or topoedaphic variables, simplifying dimensionality. This study demonstrates the necessity of training biomass and biodiversity models using a broad range of environmental conditions and ensuring spatial independence to have realistic and transferable models where plot level information can be upscaled to landscape scale.

Keywords: ecosystem services, grassland management, machine learning, remote sensing

Procedia PDF Downloads 218

Authors: Khaled Halimi, Hassina Seridi-Bouchelaghem

Abstract:

The purpose of this paper is to describe how learning analytics approaches based on social semantic web techniques can be applied to enhance the lifelong learning experiences in a connectivist perspective. For this reason, a prototype of a system called SoLearn (Social Learning Environment) that supports this approach. We observed and studied literature related to lifelong learning systems, social semantic web and ontologies, connectivism theory, learning analytics approaches and reviewed implemented systems based on these fields to extract and draw conclusions about necessary features for enhancing the lifelong learning process. The semantic analytics of learning can be used for viewing, studying and analysing the massive data generated by learners, which helps them to understand through recommendations, charts and figures their learning and behaviour, and to detect where they have weaknesses or limitations. This paper emphasises that implementing a learning analytics approach based on social semantic web representations can enhance the learning process. From one hand, the analysis process leverages the meaning expressed by semantics presented in the ontology (relationships between concepts). From the other hand, the analysis process exploits the discovery of new knowledge by means of inferring mechanism of the semantic web.

Keywords: connectivism, learning analytics, lifelong learning, social semantic web

Procedia PDF Downloads 214

Authors: Hélène Knoerr

Abstract:

In an increasingly global world, more and more international students attend academic courses and programs in a second or foreign language, and local students register in language learning classes in order to improve their employability. These students need to quickly become proficient in the new language. How can we, as administrators, curriculum developers and teachers, make sure that they have the tools they need in order to develop their language skills in an academic context? This paper will describe the development and implementation of a new course, Learning to learn, as part of the Major in French/English as a Second Language at the University of Ottawa. This academic program was recently completely overhauled in order to reflect the current approaches in language learning (more specifically, the action-oriented approach as embodied in the Common European Framework of Reference for Languages, and the concept of life-long autonomous learning). The course itself is based on research on language learning strategies, with a particular focus on the characteristics of the “good language learner”. We will present the methodological and pedagogical foundations, describe the course objectives and learning outcomes, the language learning strategies, and the classroom activities. The paper will conclude with students’ feedback and suggest avenues for further exploration.

Keywords: curriculum development, language learning, learning strategies, second language

Procedia PDF Downloads 411