In order to predict the crime in YD county, datamining and machinelearning are used in this paper. the aim of the study is to show the pattern and rate of crime in YD county based on the data collected and to show t...
详细信息
datamining in education is a developing interdisciplinary research field also known as educational datamining (EDM). the goal is to understand students' learning process and identify the way by which they can le...
详细信息
ISBN:
(纸本)9781728107882
datamining in education is a developing interdisciplinary research field also known as educational datamining (EDM). the goal is to understand students' learning process and identify the way by which they can learn to improve educational outcomes. learning using IT is one of the most widely used methods for education in modern days. Digital learning gives students an experience of individual learning at any time as well as anywhere, so students get more interest, flexibility at learning. Knowing the preferences of students learning will help the instructors to design better learning materials and teaching styles. We have surveyed on the students of undergraduate level and evaluated the students in three categories: good, average and excellent. We have used four classification models: Support Vector machine (SVM), Logistic Regression (LR), Decision Tree and Random Forest (RF) model to predict the performance of students on basis of the impact of IT and other study mediums based on their results. In this article, we have identified different parameters or features from five different learning sectors or fields which can give an impact on the student's learning process. So, we have processed in a way that will find out the datamining model which can give better accuracy of student's performance and also can find out which parameters or features among the five fields are playing a great role in their academic results. Moreover, we can apply these features by inspiring good or average students to improve their learning process.
Our work is focused on determining whether any correlation exists between preparatory classes taken by Electrical Engineering (EE) students at Eastern Washington University (EWU) early in their academic careers (e.g. ...
详细信息
ISBN:
(纸本)9781728107882
Our work is focused on determining whether any correlation exists between preparatory classes taken by Electrical Engineering (EE) students at Eastern Washington University (EWU) early in their academic careers (e.g. Calculus and Physics sequences) and their departmental GPAs upon graduation. Using academic data from prior EE graduates, a machinelearning algorithm was trained to predict with85% certainty whether a student's GPA will fall above/below one standard deviation from the mean. this prediction can be used to channel university resources to support those students who need it the most. However, there is a significant prediction overlap for average students, i.e. those who fall within approximately one standard deviation around the mean. It is our conjecture that incorporating more major-specific data (e.g. grades in a set of core introductory level departmental courses) or a customized general aptitude test administered at the end of the sophomore year could improve the prediction accuracy for the average group.
In this paper, we investigate deep learning methods that may extract some word context for Twitter mining for syndromic surveillance. Most of the work on syndromic surveillance has been done on the flu or InfluenzaLik...
详细信息
ISBN:
(纸本)9789897583513
In this paper, we investigate deep learning methods that may extract some word context for Twitter mining for syndromic surveillance. Most of the work on syndromic surveillance has been done on the flu or InfluenzaLike Illnesses (ILIs). For this reason, we decided to look at a different but equally important syndrome, asthma/difficulty breathing, as this is quite topical given global concerns about the impact of air pollution. We also compare deep learning algorithms for the purpose of filtering Tweets relevant to our syndrome of interest, asthma/difficulty breathing. We make our comparisons using different variants of the F-measure as our evaluation metric because they allow us to emphasise recall over precision, which is important in the context of syndromic surveillance so that we do not lose relevant Tweets in the classification. We then apply our relevance filtering systems based on deep learning algorithms, to the task of syndromic surveillance and compare the results with real-world syndromic surveillance data provided by Public Health England (PHE).We find that the RNN performs best at relevance filtering but can also be slower than other architectures which is important for consideration in real-time application. We also found that the correlation between Twitter and the real-world asthma syndromic surveillance data was positive and improved withthe use of the deeplearning-powered relevance filtering. Finally, the deep learning methods enabled us to gather context and word similarity information which we can use to fine tune the vocabulary we employ to extract relevant Tweets in the first place.
the proceedings contain 131 papers. the special focus in this conference is on patternrecognition and machine Intelligence. the topics include: QIBDS Net: A Quantum-Inspired Bi-Directional Self-supervised Neural Netw...
ISBN:
(纸本)9783030348717
the proceedings contain 131 papers. the special focus in this conference is on patternrecognition and machine Intelligence. the topics include: QIBDS Net: A Quantum-Inspired Bi-Directional Self-supervised Neural Network Architecture for Automatic Brain MR Image Segmentation;colonoscopic Image Polyp Classification Using Texture Features;GRaphical Footprint Based Alignment-Free Method (GRAFree) for Classifying the Species in Large-Scale Genomics;density-Based Clustering of Functionally Similar Genes Using Biological Knowledge;impact of the Continuous Evolution of Gene Ontology on Similarity Measures;DEGnet: Identifying Differentially Expressed Genes Using Deep Neural Network from RNA-Seq datasets;Survival Analysis withthe Integration of RNA-Seq and Clinical data to Identify Breast Cancer Subtype Specific Genes;Deep learning Based Fully Automated Decision Making for Intravitreal Anti-VEGF therapy;Biomarker Identification for ESCC Using Integrative DEA;critical Gene Selection by a Modified Particle Swarm Optimization Approach;automated Counting of Platelets and White Blood Cells from Blood Smear Images;neuronal Dendritic Fiber Interference Due to Signal Propagation;Two-Class in Silico Categorization of Intermediate Epileptic EEG data;employing Temporal Properties of Brain Activity for Classifying Autism Using machinelearning;Time-Frequency Analysis Based Detection of Dysrhythmia in ECG Using Stockwell Transform;Block-Sparsity Based Compressed Sensing for Multichannel ECG Reconstruction;a Dynamical Phase Synchronization Based Approach to Study the Effects of Long-Term Alcoholism on Functional Connectivity Dynamics;RBM Based Joke Recommendation System and Joke Reader Segmentation;TagEmbedSVD: Leveraging Tag Embeddings for Cross-Domain Collaborative Filtering;On Applying Meta-path for Network Embedding in mining Heterogeneous DBLP Network;an Improved Approach for Sarcasm Detection Avoiding Null Tweets.
the goal of this tutorial is presenting new visual knowledge discovery and machinelearning methods that allow making knowledge discovery and predictive models more effective and rigorous. Specifically, we focus on le...
详细信息
the goal of this tutorial is presenting new visual knowledge discovery and machinelearning methods that allow making knowledge discovery and predictive models more effective and rigorous. Specifically, we focus on learning tasks of classification and clustering of n-D data using lossless visual representation of n-D data as graphs.
these days a lot of raw data is generated from various common sources. this large amount of data, which would appear useless at first glance, is very important for companies and researchers as could provide a lot of h...
详细信息
ISBN:
(纸本)9783319606187;9783319606170
these days a lot of raw data is generated from various common sources. this large amount of data, which would appear useless at first glance, is very important for companies and researchers as could provide a lot of helpful information. the data could be mined to get useful knowledge that could be used to make fruitful decisions. A lot of online tools and proprietary toolkits are available to the users and it becomes all the more cumbersome for them to know which is the best tool among these for the supervised learning algorithm and datasets they are applying. In order to aid this process, the paper progresses in this direction by doing a comparison of various datamining tools on the basis of their classification finesse. the various tools used in the paper are weka, knime and tanagra. Rigorous work on this has given the result that the performance of the tools is affected by the kind of datasets used and the way in which the supervised learning is done.
datamining in education is a developing interdisciplinary research field also known as educational datamining (EDM). the goal is to understand students' learning process and identify the way by which they can le...
详细信息
datamining in education is a developing interdisciplinary research field also known as educational datamining (EDM). the goal is to understand students' learning process and identify the way by which they can learn to improve educational outcomes. learning using IT is one of the most widely used methods for education in modern days. Digital learning gives students an experience of individual learning at any time as well as anywhere, so students get more interest, flexibility at learning. Knowing the preferences of students learning will help the instructors to design better learning materials and teaching styles. We have surveyed on the students of undergraduate level and evaluated the students in three categories: good, average and excellent. We have used four classification models: Support Vector machine (SVM), Logistic Regression (LR), Decision Tree and Random Forest (RF) model to predict the performance of students on basis of the impact of IT and other study mediums based on their results. In this article, we have identified different parameters or features from five different learning sectors or fields which can give an impact on the student's learning process. So, we have processed in a way that will find out the datamining model which can give better accuracy of student's performance and also can find out which parameters or features among the five fields are playing a great role in their academic results. Moreover, we can apply these features by inspiring good or average students to improve their learning process.
Process mining results can be enhanced by adding semantic knowledge to the derived models. Information discovered due to semantic enrichment of the deployed process models can be used to lift process analysis from syn...
详细信息
ISBN:
(纸本)9783319606187;9783319606170
Process mining results can be enhanced by adding semantic knowledge to the derived models. Information discovered due to semantic enrichment of the deployed process models can be used to lift process analysis from syntactic level to a more conceptual level. the work in this paper corroborates that semantic-based process mining is a useful technique towards improving the information value of derived models from the large volume of event logs about any process domain. We use a case study of learning process to illustrate this notion. Our goal is to extract streams of event logs from a learning execution environment and describe formats that allows for mining and improved process analysis of the captured data. the approach involves mapping of the resulting learning model derived from mining event data about a learning process by semantically annotating the process elements with concepts they represent in real time using process descriptions languages, and linking them to an ontology specifically designed for representing learning processes. the semantic analysis allows the meaning of the learning objects to be enhanced through the use of property characteristics and classification of discoverable entities, to generate inference knowledge which are used to determine useful learningpatterns by means of the Semantic learning Process mining (SLPM) algorithm - technically described as Semantic-Fuzzy Miner. To this end, we show how data from learning processes are being extracted, semantically prepared, and transformed into mining executable formats to enable prediction of individual learningpatterns through further semantic analysis of the discovered models.
the proceedings contain 60 papers. the topics discussed include: 3D-printed sole with variable density using foot plantar pressure measurements;HUPM: efficient high utility patternmining algorithm for e-business;Pubw...
ISBN:
(纸本)9781538666784
the proceedings contain 60 papers. the topics discussed include: 3D-printed sole with variable density using foot plantar pressure measurements;HUPM: efficient high utility patternmining algorithm for e-business;Pubworld -A R2rml mapping driven approach to transform relational database data into shareable format;a pattern and polarization reconfigurable antenna for WLAN application;an efficient method for text encryption using elliptic curve cryptography;a machinelearning approach to georeferencing;a new paradigm for generation of fuzzy membership function;on the combined use of electromyogram and accelerometer in lower limb motion recognition;comparative analysis of clustering algorithm for facial recognition system;and a new term weight measure for gender and age prediction of the authors by analyzing their written texts.
暂无评论