scholarly journals ANALISIS SENTIMEN PT TIKI JALUR NUGRAHA EKAKURIR (PT TIKI JNE) PADA MEDIA SOSIAL TWITTER MENGGUNAKAN MODEL FEED FORWARD NEURAL NETWORK

2020 ◽  
Vol 8 (2) ◽  
pp. 103
Author(s):  
Salma Farah Aliyah ◽  
Hasbi Yasin ◽  
Suparti Suparti ◽  
Budi Warsito ◽  
Tatik Widiharih
Keyword(s):  
Neural Network ◽  
Evaluation Model ◽  
Numerical Data ◽  
Test Results ◽  
Feed Forward Neural Network ◽  
The Public ◽  
Freight Forwarding ◽  
Initial Source ◽  
Accuracy Performance ◽  
Fold Cross Validation

In the 2000s until now, e-commerce systems have continued to develop throughout the world and even in Indonesia. PT Tiki Jalur Nugraha Ekakurir (PT Tiki JNE) is a freight forwarding company that provides convenience for the public in carrying out online shopping activities, and shipping other goods. The large volume of shipments makes PT Tiki JNE have several problems in service that have led to several kinds of responses from users. Sentiment analysis on Twitter social media can be an option to see how PT Tiki JNE’s users respond to services that have been provided. These responses are classified into positive sentiments and negative sentiments. In this research data processing is performed using text mining as the initial source of numerical data from document data which will later be classified using the Artificial Neural Network model with the Resilient Backpropagation algorithm. Data labeling is done manually and sentiment scoring. The test results show that the best model obtained is FFNN 867-7-1 by using the evaluation model 10-Fold Cross Validation to get an overall accuracy performance of 80.27%, kappa accuracy of 39.13%, precision of 69.04%, recall of 70.56%, and f-measure of 69.8% which can be interpreted that the model used is quite good. Analysis of the results using wordcloud shows the tendency of opinion sentiment categories depending on the words used in the tweet.

PREDICTION OF POTENTIAL HIT SONG AND MUSICAL GENRE USING ARTIFICIAL NEURAL NETWORKS

2009 ◽  
Vol 20 (11) ◽  
pp. 1697-1718 ◽  
Author(s):  
CHRISTOPHER MONTEROLA ◽  
CHERYL ABUNDO ◽  
JERIC TUGAFF ◽  
LORCEL ERICKA VENTURINA
Keyword(s):  
Neural Network ◽  
Feed Forward Neural Network ◽  
Linear Discriminant ◽  
The Public ◽  
Musical Genre ◽  
Alternative Rock ◽  
Discriminating Power ◽  
Average Accuracy ◽  
Classification And Regression ◽  
Size Criterion

Accurately quantifying the goodness of music based on the seemingly subjective taste of the public is a multi-million industry. Recording companies can make sound decisions on which songs or artists to prioritize if accurate forecasting is achieved. We extract 56 single-valued musical features (e.g. pitch and tempo) from 380 Original Pilipino Music (OPM) songs (190 are hit songs) released from 2004 to 2006. Based on an effect size criterion which measures a variable's discriminating power, the 20 highest ranked features are fed to a classifier tasked to predict hit songs. We show that regardless of musical genre, a trained feed-forward neural network (NN) can predict potential hit songs with an average accuracy of Φ NN = 81%. The accuracy is about +20% higher than those of standard classifiers such as linear discriminant analysis (LDA, Φ LDA = 61%) and classification and regression trees (CART, Φ CART = 57%). Both LDA and CART are above the proportional chance criterion (PCC, Φ PCC = 50%) but are slightly below the suggested acceptable classifier requirement of 1.25*Φ PCC = 63%. Utilizing a similar procedure, we demonstrate that different genres (ballad, alternative rock or rock) of OPM songs can be automatically classified with near perfect accuracy using LDA or NN but only around 77% using CART.

scholarly journals Automatic Cigarette Object Concealment in Video using R-CNN

2021 ◽  
Vol 5 (1) ◽  
pp. 21
Author(s):  
Kadek Utari Widiarsini ◽  
Duman Care Khrisne ◽  
I Made Arsa Suyadnya
Keyword(s):  
Neural Network ◽  
Causes Of Death ◽  
Test Results ◽  
Tobacco Products ◽  
Application Performance ◽  
Nicotiana Rustica ◽  
Heart Attacks ◽  
The Public ◽  
The World ◽  
Lung Infections

Cigarettes are packaged processed tobacco products, produced from the Nicotiana Tabacum, Nicotiana Rustica plants and other species or synthetics that contain nicotine with or without additives. Smoking is known to the public as one of the causes of death in the world that is quite large such as asthma, lung infections, oral cancer, throat cancer, lung cancer, heart attacks, strokes, dementia, erectile dysfunction (impotence), and so on. This research aims to build an application that can recognize cigarettes automatically and conceal pictures so that people especially minors are not affected by cigarettes. The application is built using the Region-based Convolutional Neural Network (R-CNN) method. The study uses images that have cigarette objects in them. The test is carried out to find out the application performance such as the level of application accuracy in recognizing cigarette objects. Based on the test results with a sample of 126 cigarette images, the application built is able to recognize cigarette objects by obtaining an accuracy value of 63%.

scholarly journals Big Data Digging of the Public’s Cognition about Recycled Water Reuse Based on the BP Neural Network

Complexity ◽  
2018 ◽  
Vol 2018 ◽  
pp. 1-11 ◽  
Author(s):  
Hanliang Fu ◽  
Zhijian Liu ◽  
Mengmeng Wang ◽  
Zelin Wang
Keyword(s):  
Neural Network ◽  
Big Data ◽  
Bp Neural Network ◽  
Water Reuse ◽  
Clustering Algorithm ◽  
Behavioral Control ◽  
Evaluation Model ◽  
Perceived Behavioral Control ◽  
Recycled Water ◽  
The Public

Reuse of recycled water is very important to both the environment and economy, while the public cognition degree towards recycled water reuse also plays a key role in this process, and it determines the acceptance degree of the public towards recycled water reuse. Under the background of the big data, the Hadoop platform was used to collect and save data about the public’s cognition towards recycled water in one city and the BP neural network algorithm was used to construct an evaluation model that could affect the public’s cognition level. The public’s risk perception, subjective norm, and perceived behavioral control regarding recycled water reuse were selected as key factors. Based on a multivariate clustering algorithm, MATLAB software was used to make real testing on massive effective data and assumption models, so as to analyze the proportion of three evaluation factors and understand the simulation parameter scope of the cognition degree of different groups of citizens. Lastly, several suggestions were proposed to improve the public’s cognition on recycled water reuse based on the big data in terms of policy mechanism.

scholarly journals PENERAPAN ALGORITMA EVOLVING NEURAL NETWORK UNTUK PREDIKSI CURAH HUJAN

2016 ◽  
Vol 1 (1) ◽  
pp. 1-8
Author(s):  
Subhan Panji Cipta
Keyword(s):  
Neural Network ◽  
Flood Control ◽  
Early Stage ◽  
Economic Value ◽  
Weather Forecast ◽  
Decision Makers ◽  
Test Results ◽  
The Public ◽  
Rainfall Prediction ◽  
Better Than

Weather and climate information have contributed as one consideration for decision makers. This arises because the information the weather / climate has economic value in a variety of activities , ranging from agriculture to flood control . From the data obtained implied that the current rainfall prediction not so accurate . Forecasts are often given to the public on a regular basis is the weather forecast , not the amount of rainfall. This study uses an algorithm Evolving Neural Network (ENN) as an approach to predict the rainfall , the data processing and calculations will use MatLab 2009b . The parameters used in this study is time , rainfall , humidity and temperature. The results also compared with the test results and predictions BPNN BMKG. From the results of research conducted from early stage to test and measurement , the application of this ENN has a rainfall prediction with accuracy better than the BPNN and prediction algorithms BMKG.  

scholarly journals MODEL CNN LENET DALAM PENGENALAN JENIS GOLONGAN KENDARAAN PADA JALAN TOL

2020 ◽  
Vol 12 (2) ◽  
pp. 65
Author(s):  
Anggay Luri Pramana ◽  
Endang Setyati ◽  
Yosi Kristian
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Vehicle Classification ◽  
Test Results ◽  
Field Of Study ◽  
Neural Network Method ◽  
The Public ◽  
Network Method

Research in the field of transportation, especially vehicle classification with various methods, is a widely developed field of study. Vehicles can be categorized by shape, dimension, logo, and  type. The vehicle dataset is also not difficult to find because it is general in nature. Based on the research that has been done, the introduction of group types based on the number of axles with CNN, the dataset is not yet available to the public. In this paper, we discuss the introduction of the types of groups using the Convolutional Neural Network method. The architecture used is the LeNet model. The trial scenario is carried out in 4 stages, namely 25 epochs, 50 epochs, 75 epochs and 100 epochs. Based on the test results, the accuracy obtained continues to increase at 50 epochs and 100 epochs iterations. Starting from an accuracy of 82%, 94% to the highest accuracy of 95%. Likewise in the prediction the data has increased from 80%, 85% to the highest accuracy that can be 86%. From 50 epochs to 75 epochs, the accuracy of both training and testing has decreased.

IDENTIFICATION OF HOAX BASED ON TEXT MINING USING K-NEAREST NEIGHBOR METHOD

2022 ◽  
Vol 10 (2) ◽  
pp. 217
Author(s):  
I Wayan Santiyasa ◽  
Gede Putra Aditya Brahmantha ◽  
I Wayan Supriana ◽  
I GA Gede Arya Kadyanan ◽  
I Ketut Gede Suhartana ◽  
...  
Keyword(s):  
Nearest Neighbor ◽  
The Internet ◽  
Test Results ◽  
K Nearest Neighbor ◽  
K Value ◽  
The Public ◽  
A Value ◽  
K Nearest Neighbor Algorithm ◽  
Time Information ◽  
Fold Cross Validation

At this time, information is very easy to obtain, information can spread quickly to all corners of society. However, the information that spreaded are not all true, there is false information or what is commonly called hoax which of course is also easily spread by the public, the public only thinks that all the information circulating on the internet is true. From every news published on the internet, it cannot be known directly that the news is a hoax or valid one. The test uses 740 random contents / issue data that has been verified by an institution, where 370 contents are hoaxes and 370 contents are valid. The test uses the K-Nearest Neighbor algorithm, before the classification process is performed, the preprocessing stage is performed first and uses the TF-IDF equation to get the weight of each feature, then classified using K-Nearest Neighbor and the test results is evaluated using 10-Fold Cross Validation. The test uses the k value with a value of 2 to 10. The optimal use of the k value in the implementation is obtained at a value of k = 4 with precision, recall, and F-Measure results of 0.764856, 0.757583, and 0.751944 respectively and an accuracy of 75.4%

Public finance flow in contemporary Russia

2020 ◽  
Vol 26 (11) ◽  
pp. 2501-2523
Author(s):  
V.V. Smirnov
Keyword(s):  
Neural Network ◽  
Public Finance ◽  
Systems Approach ◽  
Management Decisions ◽  
Public Authorities ◽  
Cluster Analyses ◽  
The Public ◽  
National Wealth ◽  
Economic Formation

Subject. This article discusses the issues related to public finance. Objectives. The article aims to identify the determinants, indicators, and priorities of the public finance flow in contemporary Russia. Methods. For the study, I used the methods of statistical, neural network, and cluster analyses, and the systems approach. Results. The article identifies and describes the determining indicators of the main aggregates and balances of public finance, sources, and the use of funds. It establishes a link between the main aggregates and balances of public finance, defining the form and content of Russian capitalism. Conclusions. Understanding the issue and problem of public finance flow in contemporary Russia helps identify the reasons for the inability to transit to a capitalist socio-economic formation. The provisions of the study expand the scope of knowledge and develop the competence of public authorities to make management decisions on the distribution and redistribution of the value of a public product and part of the national wealth.

Algorithm Comparation of Naive Bayes and Support Vector Machine based on Particle Swarm Optimization in Sentiment Analysis of Freight Forwarding Services

2020 ◽  
Vol 4 (2) ◽  
pp. 362-369
Author(s):  
Sharazita Dyah Anggita ◽  
Ikmah
Keyword(s):  
Support Vector Machine ◽  
Sentiment Analysis ◽  
Naive Bayes ◽  
Naïve Bayes ◽  
Support Vector ◽  
The Public ◽  
Svm Algorithm ◽  
Bayes Algorithm ◽  
Freight Forwarding ◽  
Improved Accuracy

The needs of the community for freight forwarding are now starting to increase with the marketplace. User opinion about freight forwarding services is currently carried out by the public through many things one of them is social media Twitter. By sentiment analysis, the tendency of an opinion will be able to be seen whether it has a positive or negative tendency. The methods that can be applied to sentiment analysis are the Naive Bayes Algorithm and Support Vector Machine (SVM). This research will implement the two algorithms that are optimized using the PSO algorithms in sentiment analysis. Testing will be done by setting parameters on the PSO in each classifier algorithm. The results of the research that have been done can produce an increase in the accreditation of 15.11% on the optimization of the PSO-based Naive Bayes algorithm. Improved accuracy on the PSO-based SVM algorithm worth 1.74% in the sigmoid kernel.

Sign in / Sign up

Export Citation Format

Share Document