scholarly journals Fuzzy Cross Domain Concept Mining

2019 ◽  
Vol 8 (10S) ◽  
pp. 326-333
Keyword(s):  
Semantic Similarity ◽  
Concept Maps ◽  
Information Gain ◽  
Learning Algorithm ◽  
Concept Map ◽  
Research Area ◽  
Unstructured Data ◽  
Concept Mining ◽  
Novel Approach ◽  
E Learning

E-Learning has emerged as an important research area. Concept maps creation for emerging new domains such as e-Learning is even more challenging due to its ongoing development nature. For creating Concept map, concepts are extracted. Concepts are domain dependent but big data can have data from different domains. Data in different domain has different semantics. So before applying any analytics to such big unstructured data, we have to categorize the important concepts domain wise semantically before applying any machine learning algorithm. In this paper, we have used a novel approach to automatically cluster the E-Learning concept semantically; we have shown the cluster in table format. Initially, we have extracted important concepts from unstructured data followed by generation of vector space of each concept. Then we used different similarity formula to calculate fuzzy membership values of elements of vector to its corresponding concepts. Semantic Similarity is calculated between two concepts by considering repeatedly the semantic similarity or information gain between two elements of each vector. Then Semantic similarity between two concepts is calculated. Thus concept map can be generated for a particular domain. We have taken research articles as our dataset from different domains like computer science and medical domain containing articles on Cancer. A graph is generated to show that fuzzy relationship between them for all domain. Then clustering them in based on their distances

Exploring Semiotic Approaches to Analysing Multidimensional Concept Maps Using Methods that Value Collaboration

2010 ◽  
pp. 256-282 ◽  
Author(s):  
Christina J. Preston
Keyword(s):  
Professional Learning ◽  
Concept Maps ◽  
Concept Map ◽  
Assessment Process ◽  
Multimodal Literacy ◽  
Equal Importance ◽  
E Learning ◽  
Collaborative Engagement ◽  
One Year ◽  
Multidimensional Concept

This chapter focuses on teachers’ multidimensional concept mapping data collected at the beginning and end of a one-year Masters level course about e-learning. A multidimensional concept map (MDCM) defines any concept map that is multimodal, multimedia, multilayered and/or multi-authored. The teachers’ personal and professional learning priorities are analysed using two semiotic methods: the first is a traditional analysis of the words used to label the nodes; the second is an innovative analysis method that treats the whole map as a semiotic artefact, in which all the elements, including the words, have equal importance. The findings suggest that these tools offer deep insights into the learning priorities of individuals and groups, especially the affective and motivational factors. The teachers, as co-researchers, also adopted MDCM to underpin collaborative thinking. These research tools can be used in the assessment process to value multimodal literacy and collaborative engagement in new knowledge construction.

AUTONOMOUS BEHAVIORS OF GRAPHICAL AVATARS BASED ON MACHINE LEARNING

2012 ◽  
Vol 26 (02) ◽  
pp. 1251002
Author(s):  
YUESHENG HE ◽  
YUAN YAN TANG
Keyword(s):  
Machine Learning ◽  
Hierarchical Structure ◽  
Learning Algorithm ◽  
Three Dimensional ◽  
Research Area ◽  
Machine Learning Techniques ◽  
3D Animation ◽  
Graphical Environment ◽  
Novel Approach ◽  
The Difference

Graphical avatars have gained popularity in many application domains such as three-dimensional (3D) animation movies and animated simulations for product design. However, the methods to edit avatars' behaviors in the 3D graphical environment remained to be a challenging research topic. Since the hand-crafted methods are time-consuming and inefficient, the automatic actions of the avatars are required. To achieve the autonomous behaviors of the avatars, artificial intelligence should be used in this research area. In this paper, we present a novel approach to construct a system of automatic avatars in the 3D graphical environments based on the machine learning techniques. Specific framework is created for controlling the behaviors of avatars, such as classifying the difference among the environments and using hierarchical structure to describe these actions. Because of the requirement of simulating the interactions between avatars and environments after the classification of the environment, Reinforcement Learning is used to compute the policy to control the avatar intelligently in the 3D environment for the solution of the problem of different situations. Thus, our approach has solved problems such as where the levels of the missions will be defined and how the learning algorithm will be used to control the avatars. In this paper, our method to achieve these goals will be presented. The main contributions of this paper are presenting a hierarchical structure to control avatars automatically, developing a method for avatars to recognize environment and presenting an approach for making the policy of avatars' actions intelligently.

scholarly journals A Random Forest Model for the Prediction of FOG Content in Inlet Wastewater from Urban WWTPs

Water ◽  
2021 ◽  
Vol 13 (9) ◽  
pp. 1237
Author(s):  
Vanesa Mateo Pérez ◽  
José Manuel Mesa Fernández ◽  
Joaquín Villanueva Balsera ◽  
Cristina Alonso Álvarez
Keyword(s):  
Random Forest ◽  
Wastewater Treatment Plants ◽  
Learning Algorithm ◽  
Global Improvement ◽  
Treatment Processes ◽  
Early Adoption ◽  
Novel Approach ◽  
Number Of Factors ◽  
Initial Stage ◽  
Correct Design

The content of fats, oils, and greases (FOG) in wastewater, as a result of food preparation, both in homes and in different commercial and industrial activities, is a growing problem. In addition to the blockages generated in the sanitary networks, it also represents a difficulty for the performance of wastewater treatment plants (WWTP), increasing energy and maintenance costs and worsening the performance of downstream treatment processes. The pretreatment stage of these facilities is responsible for removing most of the FOG to avoid these problems. However, so far, optimization has been limited to the correct design and initial installation dimensioning. Proper management of this initial stage is left to the experience of the operators to adjust the process when changes occur in the characteristics of the wastewater inlet. The main difficulty is the large number of factors influencing these changes. In this work, a prediction model of the FOG content in the inlet water is presented. The model is capable of correctly predicting 98.45% of the cases in training and 72.73% in testing, with a relative error of 10%. It was developed using random forest (RF) and the good results obtained (R2 = 0.9348 and RMSE = 0.089 in test) will make it possible to improve operations in this initial stage. The good features of this machine learning algorithm had not been used, so far, in the modeling of pretreatment parameters. This novel approach will result in a global improvement in the performance of this type of facility allowing early adoption of adjustments to the pretreatment process to remove the maximum amount of FOG.

scholarly journals Optimization of Rocky Desertification Classification Model Based on Vegetation Type and Seasonal Characteristic

2021 ◽  
Vol 13 (15) ◽  
pp. 2935
Author(s):  
Chunhua Qian ◽  
Hequn Qiang ◽  
Feng Wang ◽  
Mingyang Li
Keyword(s):  
Learning Algorithm ◽  
Vegetation Type ◽  
Research Area ◽  
Classification Model ◽  
Guizhou Province ◽  
Model Accuracy ◽  
Spatiotemporal Evolution ◽  
Rocky Desertification ◽  
The North ◽  
Svm Model

Building a high-precision, stable, and universal automatic extraction model of the rocky desertification information is the premise for exploring the spatiotemporal evolution of rocky desertification. Taking Guizhou province as the research area and based on MODIS and continuous forest inventory data in China, we used a machine learning algorithm to build a rocky desertification model with bedrock exposure rate, temperature difference, humidity, and other characteristic factors and considered improving the model accuracy from the spatial and temporal dimensions. The results showed the following: (1) The supervised classification method was used to build a rocky desertification model, and the logical model, RF model, and SVM model were constructed separately. The accuracies of the models were 73.8%, 78.2%, and 80.6%, respectively, and the kappa coefficients were 0.61, 0.672, and 0.707, respectively. SVM performed the best. (2) Vegetation types and vegetation seasonal phases are closely related to rocky desertification. After combining them, the model accuracy and kappa coefficient improved to 91.1% and 0.861. (3) The spatial distribution characteristics of rocky desertification in Guizhou are obvious, showing a pattern of being heavy in the west, light in the east, heavy in the south, and light in the north. Rocky desertification has continuously increased from 2001 to 2019. In conclusion, combining the vertical spatial structure of vegetation and the differences in seasonal phase is an effective method to improve the modeling accuracy of rocky desertification, and the SVM model has the highest rocky desertification classification accuracy. The research results provide data support for exploring the spatiotemporal evolution pattern of rocky desertification in Guizhou.

Evaluation of Semantic Fisheye Zooming to Provide Focus+Context

2007 ◽  
Vol 51 (5) ◽  
pp. 459-463
Author(s):  
Andrew J. Afram ◽  
John Briedis ◽  
Daisuke Fujiwara ◽  
Robert J.K. Jacob ◽  
Caroline G.L. Cao ◽  
...  
Keyword(s):  
Concept Maps ◽  
User Study ◽  
Concept Map ◽  
Digital Display ◽  
Individual Concepts ◽  
Semantic Zooming ◽  
Zoom In

A concept map is a diagram that consists of nodes that contain individual concepts or pieces of information. These nodes are connected by lines that represent relationships between the information. Large concept maps are difficult to explore and navigate using current digital display interfaces. As users zoom in on a desired node, connections between the node of interest and surrounding nodes become hidden from the user. A combination of fisheye zooming and semantic zooming mechanisms to maintain the visual connections between the nodes was implemented, and a user study to determine whether this technique helps users learn from the map was conducted. The user study revealed that participants were able to recall more information presented in a concept map, with practically no difference in the amount of time spent using the map, despite the novelty of the semantic fisheye interface.

scholarly journals Real-Time AI-Based Informational Decision-Making Support System Utilizing Dynamic Text Sources

2021 ◽  
Vol 11 (13) ◽  
pp. 6237
Author(s):  
Azharul Islam ◽  
KyungHi Chang
Keyword(s):  
Machine Learning ◽  
Decision Making ◽  
Random Forest ◽  
Support System ◽  
Classification Accuracy ◽  
Short Term Memory ◽  
Learning Algorithm ◽  
Unstructured Data ◽  
Stochastic Gradient Descent ◽  
Decision Making Support

Unstructured data from the internet constitute large sources of information, which need to be formatted in a user-friendly way. This research develops a model that classifies unstructured data from data mining into labeled data, and builds an informational and decision-making support system (DMSS). We often have assortments of information collected by mining data from various sources, where the key challenge is to extract valuable information. We observe substantial classification accuracy enhancement for our datasets with both machine learning and deep learning algorithms. The highest classification accuracy (99% in training, 96% in testing) was achieved from a Covid corpus which is processed by using a long short-term memory (LSTM). Furthermore, we conducted tests on large datasets relevant to the Disaster corpus, with an LSTM classification accuracy of 98%. In addition, random forest (RF), a machine learning algorithm, provides a reasonable 84% accuracy. This research’s main objective is to increase the application’s robustness by integrating intelligence into the developed DMSS, which provides insight into the user’s intent, despite dealing with a noisy dataset. Our designed model selects the random forest and stochastic gradient descent (SGD) algorithms’ F1 score, where the RF method outperforms by improving accuracy by 2% (to 83% from 81%) compared with a conventional method.

scholarly journals An Advanced Educational Tool for Digital Forensic Engineering

2016 ◽  
Vol 11 (03) ◽  
pp. 15 ◽  
Author(s):  
Primož Cigoj ◽  
Borka Jerman Blažič
Keyword(s):  
Digital Forensics ◽  
Real Life ◽  
University Education ◽  
Educational Tool ◽  
Digital Tool ◽  
College And University ◽  
Novel Approach ◽  
Wide Range ◽  
E Learning ◽  
Forensic Engineering

This paper presents a novel approach to education in the area of digital forensics based on a multi-platform cloud-computer infrastructure and an innovative computer based tool. The tool is installed and available through the cloud-based infrastructure of the Dynamic Forensic Education Alliance. Cloud computing provides an efficient mechanism for a wide range of services that offer real-life environments for teaching and training cybersecurity and digital forensics. The cloud-based infrastructure, the virtualized environment and the developed educational tool enable the construction of a dynamic e-learning environment making the training very close to reality and to real-life situations. The paper presents the Dynamic Forensic Digital tool named EduFors and describes the different levels of college and university education where the tool is introduced and used in the training of future investigators of cybercrime events.

Enhancing students' HOTS in laboratory educational activity by using concept map as an alternative assessment tool

2017 ◽  
Vol 18 (4) ◽  
pp. 849-874 ◽  
Author(s):  
I. B. A. Ghani ◽  
N. H. Ibrahim ◽  
N. A. Yahaya ◽  
J. Surif
Keyword(s):  
Alternative Assessment ◽  
Concept Maps ◽  
Assessment Tool ◽  
Concept Map ◽  
Thinking Skills ◽  
Learning Activities ◽  
Educational Activity ◽  
Chemistry Laboratory ◽  
Mapping Technique ◽  
Laboratory Learning

Educational transformation in the 21st century demands in-depth knowledge and understanding in order to promote the development of higher-order thinking skills (HOTS). However, the most commonly reported problem with respect to developing a knowledge of chemistry is poor mastery of basic concepts. Chemistry laboratory educational activities are shown to be less effective in developing an optimum conceptual understanding and HOTS among students. One factor is a lack of effective assessment and evaluation tools. Therefore, the primary focus of this study is to explore concept maps as an assessment tool in order to move students' thinking skills to a higher level during laboratory learning activities. An embedded mixed method design is used in this study, which has also employed a pre-experimental research design. This design triangulates quantitative and qualitative data, which are combined to strengthen the findings. A low-directed concept mapping technique, convergence scoring method, and pre-post laboratory concept map were used in this study. An electrolysis HOTS test was used as the research instrument in order to measure the level of student achievement with respect to high-level questions. In addition, the thought process that is involved when students construct concept maps has been explored and studied in detail by utilising a think-aloud protocol. Results showed a positive development towards understanding and higher level thinking skills in students with respect to electrolysis concepts learned through chemistry laboratory activities. An investigation of the students' thinking processes showed that high-achieving students were more capable of giving a content-based explanation of electrolysis and engaged in monitoring activities more often while building a concept map. Nonetheless, all categories of students managed to show a positive increase in the activities of explanation and monitoring during the construction of concept maps after they were exposed to the assessment tool in the laboratory learning activities. In conclusion, the assessment activity using concept maps in laboratory learning activities has a positive impact on students' understanding and stimulates students to increase their HOTS.

scholarly journals КОНЦЕПТ-КАРТА ЯК ДІЄВИЙ ЗАСІБ НАВЧАННЯ ІНОЗЕМНОЇ МОВИ

2020 ◽  
Vol 15 ◽  
pp. 22-25
Author(s):  
Nataliia Borysova
Keyword(s):  
Foreign Language ◽  
Teaching And Learning ◽  
Concept Maps ◽  
Concept Map ◽  
Hierarchical Organization ◽  
Conceptual Mapping ◽  
Approximate Description ◽  
The Difference ◽  
Mind Maps

The article reveals the concept of conceptual mapping in the process of learning a foreign language. It is stated that a concept map is a diagram that shows the relationships between notions. Such maps are graphical tools for organizing and presenting knowledge. It is emphasized that the most useful form of a concept map for teaching and learning is one that is placed in a hierarchical organization, where more general and comprehensive notions are at the top of the map and more specific at the bottom. The difference between concert cards and mind maps is given. It is emphasized that despite a similarity of mind maps and concept maps, these two methods differ in many respects, in particular, concept maps are characterized by clear links between the described ideas and are more structured than mind maps, as a formally approximate description, which places ideas in some sequence and organizes them hierarchically by levels of importance.

Sign in / Sign up

Export Citation Format

Share Document