An improved learning-based LSTM approach for lane change intention prediction subject to imbalanced data

2021 ◽  
Vol 133 ◽  
pp. 103414
Author(s):  
Qian Shi ◽  
Hui Zhang
Keyword(s):  
Imbalanced Data ◽  
Lane Change ◽  
Improved Learning

scholarly journals EMSGD: An Improved Learning Algorithm of Neural Networks With Imbalanced Data

IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 64086-64098 ◽  
Author(s):  
Qian Ya-Guan ◽  
Ma Jun ◽  
Zhang Xi-Min ◽  
Pan Jun ◽  
Zhou Wu-Jie ◽  
...  
Keyword(s):  
Neural Networks ◽  
Learning Algorithm ◽  
Imbalanced Data ◽  
Improved Learning

Handling Imbalanced Data for Real-Time Crash Prediction: Application of Boosting and Sampling Techniques

2021 ◽  
Vol 147 (3) ◽  
pp. 04020165
Author(s):  
Amin Ariannezhad ◽  
Abolfazl Karimpour ◽  
Xiao Qin ◽  
Yao-Jan Wu ◽  
Yasamin Salmani
Keyword(s):  
Real Time ◽  
Imbalanced Data ◽  
Sampling Techniques ◽  
Crash Prediction

MENINGKATKAN HASIL BELAJAR IPS SISWA KELAS VC SD NEGERI 164 PEKANBARU DENGAN MENGGUNAKAN METODE PEMBELAJARAN KOOPERATIF NUMBERED HEADS TOGETHER (NHT)

2019 ◽  
Vol 3 (1) ◽  
pp. 197
Author(s):  
Rosita L. Tobing
Keyword(s):  
Action Research ◽  
Social Studies ◽  
Learning Outcomes ◽  
Class Actions ◽  
Heterogeneous Groups ◽  
The Social ◽  
Classroom Action Research ◽  
Improved Learning ◽  
Academic Year

The problem of classroom action research is the low learning outcomes of VC grade 164 students in Pekanbaru. This study aims to improve social studies learning outcomes of VC grade 164 students in Pekanbaru by applying the cooperative method of numbered heads together (NHT). The results of the research and class actions of the Social Studies Course conducted at the VC class SDN 164 Pekanbaru students concluded; Learning outcomes in the first cycle have increased compared to conventional learning. Pre-cycle learning outcomes are an average of 50.25 or sufficient categories; in cycle I, learning outcomes reached an average of 71.75 or in the Good category; in cycle II it increased again by 80.25 or in the Good category; Prasiklus classical completeness is 10 students (25.00%.); the first cycle is 27 students (67.50%); and in the second cycle were 38 students (95.00%). Students who have not been completed are remedial. Observers observed that VC grade 164 students at Pekanbaru Pekanbaru seemed to understand the Numbered Heads Together (NHT) Cooperative Method. They learn and understand shared material in heterogeneous groups of 4-5 students. Based on the results of improved learning studies, the application of the cooperative method of numbered heads together (NHT) succeeded in correcting the problem of the low social studies learning outcomes in VC Class SDN 164 Pekanbaru 2017/2018 Academic Year.

PENERAPAN STRATEGI MAKE A MATCH UNTUK MENINGKATKAN HASIL BELAJAR IPS KELAS IV SDN 005 KOTO SENTAJO KECAMATAN SENTAJO RAYA

2018 ◽  
Vol 2 (3) ◽  
pp. 444
Author(s):  
Fuji Nengsih
Keyword(s):  
Action Research ◽  
Initial Data ◽  
Learning Outcomes ◽  
Primary Schools ◽  
Activity Cycle ◽  
Student Activity ◽  
Teachers And Students ◽  
Classroom Action Research ◽  
Improved Learning ◽  
Daily Test

IPS learning is a science of socio-cultural phenomena, and economics. IPS education in primary schools aims todevelop student potential. This study is a classroom action research that aims to improve the learning processwith the ultimate impact of improved learning outcomes. Data obtained on teacher activity cycle II percentage62.5% and 71% at the second meeting. Cycle II the percentage of teacher activity 83% and 92% at the secondmeeting whereas in student activity on cycle I with percentage 50% and second meeting 62,5% increase in cycleII become 75% and 88% at second meeting cycle II. The activity of teachers and students influences the IPSlearning result data with average views on the initial data 68.3, increased to 79.8 and in the daily test II with anaverage of 89.5. The conclusions in this study are make-match strategies effective in improving IPS learningoutcomes.

PENERAPAN MODEL PEMBELAJARAN PETA KONSEP UNTUK MENINGKATKAN HASIL BELAJAR IPS SISWA KELAS VI SD NEGERI 022 JAYA MUKTI KOTA DUMAI

2018 ◽  
Vol 2 (3) ◽  
pp. 395
Author(s):  
Burhanuddin Burhanuddin
Keyword(s):  
Social Sciences ◽  
Data Analysis ◽  
Student Learning ◽  
Learning Outcomes ◽  
Concept Map ◽  
Student Learning Outcomes ◽  
Learning Model ◽  
Model Concept ◽  
Student Activity ◽  
Improved Learning

This research is motivated by the learning result of Social Sciences of Grade VI SD Negeri 022 Jaya Mukti KotaDumai which is still very low. This study aims to improve the learning outcomes of Social Sciences students.From the data analysis there is an increase of both teacher activity, student activity, and student learning result,that is teacher activity at meeting 1 cycle I percentage is 65% (enough) and at meeting 2 increase to 80%(good). In the second cycle of meeting 3 it increases again to 90% (very good) and at meeting 4 increases to95% (very good). Judging from the student activity also increased from the 1st meeting of cycle I was 60%(enough) and at meeting 2 increased to 70% (good). In the second cycle of meeting 3 it increased to 85% (verygood) and at the 4th meeting to 95% (very good). Judging from student learning outcomes, the average basicscore 63 increased to 75 in the first cycle of increase 12 points later in cycle II increased to 95 in cycle II largeincrease of 20 points. From the data analysis there is an increase both from teacher activity, student activity,and student learning outcomes. It can be concluded that the Improved Learning Model concept map can improvethe learning outcomes of IPS students of class VI SD Negeri 022 Jaya Mukti Kota Dumai.

Un-Supervised approach to backorder prediction using deep autoencoder

2019 ◽  
Vol 12 ◽  
Author(s):  
Gunjan Saraogi ◽  
Deepa Gupta ◽  
Lavanya Sharma ◽  
Ajay Rana
Keyword(s):  
Anomaly Detection ◽  
Predictive Model ◽  
Inventory Management ◽  
Supervised Classification ◽  
Operating Characteristic ◽  
Imbalanced Data ◽  
Bullwhip Effect ◽  
Detection Methods ◽  
Good Representation ◽  
Operational Management

Background: Backorders are an accepted abnormality affecting accumulation alternation and logistics, sales, chump service, and manufacturing, which generally leads to low sales and low chump satisfaction. A predictive archetypal can analyse which articles are best acceptable to acquaintance backorders giving the alignment advice and time to adjust, thereby demography accomplishes to aerate their profit. Objective: To address the issue of predicting backorders, this paper has proposed an un-supervised approach to backorder prediction using Deep Autoencoder. Method: In this paper, artificial intelligence paradigms are researched in order to introduce a predictive model for the present unbalanced data issues, where the number of products going on backorder is rare. Result: Un-supervised anomaly detection using deep auto encoders has shown better Area under the Receiver Operating Characteristic and precision-recall curves than supervised classification techniques employed with resampling techniques for imbalanced data problems. Conclusion: We demonstrated that Un-supervised anomaly detection methods specifically deep auto-encoders can be used to learn a good representation of the data. The method can be used as predictive model for inventory management and help to reduce bullwhip effect, raise customer satisfaction as well as improve operational management in the organization. This technology is expected to create the sentient supply chain of the future – able to feel, perceive and react to situations at an extraordinarily granular level

Imbalanced Data Detection Kernel Method in Closed Systems

2013 ◽  
Vol 756-759 ◽  
pp. 3652-3658
Author(s):  
You Li Lu ◽  
Jun Luo
Keyword(s):  
Kernel Methods ◽  
Kernel Method ◽  
Imbalanced Data ◽  
Data Detection ◽  
Data Sets ◽  
System Call ◽  
Data Set ◽  
Imbalanced Data Sets ◽  
Lower Complexity ◽  
Closed Systems

Under the study of Kernel Methods, this paper put forward two improved algorithm which called R-SVM & I-SVDD in order to cope with the imbalanced data sets in closed systems. R-SVM used K-means algorithm clustering space samples while I-SVDD improved the performance of original SVDD by imbalanced sample training. Experiment of two sets of system call data set shows that these two algorithms are more effectively and R-SVM has a lower complexity.

scholarly journals Cluster-Wise Weighted NMF for Hyperspectral Images Unmixing with Imbalanced Data

2021 ◽  
Vol 13 (2) ◽  
pp. 268
Author(s):  
Xiaochen Lv ◽  
Wenhong Wang ◽  
Hongfu Liu
Keyword(s):  
Spatial Information ◽  
Hyperspectral Image ◽  
Imbalanced Data ◽  
Reconstruction Error ◽  
Hyperspectral Data ◽  
Weight Matrix ◽  
Hyperspectral Images ◽  
Mixed Data ◽  
Sparsity Constraints ◽  
Additional Constraints

Hyperspectral unmixing is an important technique for analyzing remote sensing images which aims to obtain a collection of endmembers and their corresponding abundances. In recent years, non-negative matrix factorization (NMF) has received extensive attention due to its good adaptability for mixed data with different degrees. The majority of existing NMF-based unmixing methods are developed by incorporating additional constraints into the standard NMF based on the spectral and spatial information of hyperspectral images. However, they neglect to exploit the nature of imbalanced pixels included in the data, which may cause the pixels mixed with imbalanced endmembers to be ignored, and thus the imbalanced endmembers generally cannot be accurately estimated due to the statistical property of NMF. To exploit the information of imbalanced samples in hyperspectral data during the unmixing procedure, in this paper, a cluster-wise weighted NMF (CW-NMF) method for the unmixing of hyperspectral images with imbalanced data is proposed. Specifically, based on the result of clustering conducted on the hyperspectral image, we construct a weight matrix and introduce it into the model of standard NMF. The proposed weight matrix can provide an appropriate weight value to the reconstruction error between each original pixel and the reconstructed pixel in the unmixing procedure. In this way, the adverse effect of imbalanced samples on the statistical accuracy of NMF is expected to be reduced by assigning larger weight values to the pixels concerning imbalanced endmembers and giving smaller weight values to the pixels mixed by majority endmembers. Besides, we extend the proposed CW-NMF by introducing the sparsity constraints of abundance and graph-based regularization, respectively. The experimental results on both synthetic and real hyperspectral data have been reported, and the effectiveness of our proposed methods has been demonstrated by comparing them with several state-of-the-art methods.

Sign in / Sign up

Export Citation Format

Share Document