Search results for: task based learning.

Authors: Peter A. Bibby

Abstract:

Research has suggested that implicit learning tasks may rely on episodic processing to generate above chance performance on the standard classification tasks. The current research examines the invariant features task (McGeorge and Burton, 1990) and argues that such episodic processing is indeed important. The results of the experiment suggest that both rejection and similarity strategies are used by participants in this task to simultaneously reject unfamiliar items and to accept (falsely) familiar items. Primarily these decisions are based on the presence of low or high frequency goal based features of the stimuli presented in the incidental learning phase. It is proposed that a goal based analysis of the incidental learning task provides a simple step in understanding which features of the episodic processing are most important for explaining the match between incidental, implicit learning and test performance.

Keywords: Episodic processing, incidental learning, implicitlearning, invariant learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1437

Authors: Bekim Fetaji, Majlinda Fetaji

Abstract:

The development and use of mobile devices as well as its integration within education systems to deliver electronic contents and to support real-time communications was the focus of this research. In order to investigate the software engineering issues in using mobile devices a research on electronic content was initiated. The Developed MP3 mobile software solution was developed as a prototype for testing and developing a strategy for designing a usable m-learning environment. The mobile software solution was evaluated using mobile device using the link: http://projects.seeu.edu.mk/mlearn. The investigation also tested the correlation between the two mobile learning indicators: electronic content and attention, based on the Task Based learning instructional method. The mobile software solution ''M-Learn“ was developed as a prototype for testing the approach and developing a strategy for designing usable m-learning environment. The proposed methodology is about what learning modeling approach is more appropriate to use when developing mobile learning software.

Keywords: M-learning, mobile software development, mobiledevices, learning instructions, task based learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1643

Authors: Fiseha M. Guangul, Annissa Muhammed, Aja O. Chikere

Abstract:

Group task is one method to create the conducive environment for the active teaching-learning process. Performing group task with active involvement of students will benefit the students in many ways. However, in most cases all students do not participate actively in the group task, and hence the intended benefits are not acquired. This paper presents the improvements of students’ participation in the group task and learning from the group task by introducing different techniques to enhance students’ participation. For the purpose of this research Carpentry and Joinery II (WT-392) course from Wood Technology Department at Adama Science and Technology University was selected, and five groups were formed. Ten group tasks were prepared and the first five group tasks were distributed to the five groups in the first day without introducing the techniques that are used to enhance participation of students in the group task. On another day, the other five group tasks were distributed to the same groups and various techniques were introduced to enhance students’ participation in the group task. The improvements of students’ learning from the group task after the implementation of the techniques. After implementing the techniques the evaluation showed that significant improvements were obtained in the students’ participation and learning from the group task.

Keywords: Active learning, evaluation method, group task, students participation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 748

Authors: Majlinda Fetaji, Alajdin Abazi, Zamir Dika, Bekim Fetaji

Abstract:

The assessment of the efficacy of devised Mobile- Assisted Instructional Modes in Mobile Learning was the focus of this research. The study adopted pre-test, post-test, control group quasi-experimental design. Research instruments were developed, validated and used for collecting data. Findings revealed that the students exposed to Mobile Task Based Learning Mode (MTBLM) in using Mobile-Assisted Instruction (MAI) performed significantly better. The implication of these findings is that, the Audio tutorial and Practice Mode (ATPM) (Stimulus instruments) of MAI had been found better over the other modes used in the study.

Keywords: Mobile-Assisted instructions, Mobile learning, learning instructions, task based learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1572

Authors: Endrick Barnacin, Jean-Luc Henry, Jimmy Nagau, Jack Molinié

Abstract:

Palynology is a field of interest in many disciplines due to its multiple applications: chronological dating, climatology, allergy treatment, and honey characterization. Unfortunately, the analysis of a pollen slide is a complicated and time consuming task that requires the intervention of experts in the field, which are becoming increasingly rare due to economic and social conditions. In this context, the automation of this task is urgent. In this work, we compare classical feature extraction methods (Shape, GLCM, LBP, and others) and Deep Learning (CNN and Transfer Learning) to perform a recognition task over 80 regional pollen species. It has been found that the use of Transfer Learning seems to be more precise than the other approaches.

Keywords: Image segmentation, stuck particles separation, Sobel operator, thresholding.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 201

Authors: Dejanira Araiza-Illan, Tony J. Dodd

Abstract:

A novel biologically inspired controller for the autonomous navigation of a mobile robot in an evasion task is proposed. The controller takes advantage of the environment by calculating a measure of danger and subsequently choosing the parameters of a reinforcement learning based decision process. Two different reinforcement learning algorithms were used: Qlearning and Sarsa (λ). Simulations show that selecting dynamic parameters reduce the time while executing the decision making process, so the robot can obtain a policy to succeed in an escaping task in a realistic time.

Keywords: Autonomous navigation, mobile robots, reinforcement learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1480

Authors: Arun Prasad Jaganathan

Abstract:

In today's dynamic industrial world, traditional task allocation methods often fall short in adapting to evolving operational conditions. This paper presents an AI-enabled task assistance and management system designed to overcome the limitations of conventional approaches. By using artificial intelligence (AI) and machine learning (ML), the system intelligently interprets user instructions, analyzes tasks, and allocates resources based on real-time data and environmental factors. Additionally, geolocation tracking enables proactive identification of potential delays, ensuring timely interventions. With its transparent reporting mechanisms, the system provides stakeholders with clear insights into task progress, fostering accountability and informed decision-making. The paper presents a comprehensive overview of the system architecture, algorithm, and implementation, highlighting its potential to revolutionize task management across diverse industries.

Keywords: Artificial intelligence, machine learning, task allocation, operational efficiency, resource optimization.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 75

Authors: Costin Pribeanu, Rytis Vilkonis, Dragoş Daniel Iordache

Abstract:

User interaction components of Augmented Reality (AR) systems have to be tested with users in order to find and fix usability problems as early as possible. In this paper we will report on a user-centered design approach for AR systems following the experience acquired during the design and evaluation of a software prototype for an AR-based educational platform. In this respect we will focus on the re-design of the user task based on the results from a formative usability evaluation. The basic idea of our approach is to describe task scenarios in a tabular format, to develop a task model in a task modeling environment and then to simulate the execution.

Keywords: AR-based educational systems, task-based design, usability evaluation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2485

Authors: Sherry S. Herron, Douglas Magomo, Paula Gossard

Abstract:

In this article, we discuss project-based learning in the context of a wheel garden as an instructional tool in science and mathematics education. A wheel garden provides multiple opportunities to teach across the curriculum, to integrate disciplines, and to promote community involvement. Grounded in the theoretical framework of constructivism, the wheel garden provides a multidisciplined educational tool that provides a hands-on, non-traditional arena for learning. We will examine some of the cultural, art, science, and mathematics connections made with this project.

Keywords: Art education, cross-curriculum instruction, multicultural education, project-based learning, school gardens, task based learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2835

Authors: Jian-Wei Li, Yao-Tien Wang, Yi-Chun Chang

Abstract:

Cooperative learning has been defined as learners working together as a team to solve a problem to complete a task or to accomplish a common goal, which emphasizes the importance of interactions among members to promote the whole learning performance. With the popularity of society networks, cooperative learning is no longer limited to traditional classroom teaching activities. Since society networks facilitate to organize online learners, to establish common shared visions, and to advance learning interaction, the online community and online learning community have triggered the establishment of web-based societies. Numerous research literatures have indicated that the collaborative learning community is a critical issue to enhance learning performance. Hence, this paper proposes a learning community recommendation approach to facilitate that a learner joins the appropriate learning communities, which is based on k-nearest neighbor (kNN) classification. To demonstrate the viability of the proposed approach, the proposed approach is implemented for 117 students to recommend learning communities. The experimental results indicate that the proposed approach can effectively recommend appropriate learning communities for learners.

Keywords: k-nearest neighbor classification, learning community, Cooperative/Collaborative Learning and Environments.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1905

Authors: T. C. Manjunath, C. Ardil

Abstract:

This paper deals with the design and the implementation of an automatic task planner for a robot, irrespective of whether it is a stationary robot or a mobile robot. The aim of the task planner nothing but, they are planning systems which are used to plan a particular task and do the robotic manipulation. This planning system is embedded into the system software in the computer, which is interfaced to the computer. When the instructions are given using the computer, this is transformed into real time application using the robot. All the AI based algorithms are written and saved in the control software, which acts as the intelligent task planning system.

Keywords: AI, Robot, Task Planner, RT, Algorithm, Specs, Controller.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 620

Authors: Sandra Baßler, Peter Dünow, Mathias Marquardt

Abstract:

A Fourier series based learning control (FSBLC) algorithm for tracking trajectories of mechanical systems with unknown nonlinearities is presented. Two processes are introduced to which the FSBLC with PD controller is applied. One is a simplified service robot capable of climbing stairs due to special wheels and the other is a propeller driven pendulum with nearly the same requirements on control. Additionally to the investigation of learning the feed forward for the desired trajectories some considerations on the implementation of such an algorithm on low cost microcontroller hardware are made. Simulations of the service robot as well as practical experiments on the pendulum show the capability of the used FSBLC algorithm to perform the task of improving control behavior for repetitive task of such mechanical systems.

Keywords: Climbing stairs, FSBLC, ILC, Service robot.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1376

Authors: Nobue T. Ellis

Abstract:

This preliminary study attempts to see if a learning environment influences instructor’s teaching strategies and learners’ in-class activities in a foreign language class at a university in Japan. The class under study was conducted in a computer room, while the majority of classes of the same course were offered in traditional classrooms without computers. The study also sees if the unplanned blended learning environment, enhanced, or worked against, in achieving course goals, by paying close attention to in-class artefacts, such as computers. In the macro-level analysis, the course syllabus and weekly itinerary of the course were looked at; and in the microlevel analysis, nonhuman actors in their environments were named and analyzed to see how they influenced the learners’ task processes. The result indicated that students were heavily influenced by the presence of computers, which lead them to disregard some aspects of intended learning objectives.

Keywords: Computer-assisted language learning, actor-network theory, English as a foreign language, task-based teaching.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1610

Authors: Simon Thiel, Stavros Dalakakis, Dieter Roller

Abstract:

This paper outlines the development of a learning retrieval agent. Task of this agent is to extract knowledge of the Active Semantic Network in respect to user-requests. Based on a reinforcement learning approach, the agent learns to interpret the user-s intention. Especially, the learning algorithm focuses on the retrieval of complex long distant relations. Increasing its learnt knowledge with every request-result-evaluation sequence, the agent enhances his capability in finding the intended information.

Keywords: Reinforcement learning, learning retrieval agent, search in semantic networks.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1494

Authors: Mia Sorensen

Abstract:

The introduction of haptic elements in a graphic user interfaces are becoming more widespread. Since haptics are being introduced rapidly into computational tools, investigating how these models affect Human-Computer Interaction would help define how to integrate and model new modes of interaction. The interest of this paper is to discuss and investigate the issues surrounding Haptic and Graphic User Interface designs (GUI) as separate systems, as well as understand how these work in tandem. The development of these systems is explored from a psychological perspective, based on how usability is addressed through learning and affordances, defined by J.J. Gibson. Haptic design can be a powerful tool, aiding in intuitive learning. The problems discussed within the text is how can haptic interfaces be integrated within a GUI without the sense of frivolity. Juxtaposing haptics and Graphic user interfaces has issues of motivation; GUI tends to have a performatory process, while Haptic Interfaces use affordances to learn tool use. In a deeper view, it is noted that two modes of perception, foveal and ambient, dictate perception. These two modes were once thought to work in tandem, however it has been discovered that these processes work independently from each other. Foveal modes interpret orientation is space which provide for posture, locomotion, and motor skills with variations of the sensory information, which instructs perceptions of object-task performance. It is contended, here, that object-task performance is a key element in the use of Haptic Interfaces because exploratory learning uses affordances in order to use an object, without meditating an experience cognitively. It is a direct experience that, through iteration, can lead to skill-sets. It is also indicated that object-task performance will not work as efficiently without the use of exploratory or kinesthetic learning practices. Therefore, object-task performance is not as congruently explored in GUI than it is practiced in Haptic interfaces.

Keywords: Affordances, Graphic User Interface, HapticInterfaces, Tool-Use, Object-Naming, Object-Task Performance

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1752

Authors: Nouha Khediri, Mohammed Ben Ammar, Monji Kherallah

Abstract:

Recently, facial emotion recognition (FER) has become increasingly essential to understand the state of the human mind. However, accurately classifying emotion from the face is a challenging task. In this paper, we present a facial emotion recognition approach named CV-FER benefiting from deep learning, especially CNN and VGG16. First, the data are pre-processed with data cleaning and data rotation. Then, we augment the data and proceed to our FER model, which contains five convolutions layers and five pooling layers. Finally, a softmax classifier is used in the output layer to recognize emotions. Based on the above contents, this paper reviews the works of facial emotion recognition based on deep learning. Experiments show that our model outperforms the other methods using the same FER2013 database and yields a recognition rate of 92%. We also put forward some suggestions for future work.

Keywords: CNN, deep-learning, facial emotion recognition, machine learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 710

Authors: Fabio Fabris, Alex A. Freitas

Abstract:

Hierarchical classification is a special type of classification task where the class labels are organised into a hierarchy, with more generic class labels being ancestors of more specific ones. Meta-learning for classification-algorithm recommendation consists of recommending to the user a classification algorithm, from a pool of candidate algorithms, for a dataset, based on the past performance of the candidate algorithms in other datasets. Meta-learning is normally used in conventional, non-hierarchical classification. By contrast, this paper proposes a meta-learning approach for more challenging task of hierarchical classification, and evaluates it in a large number of bioinformatics datasets. Hierarchical classification is especially relevant for bioinformatics problems, as protein and gene functions tend to be organised into a hierarchy of class labels. This work proposes meta-learning approach for recommending the best hierarchical classification algorithm to a hierarchical classification dataset. This work’s contributions are: 1) proposing an algorithm for splitting hierarchical datasets into new datasets to increase the number of meta-instances, 2) proposing meta-features for hierarchical classification, and 3) interpreting decision-tree meta-models for hierarchical classification algorithm recommendation.

Keywords: Algorithm recommendation, meta-learning, bioinformatics, hierarchical classification.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1370

Authors: Saeed Mohammed Baneamoon, Rosalina Abdul Salam, Abdullah Zawawi Hj. Talib

Abstract:

Designing a simulated system and training it to optimize its tasks in simulated environment helps the designers to avoid problems that may appear when designing the system directly in real world. These problems are: time consuming, high cost, high errors percentage and low efficiency and accuracy of the system. The proposed system will investigate and improve the efficiency and accuracy of a simulated robot to choose correct behavior to perform its task. In this paper, machine learning, which uses genetic algorithm, is adopted. This type of machine learning is called genetic-based machine learning in which a distributed classifier system is used to improve the efficiency and accuracy of the robot. Consequently, it helps the robot to achieve optimal action.

Keywords: Machine Learning, Genetic-Based MachineLearning, Learning Classifier System, Behaviors.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1529

Authors: Zehra Sultan

Abstract:

The study is based on the Task-based Language Teaching (TBLT) approach which is found to be very effective in the EFL/ESL classroom. This approach engages learners to acquire the usage of authentic language skills by interacting with the real world through a sequence of pedagogical tasks. The use of technology enhances the effectiveness of this approach. This study throws light on the historical background of TBLT, and its efficacy in the EFL /ESL classroom. In addition, this study precisely talks about the implementation of this approach in the General Foundation Program (GFP) of Muscat College, Oman. It furnishes the list of the pedagogical tasks embedded in the language curriculum of the GFP which are skillfully allied to the College graduate attributes. Moreover, the study also discusses the challenges pertaining to this approach from the point of view of teachers, students and its classroom application. Additionally, the operational success of this methodology is gauged through formative assessments of the GFP which is apparent in the students’ progress.

Keywords: Task-based language teaching, authentic language, communicative approach, real world activities, ESL/EFL activities.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 954

Authors: C. Manjula, Lilly Florence

Abstract:

Software technology is developing rapidly which leads to the growth of various industries. Now-a-days, software-based applications have been adopted widely for business purposes. For any software industry, development of reliable software is becoming a challenging task because a faulty software module may be harmful for the growth of industry and business. Hence there is a need to develop techniques which can be used for early prediction of software defects. Due to complexities in manual prediction, automated software defect prediction techniques have been introduced. These techniques are based on the pattern learning from the previous software versions and finding the defects in the current version. These techniques have attracted researchers due to their significant impact on industrial growth by identifying the bugs in software. Based on this, several researches have been carried out but achieving desirable defect prediction performance is still a challenging task. To address this issue, here we present a machine learning based hybrid technique for software defect prediction. First of all, Genetic Algorithm (GA) is presented where an improved fitness function is used for better optimization of features in data sets. Later, these features are processed through Decision Tree (DT) classification model. Finally, an experimental study is presented where results from the proposed GA-DT based hybrid approach is compared with those from the DT classification technique. The results show that the proposed hybrid approach achieves better classification accuracy.

Keywords: Decision tree, genetic algorithm, machine learning, software defect prediction.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1465

Authors: Wei Hu, Tianzhou Chen, Qingsong Shi

Abstract:

In recent years, the development of e-learning is very rapid. E-learning is an attractive and efficient way for computer education. Student interaction and collaboration also plays an important role in e-learning. In this paper, a collaborative web-based e-learning environment is presented. A wide range of interactive and collaborative methods are integrated into a web-based environment. This e-learning environment is designed for information security curriculum.

Keywords: E-learning, information Security, curriculum, web-based environment.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1729

Authors: Costin Pribeanu

Abstract:

The model-based approach to user interface design relies on developing separate models capturing various aspects about users, tasks, application domain, presentation and dialog structures. This paper presents a task modeling approach for user interface design and aims at exploring mappings between task, domain and presentation models. The basic idea of our approach is to identify typical configurations in task and domain models and to investigate how they relate each other. A special emphasis is put on applicationspecific functions and mappings between domain objects and operational task structures. In this respect, we will address two layers in task decomposition: a functional (planning) layer and an operational layer.

Keywords: task modeling, user interface design, unit tasks, basic tasks, operational task model.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1878

Authors: Costin Pribeanu

Abstract:

The model-based approach to user interface design relies on developing separate models that are capturing various aspects about users, tasks, application domain, presentation and dialog representations. This paper presents a task modeling approach for user interface design and aims at exploring the mappings between task, domain and presentation models. The basic idea of our approach is to identify typical configurations in task and domain models and to investigate how they relate each other. A special emphasis is put on application-specific functions and mappings between domain objects and operational task structures. In this respect, we will distinguish between three layers in the task decomposition: a functional layer, a planning layer, and an operational layer.

Keywords: task modeling, user interface design, unit tasks, basic tasks, operational task model

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1594

Authors: Olaf Hallan Graven, Dag Andreas Hals Samuelsen

Abstract:

An implementation of a design for a game based virtual learning environment is described. The game is developed for a course in analogue electronics, and the topic is the design of a power supply. This task can be solved in a number of different ways, with certain constraints, giving the students a certain amount of freedom, although the game is designed not to facilitate trial-and error approach. The use of storytelling and a virtual gaming environment provides the student with the learning material in a MMORPG environment. The game is tested on a group of second year electrical engineering students with good results.

Keywords: analogue electronics, e-learning, computer games for learning, virtual reality

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1528

Authors: Rui Antunes

Abstract:

This article presents the implementation of several different e/b-Learning collaborative activities, used to improve the students learning process in an high school Polytechnic Institution. A new learning model arises, based on a combination between face-toface and distance leaning. Learning is now becoming centered with the development of collaborative activities, and its actors (teachers and students) have to be re-socialized to a new e/b-Learning paradigm. Measuring approaches are proposed for this model and results are presented, showing prospective correlation between students learning success and the use of online collaborative activities.

Keywords: e/b-Learning, Collaborative Learning, TeachingCommunities, Web-based Courseware

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1705

Authors: A. Nassiry, A. Kardan

Abstract:

According to development of communications and web-based technologies in recent years, e-Learning has became very important for everyone and is seen as one of most dynamic teaching methods. Grid computing is a pattern for increasing of computing power and storage capacity of a system and is based on hardware and software resources in a network with common purpose. In this article we study grid architecture and describe its different layers. In this way, we will analyze grid layered architecture. Then we will introduce a new suitable architecture for e-Learning which is based on grid network, and for this reason we call it Grid Learning Architecture. Various sections and layers of suggested architecture will be analyzed; especially grid middleware layer that has key role. This layer is heart of grid learning architecture and, in fact, regardless of this layer, e-Learning based on grid architecture will not be feasible.

Keywords: Distributed learning, Grid Learning, Grid network, SCORM standard.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1727

Authors: Wernhuar Tarng, Weichian Tsai

Abstract:

The major purpose of this study is to use network and multimedia technologies to build a game-based learning system for junior high school students to apply in learning “World Geography" through the “role-playing" game approaches. This study first investigated the motivation and habits of junior high school students to use the Internet and online games, and then designed a game-based learning system according to situated and game-based learning theories. A teaching experiment was conducted to analyze the learning effectiveness of students on the game-based learning system and the major factors affecting their learning. A questionnaire survey was used to understand the students- attitudes towards game-based learning. The results showed that the game-based learning system can enhance students- learning, but the gender of students and their habits in using the Internet have no significant impact on learning. Game experience has a significant impact on students- learning, and the higher the experience value the better the effectiveness of their learning. The results of questionnaire survey also revealed that the system can increase students- motivation and interest in learning "World Geography".

Keywords: Game-based learning, situated learning, role playing, learning effectiveness, learning motivation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2595

Authors: Samiah Alammari, Nassim Ammour

Abstract:

When providing a massive number of tasks successively to a deep learning process, a good performance of the model requires preserving the previous tasks data to retrain the model for each upcoming classification. Otherwise, the model performs poorly due to the catastrophic forgetting phenomenon. To overcome this shortcoming, we developed a successful continual learning deep model for remote sensing hyperspectral image regions classification. The proposed neural network architecture encapsulates two trainable subnetworks. The first module adapts its weights by minimizing the discrimination error between the land-cover classes during the new task learning, and the second module tries to learn how to replicate the data of the previous tasks by discovering the latent data structure of the new task dataset. We conduct experiments on hyperspectral image (HSI) dataset on Indian Pines. The results confirm the capability of the proposed method.

Keywords: Continual learning, data reconstruction, remote sensing, hyperspectral image segmentation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 232

Authors: Varun Gupta, Ankit Pandey

Abstract:

Crude oil market is an immensely complex and dynamic environment and thus the task of predicting changes in such an environment becomes challenging with regards to its accuracy. A number of approaches have been adopted to take on that challenge and machine learning has been at the core in many of them. There are plenty of examples of algorithms based on machine learning yielding satisfactory results for such type of prediction. In this paper, we have tried to predict crude oil prices using Long Short-Term Memory (LSTM) based recurrent neural networks. We have tried to experiment with different types of models using different epochs, lookbacks and other tuning methods. The results obtained are promising and presented a reasonably accurate prediction for the price of crude oil in near future.

Keywords: Crude oil price prediction, deep learning, LSTM, recurrent neural networks.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3712

Authors: Ekachai Phaisangittisagul, Rapeepol Chongprachawat

Abstract:

Obtaining labeled data in supervised learning is often difficult and expensive, and thus the trained learning algorithm tends to be overfitting due to small number of training data. As a result, some researchers have focused on using unlabeled data which may not necessary to follow the same generative distribution as the labeled data to construct a high-level feature for improving performance on supervised learning tasks. In this paper, we investigate the impact of the relationship between unlabeled and labeled data for classification performance. Specifically, we will apply difference unlabeled data which have different degrees of relation to the labeled data for handwritten digit classification task based on MNIST dataset. Our experimental results show that the higher the degree of relation between unlabeled and labeled data, the better the classification performance. Although the unlabeled data that is completely from different generative distribution to the labeled data provides the lowest classification performance, we still achieve high classification performance. This leads to expanding the applicability of the supervised learning algorithms using unsupervised learning.

Keywords: Autoencoder, high-level feature, MNIST dataset, selftaught learning, supervised learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1832