Analisis Sentiment merupakan salah satu cabang dari bidang ilmu Text Mining. Analisis sentiment merupakan sumber penting dalam melakukan evaluasi dan pengambilan keputusan terhadap sebuah topik permasalahan. Tujuan utama dari analisis sentiment adalah untuk mengetahui polaritas dari sentiment positif, negatif ataupun netral. Sentiment-sentiment tersebut salah satunya didapatkan dari Twitter. Dalam tulisan ini, tweet-tweet yang berhubungan dengan kata kunci yang dicari dikumpulkan dari Twitter dengan menggunakan API Twitter dan data mentah yang didapatkan diolah dengan menggunakan Natural Language Toolkit pada bahasa pemrograman Python. Setelah diolah selanjutnya akan dilakukan klasifikasi dengan menggunakan Naïve Bayes Classifier untuk mengetahui tingkat akurasi dari proses klasifikasi yang dilakukan. Proses klasifikasi dilakukan dengan RapidMiner. Dari hasil uji coba sebanyak empat kali, didapatkan hasil tingkat akurasi pada percobaan pertama sebesar 62.98%, percobaan kedua sebesar 64.95%, percobaan ketiga sebesar 66.36%, dan percobaan keempat sebesar 66.79%. Dari hasil klasifikasi didapat tingkat persentase sentiment positif sebesar 28%, sentiment negatif sebesar 20% dan sentiment netral sebesar 52%.
Sentiment classification is the one branch o f the field o f Text Mining. Sentiment classification can be an important in the process o f evaluations about something problem. The main o f sentiment classification are to fin d out the polarity o f positive, negative and neutral sentiments. The sentiment classification obtained from Twitter. In this paper, the tweets related to predefined keyword are collected using the tools provided by Twitter. The data that has been collected is processed by using Natural Language Toolkit that run on Python programming language. After that, the data will be classified by using Naive Bayes Classifier to fin d out about the sentiment. The result o f classification will be measured accurate level. Based on the experimental result fo r three times trial, the result obtained accuracy level in the first is 64.95%, the second is 66.36%, and the third is 66.79%. Another result obtained is percentage o f sentiment are positive sentiment is 28%, negative is 20% and neutral is 52%. Based on percentage result o f sentiment classes, neutral sentiment is the most sentiment that related to Joko Widodo and his government topic.
ABSTRAKPenelitian yang telah dilakukan adalah pembuatan dan penghitungan kualitas citra digital menggunakan program Modulation Transfer Function (MTF) pada sistem Computed Radiography (CR) untuk kegiatan Quality Control (QC). MTF dapat digunakan untuk menganalisis resolusi spasial citra digital secara akurat. Pada penelitian ini menggunakan phantom yang terbuat dari tembaga berukuran 15x15 cm dengan ketebalan 1 mm. Phantom dieksposi dengan variasi tegangan 50 kV, 60 kV, 70 kV dan 81 kV dan masingmasing dilakukan variasi arus. Data yang diperoleh berupa file citra digital radiografi format DICOM yang kemudian dilakukan analisis kualitas citranya menggunakan PC diluar sistem CR dengan metode MTF. Metode ini sangat efisien dalam melakukan QC resolusi spasial secara kuantitatif sehingga dapat digunakan untuk menilai kualitas pesawat CR. Hasil pengukuran menunjukkan bahwa semakin tinggi tegangan yang digunakan, maka kualitas citra semakin baik dengan arus optimal pada rentang 4-8 mAs dengan rata-rata nilai resolusi spasial 7,26 lp/mm. ABSTRACTThe research was analyzing of digital image quality by using Modulation Transfer Function (MTF) on Computed Radiography (CR) system for Quality Control (QC). MTF can be used for analyzing digital image spatial resolution accurately. The research used phantom that made of 15x15 cm2 copper and 1 mm thickness. The phantom was expounded with voltage variations by 50 kV, 60 kV, 70 kV dan 81 kV and each of them have been taken by variations of the current. The the image quality of data obtained in the form of radiography digital image files with DICOM format were then analyzed using PC out of CR system with methode of MTF. This methode is really efficient for QC spatial resolution quantitatively and so it can be used for assesing the quality of CR. The measurement results showed that the higher the voltage, the better image quality with optimal current was on the range between 4-8 mAs with the average value of MTF 7,26 lp/mm.
Prediction of the growth of plant seedlings is one of the important problems in the world in order to fulfill the availability of food for all residents. At this time Greenhouse technology has been developed which is one of the technologies that support plant growth. Unfortunately, prediction technology is still done manually so the results are not accurate. This paper proposes the Neural Network Backpropagation method to evaluate the growth of plant seedlings in the greenhouse area. Data collected from the internet network system from temperature sensors, soil humidity, environmental humidity, light intensity and cameras to monitor growth. Seedling prediction is done by building a computer program using the neural network backpropagation algorithm based on time series that has input layer, hidden layer and output prediction architecture. Training data is used to carry out the training process before the program is used to perform predictions. Furthermore, the program is used to make predictions. The results of applying the neural network backpropagation algorithm to predict the growth of plant seedlings in the greenhouse get good results based on the first iteration Mean Squared Error (MSE) of 0.0112, with computing time 0.0193 seconds and data accuracy of 92.79%, which means that the prediction generated approximates actual data for the application of backpropagation neural network algorithms to the evaluation of plant seedling growth.
Air pollution (O3, SO2, CO, NOx, PM, and Pb) can have a severe impact on environmental damage and human health problems. Therefore, monitoring of pollutant levels in the air is essential to find out how much that gas levels can cause air pollution. In general, air quality monitoring is carried out using a conventional system. Inside the system requires large-sized equipment, long time for analysis, expensive, and with limited space resolution. It becomes inefficient, amid the development of technology that can carry out online monitoring, real-time, low cost, small size and a wide range of distance. The technology is known as the wireless sensor network system. The aim of this research is to design an air quality monitoring system using a Wireless Sensor Network (WSN) that can be accessed via the web and smartphone. The developing of WSN systems consist of two steps, are design and implementation device. The first step is done by assembling sensor nodes and hosting a web server. And after the device was finished, the next step is testing and calibrating of the system. The results of experiment show that the system is able to detect various air pollution, such as SO2, NOX, CO, and other environmental factors such as temperature, humidity and wind speed.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.