Search results for: interpreting deep learning

Authors: Thiago Spilborghs Bueno Meyer, Plinio Thomaz Aquino Junior

Abstract:

Through speech, which privileges the functional and interactive nature of the text, it is possible to ascertain the spatiotemporal circumstances, the conditions of production and reception of the discourse, the explicit purposes such as informing, explaining, convincing, etc. These conditions allow bringing the interaction between humans closer to the human-robot interaction, making it natural and sensitive to information. However, it is not enough to understand what is said; it is necessary to recognize emotions for the desired interaction. The validity of the use of neural networks for feature selection and emotion recognition was verified. For this purpose, it is proposed the use of neural networks and comparison of models, such as recurrent neural networks and deep neural networks, in order to carry out the classification of emotions through speech signals to verify the quality of recognition. It is expected to enable the implementation of robots in a domestic environment, such as the HERA robot from the RoboFEI@Home team, which focuses on autonomous service robots for the domestic environment. Tests were performed using only the Mel-Frequency Cepstral Coefficients, as well as tests with several characteristics of Delta-MFCC, spectral contrast, and the Mel spectrogram. To carry out the training, validation and testing of the neural networks, the eNTERFACE’05 database was used, which has 42 speakers from 14 different nationalities speaking the English language. The data from the chosen database are videos that, for use in neural networks, were converted into audios. It was found as a result, a classification of 51,969% of correct answers when using the deep neural network, when the use of the recurrent neural network was verified, with the classification with accuracy equal to 44.09%. The results are more accurate when only the Mel-Frequency Cepstral Coefficients are used for the classification, using the classifier with the deep neural network, and in only one case, it is possible to observe a greater accuracy by the recurrent neural network, which occurs in the use of various features and setting 73 for batch size and 100 training epochs.

Keywords: emotion recognition, speech, deep learning, human-robot interaction, neural networks

Procedia PDF Downloads 170

Authors: Ming-Jen Huang, Chun-Fang Huang, Chiching Wei

Abstract:

With the recent advance of the deep neural network, we observe new applications of NLP (natural language processing) and CV (computer vision) powered by deep neural networks for processing business documents. However, creating a real-world document processing system needs to integrate several NLP and CV tasks, rather than treating them separately. There is a need to have a unified approach for processing documents containing textual and graphical elements with rich formats, diverse layout arrangement, and distinct semantics. In this paper, a framework that fulfills this unified approach is presented. The framework includes a representation model definition for holding the information generated by various tasks and specifications defining the coordination between these tasks. The framework is a blueprint for building a system that can process documents with rich formats, styles, and multiple types of elements. The flexible and lightweight design of the framework can help build a system for diverse business scenarios, such as contract monitoring and reviewing.

Keywords: document processing, framework, formal definition, machine learning

Procedia PDF Downloads 214

Authors: Nidhal K. Azawi, John M. Gauch

Abstract:

Colorectal cancer is one of the leading causes of cancer death in the US and the world, which is why millions of colonoscopy examinations are performed annually. Unfortunately, noise, specular highlights, and motion artifacts corrupt many images in a typical colonoscopy exam. The goal of our research is to produce automated techniques to detect and correct or remove these noninformative images from colonoscopy videos, so physicians can focus their attention on informative images. In this research, we first automatically extract features from images. Then we use machine learning and deep neural network to classify colonoscopy images as either informative or noninformative. Our results show that we achieve image classification accuracy between 92-98%. We also show how the removal of noninformative images together with image alignment can aid in the creation of image panoramas and other visualizations of colonoscopy images.

Keywords: colonoscopy classification, feature extraction, image alignment, machine learning

Procedia PDF Downloads 253

Authors: Hossam Abdelrahman, Sama Rostom, Reem Yassein, Yara Mohamed, Salma Salah, Nour Awny

Abstract:

In today’s environment, people are becoming increasingly interested in their appearance. However, they are afraid of their unknown appearance after a plastic surgery or treatment. Accidents, burns and genetic problems such as bowing of body parts of people have a negative impact on their mental health with their appearance and this makes them feel uncomfortable and underestimated. The approach presents a revolutionary deep learning-based image inpainting method that analyses the various picture structures and corrects damaged images. In this study, A model is proposed based on the in-painting of medical images with Stable Diffusion Inpainting method. Reconstructing missing and damaged sections of an image is known as image inpainting is a key progress facilitated by deep neural networks. The system uses the input of the user of an image to indicate a problem, the system will then modify the image and output the fixed image, facilitating for the patient to see the final result.

Keywords: generative adversarial network, large mask inpainting, stable diffusion inpainting, plastic surgery

Procedia PDF Downloads 74

Authors: Kherafa Abdennasser

Abstract:

The application of Information and Communication Technologies (ICT) to the training area led to the creation of this new reality called E-learning. That last one is described like the marriage of multi- media (sound, image and text) and of the internet (diffusion on line, interactivity). Distance learning became an important totality for training and that last pass in particular by the setup of a distance learning platform. In our memory, we will use an open source platform named Dokeos for the management of a distance training of GPS called e-GPS. The learner is followed in all his training. In this system, trainers and learners communicate individually or in group, the administrator setup and make sure of this system maintenance.

Keywords: ICT, E-learning, learning plate-forme, Dokeos, GPS

Procedia PDF Downloads 477

Authors: Fangfei Li

Abstract:

This research was conducted to explore how Chinese overseas students, who rarely received teacher feedback during their undergraduate studies in China, engaged in a different feedback provision context in the UK universities. In particular, this research provides some insights into Chinese students’ perspectives on how they made sense of the teacher feedback they obtained and how they took it on board in their assignments. Research questions in this study are 1) What are Chinese overseas students’ perceptions of teacher feedback on courses in UK higher education? 2) How do they respond to the teacher feedback they obtained? 3) What factors might influence their engagement with teacher feedback? Multiple case studies of five Chinese overseas students in a UK university have been carried out to address the research questions. The main data collection instruments are various types of semi-structured interviews, consisting of background interviews, scenario-based activities, stimulated recall sessions and retrospective interviews. Research findings indicate that student engagement with teacher feedback is a complex learning process incorporating several stages: from initial teacher input to ultimate transformational learning. Apart from students interpreting teachers’ comments/suggestions by themselves, students’ understandings of and responses to teacher feedback could also be influenced by pre-submission guidance, peer discussion, use of exemplars and post-submission discussion with teachers. These are key factors influencing students to make use of teacher feedback. Findings also reveal that the level of students’ reflections on tutor feedback influences the quality of their assignments and even their future learning. To sum up, this paper will discuss the current concepts of teacher feedback in existing studies and research findings of this study from which reconceptualization of teacher feedback has occurred.

Keywords: Chinese students, student engagement, teacher feedback, the UK higher education

Procedia PDF Downloads 348

Authors: Mohamed Bendahmane, Brahim Elfalaki, Mohammed Benattou

Abstract:

One of the major sources of learners' professional difficulties is their heterogeneity. Whether on cognitive, social, cultural or emotional level, learners being part of the same group have many differences. These differences do not allow to apply the same learning process at all learners. Thus, an optimal learning path for one, is not necessarily the same for the other. We present in this paper a model-oriented service to offer to each learner a personalized learning path to acquire the targeted skills.

Keywords: learning path, web service, trace analysis, personalization

Procedia PDF Downloads 356

Authors: Omran Alharbi

Abstract:

It is difficult to find an aspect of our modern lives that has been untouched by mobile technology. Indeed, the use of mobile learning in Saudi Arabia may enhance students’ learning and increase overall educational standards. However, within tertiary education, the success of e-learning implementation depends on the degree to which students and educators accept mobile learning and are willing to utilise it. Therefore, this research targeted the factors that influence Hail University instructors’ intentions to use mobile learning. An online survey was completed by eighty instructors and it was found that their use of mobile learning was heavily predicted by performance experience, effort expectancy, social influence, and facilitating conditions; the multiple regression analysis revealed that 67% of the variation was accounted for by these variables. From these variables, effort expectancy was shown to be the strongest predictor of intention to use e-learning for instructors.

Keywords: acceptance, faculty member, mobile learning, KSA

Procedia PDF Downloads 153

Authors: Marina Vicario, Amadeo Argüelles, Pilar Gómez, Carlos Hernández

Abstract:

In this paper, the Computer Research Network of the National Polytechnic Institute of Mexico proposes a paradigmatic model for the inference of cognitive patterns in digital learning systems. This model leads to metadata architecture useful for analysis and prediction in online learning systems; especially on MOOc's architectures. The model is in the design phase and expects to be tested through an institutional of courses project which is going to develop for the MOOc.

Keywords: cognitive footprints, learning analytics, predictive learning, digital learning, educational computing, educational informatics

Procedia PDF Downloads 477

Authors: Flavio Campos, Patricia Masmo, Fernanda Yamamoto

Abstract:

The report presents a research about teaching professional competencies through projects, considering the student as an active learner and curriculum development. Considering project based-learning, the report articulate the result of research about curriculum development for professional competencies and teaching-learning strategies to help the development of professional competencies in learning environments in the courses of National Learning Service in São Paulo, Brazil. There so, intend to demonstrate fundamentals to elaborate curriculum to learning environment, specific about teaching methodologies to enrich student-learning process, using projects. The practice that has been taking place since 2013 indicates the needs of rethinking knowledge and practice in courses that prepared students to labor.

Keywords: curriculum design, active learning, professional competencies, project based-learning

Procedia PDF Downloads 427

Authors: Aisultan Shoiynbek, Darkhan Kuanyshbay, Paulo Menezes, Akbayan Bekarystankyzy, Assylbek Mukhametzhanov, Temirlan Shoiynbek

Abstract:

Speech emotion recognition (SER) has received increasing research interest in recent years. It is a common practice to utilize emotional speech collected under controlled conditions recorded by actors imitating and artificially producing emotions in front of a microphone. There are four issues related to that approach: emotions are not natural, meaning that machines are learning to recognize fake emotions; emotions are very limited in quantity and poor in variety of speaking; there is some language dependency in SER; consequently, each time researchers want to start work with SER, they need to find a good emotional database in their language. This paper proposes an approach to create an automatic tool for speech emotion extraction based on facial emotion recognition and describes the sequence of actions involved in the proposed approach. One of the first objectives in the sequence of actions is the speech detection issue. The paper provides a detailed description of the speech detection model based on a fully connected deep neural network for Kazakh and Russian. Despite the high results in speech detection for Kazakh and Russian, the described process is suitable for any language. To investigate the working capacity of the developed model, an analysis of speech detection and extraction from real tasks has been performed.

Keywords: deep neural networks, speech detection, speech emotion recognition, Mel-frequency cepstrum coefficients, collecting speech emotion corpus, collecting speech emotion dataset, Kazakh speech dataset

Procedia PDF Downloads 26

Authors: Ting Lu, Ya-Ru Diao, Fei Fan, Ye Xue, Lei Shi, Xian-e Tang, Meng-jun Zhan, Zhen-hua Deng

Abstract:

Accurate adult age estimation (AAE) is a significant and challenging task in forensic and archeology fields. Attempts have been made to explore optimal adult age metrics, and the rib is considered a potential age marker. The traditional way is to extract age-related features designed by experts from macroscopic or radiological images followed by classification or regression analysis. Those results still have not met the high-level requirements for practice, and the limitation of using feature design and manual extraction methods is loss of information since the features are likely not designed explicitly for extracting information relevant to age. Deep learning (DL) has recently garnered much interest in imaging learning and computer vision. It enables learning features that are important without a prior bias or hypothesis and could be supportive of AAE. This study aimed to develop DL models for AAE based on CT images and compare their performance to the manual visual scoring method. Chest CT data were reconstructed using volume rendering (VR). Retrospective data of 2500 patients aged 20.00-69.99 years were obtained between December 2019 and September 2021. Five-fold cross-validation was performed, and datasets were randomly split into training and validation sets in a 4:1 ratio for each fold. Before feeding the inputs into networks, all images were augmented with random rotation and vertical flip, normalized, and resized to 224×224 pixels. ResNeXt was chosen as the DL baseline due to its advantages of higher efficiency and accuracy in image classification. Mean absolute error (MAE) was the primary parameter. Independent data from 100 patients acquired between March and April 2022 were used as a test set. The manual method completely followed the prior study, which reported the lowest MAEs (5.31 in males and 6.72 in females) among similar studies. CT data and VR images were used. The radiation density of the first costal cartilage was recorded using CT data on the workstation. The osseous and calcified projections of the 1 to 7 costal cartilages were scored based on VR images using an eight-stage staging technique. According to the results of the prior study, the optimal models were the decision tree regression model in males and the stepwise multiple linear regression equation in females. Predicted ages of the test set were calculated separately using different models by sex. A total of 2600 patients (training and validation sets, mean age=45.19 years±14.20 [SD]; test set, mean age=46.57±9.66) were evaluated in this study. Of ResNeXt model training, MAEs were obtained with 3.95 in males and 3.65 in females. Based on the test set, DL achieved MAEs of 4.05 in males and 4.54 in females, which were far better than the MAEs of 8.90 and 6.42 respectively, for the manual method. Those results showed that the DL of the ResNeXt model outperformed the manual method in AAE based on CT reconstruction of the costal cartilage and the developed system may be a supportive tool for AAE.

Keywords: forensic anthropology, age determination by the skeleton, costal cartilage, CT, deep learning

Procedia PDF Downloads 73

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: 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 512

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 133

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 355

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: 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: 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: Valentina Zhang

Abstract:

While facial expression is a complex and individualized behavior, all facial emotion recognition (FER) systems known to us rely on a single facial representation and are trained on universal data. We conjecture that: (i) different facial representations can provide different, sometimes complementing views of emotions; (ii) when employed collectively in a discussion group setting, they enable more accurate emotion reading which is highly desirable in autism care and other applications context sensitive to errors. In this paper, we first study FER using pixel-based DL vs semantics-based DL in the context of deepfake videos. Our experiment indicates that while the semantics-trained model performs better with articulated facial feature changes, the pixel-trained model outperforms on subtle or rare facial expressions. Armed with these findings, we have constructed an adaptive FER system learning from both types of models for dyadic or small interacting groups and further leveraging the synthesized group emotions as the ground truth for individualized FER training. Using a collection of group conversation videos, we demonstrate that FER accuracy and personalization can benefit from such an approach.

Keywords: neurodivergence care, facial emotion recognition, deep learning, ground truth for supervised learning

Procedia PDF Downloads 147

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 194

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