Ant Colony Optimization for Traveling Tourism Problem on Timor Island East Nusa Tenggara

Timor island consists of five districts and one city, namely Kupang District, South Central Timor District, North Central Timor, Belu District, Malaka District, and Kupang City. On the Timor island, it has natural tourist destinations, culinary tours, cultural and historical attractions most on the island of Timor. The Ant Colony Optimization (ACO) Algorithm is very unique compared to the other nearby search algorithm, this algorithm adopted because of Ant Colony who were looking for food from the nest to food sources by leaving a footprint called Pheromone. Mapping system algorithm using ant, tourist sites can show the shortest route between two points is desired. Ants algorithm proved to be applied in determining the optimum route, but still has the disadvantage of dependence on the parameter value is not maximized. From the test results based on parameters of the cycle and the number of ants affects the simulation time, for ant algorithm parameters. From the test results based on the parameters, α and β affects, number of node, the simulation time and the shortest distance varying toward the destination even if the starting location and ending on the same location.

Sentiment Analysis Of Cyberbullying On Twitter Using SentiStrength

Cyberbullying is a form of bullying that takes place across virtually every social media platform. Twitter is a form of social media that allows users to exchange information. Bullying has been a growing problem on Twitter over the past few years. Sentiment analysis is done to identify the element of bullying in a tweet. Sentiments are divided into 3 classes, namely Bullying, Non-Bullying and neutral. There are three steps to classify cyberbullying i.e. collection of data set, preprocessing data, and classification process. This research used sentiStrength, an algorithm which uses a lexicon based approach. This SentiStrength lexicon contains the weight of its sentiment strength. The assessment results from 454 tweets data obtained 161 tweet non-bullying (35.4%), 87 tweet neutral (19.1%), and 206 tweet bullying (45.4%). This research produces an accuracy value of 60.5%.

Comparative Study of Mamdani-type and Sugeno-type Fuzzy Inference Systems for Coupled Water Tank

The level and flow control in tanks are the heart of all chemical engineering system. The control of liquid level in tanks and flow between tanks is a basic problem in the process industries. Many times the liquids will be processed by chemical or mixing treatment in the tanks, but always the level of fluid in the tanks must be controlled and the flow between tanks must be regulated in presence of non-linearity. Threfore, in this paper will use fuzzy inference systems to control of level 2 are developed using Mamdani-type and Sugeno-type fuzzy models. The outcome obtained by two fuzzy inference systems is evaluated. This paper summarizes the essential variation among the Mamdani-type and Sugeno-type fuzzy inference systems with setpoint of level is 10 centimeter. Matlab fuzzy logic toolbox is used for the simulation of both the models. This also confirms which one is a superior choice of the two fuzzy inference systems to control of level 2 in tank 2. The results show madani-type fuzzy inference system is superior as compared to sugeno-type fuzzy inference system.

Internet of Things (IOT) Development for The Chicken Coop Temperature and Humidity Monitoring System Based on Fuzzy

The high increase in broiler each year there are several factors that must be considered, one of them is the temperature and humidity of the cage. The brooding cage space of 10 ekor/1. If more then that couse broiler is not optimal. The temperatur needed is 29°C-35°C and humidity 60%-70% for brooding. In general control of temperature and humidity, unable to maintain cage needs. Then it is necessary to do automatic control using the fuzzy logic method and the concept of Internet of Things (IoT). Base on the testing result the system has been able to maintain the set point of temperature and humidity and get broiler growth not same, The best stability value during the test is condition without DOC produces no overshoot temperature parameters and steady state error 0,48, no overshoot and steady state for humidity. On the condition with DOC produces overshoot temperature 0,06 and steady state error 0,15, and overshoot 0,1 and steady state 0,4 for humidity. While on the IoT concept has been able to display the temperature and humidity values on the cage

Optimzation of Interval Fuzzy Time Series With Particle Swarm Optimization for Prediction Air Quality on Pekanbaru

Kota Pekanbaru memiliki jumlah penduduk terbanyak di provinsi Riau yaitu 1.046.566 penduduk dengan jumlah kendaraan bermotor 105.941 unit. Badan Lingkungan Hidup menyatakan bahwa kota Pekanbaru memiliki kualitas udara yang tercemar yang disebabkan oleh kebakaran hutan dan lahan serta emisi gas buang kendaraam bermotor. Dengan adanya kondisi tersebut, kota Pekanbaru menggunakan alat pemantau udara yaitu Air Quality Monitoring System (AQMS) dengan penyampaian informasi kualitas udara melalui papan display ISPU. Penelitian ini bertujuan untuk memprediksi kualitas udara esok hari di kota Pekanbaru dengan menggunakan metode Fuzzy Time Series yang di optimasi menggunakan Particle Swarm Optimization. Tingkat akurasi prediksi diukur dengan menggunakan Mean Absolute Percentage Error (MAPE) dengan menghitung selisih antara data aktual dan hasil prediksi. Adapun data masukan yang digunakan yaitu 729 data dengan 5 parameter pengukur kualitas udara yaitu PM10, SO2, CO, O3 dan NO2. Hasil keluaran berupa angka prediksi untuk masing-masing parameter pengukur kualitas udara. Hasil pegujian metode FTS-PSO menunjukkan nilai MAPE sebesar 18,3583%. Parameter PSO terbaik yang digunakan adalah jumlah partikel 10, maksimal iterasi 25 dan bobot inersia 0,6. Dari hasil pengujian dapat disimpulkan bahwa prediksi kualitas udara menggunakan FTS-PSO bernilai cukup akurat.

Sentiment Analysis Using Twitter Data Regarding BPJS Cost Increase and Its Effect on Health Sector Stock Prices

News about the increase in BPJS that will increase 2x gives a variety of responses in the community. One of the social media that people use in responding is Twitter. This research is used to see people's sentiment on Twitter about BPJS tariff policies. In addition, the impact of this sentiment will also be seen on the price of health shares. The analysis used is descriptive analysis and inference analysis. Descriptive analysis is used to look at the general picture of community sentiment and inference analysis is used to see the impact of community sentiment on the price of health stocks, namely Indo Farma and Kimia Farma. The results of this study indicate that public sentiment towards rising BPJS is dominated by negative sentiment. And for the level of tendency that has been processed through binary logistic regression analysis shows that negative sentiment will make Kimia Farma shares will go down while positive sentiment will make Kimia Farma shares will go up. As for IndoFarma shares, positive and negative sentiments from IndoFarma shares will tend to fall.

Implementation of K-Medoids and FP-Growth Algorithms for Grouping and Product Offering Recommendations

212 Mart Rambutan Street on Pekanbaru City is a company engaged in retail. Meeting the needs of consumers and making the right decision in determining the sales strategy is a must. One way to find out market conditions is to observe sales transaction data using data mining. The data mining method commonly used to analyze market basket (Market Basket Analysis) is the Association Rule. The Association Rule can provide product recommendations and promotions, so that the marketing strategy is more targeted and the items promoted are the customer's needs. At 212 Mart, the determination of product promotion is obtained from the analysis of sales transaction data reports, which are based on the most sold products and the expiration date. Often the product being promoted does not fit the customer's needs. The purpose of this study is to apply the K-Medoids algorithm for clustering on FP-Growth in producing product recommendation rules on a large number of datasets so that they can provide technical recommendations / new ways to the 212 Mart in determining product promotions. The results obtained are from the experiments the number of clusters 3 to 9 obtained optimal clusters of 3 clusters based on the validity test of the Davies Bouldin Index with a value of 0.678. With a minimum support value of 5% - 9% and a minimum value of 50% confidence, the result is that the Association Rule is found only in cluster 3 with 5 rules.

K-Nearest Neighbor for Classification of Tomato Maturity Level Based on Hue, Saturation, and Value Colors

The selection of tomatoes can use several indicators. One of the indicators is the fruit color. In digital image processing, one of the color information that could be used in Hue, Saturation, and Value (HSV). In this research, HSV is proposed as a color model feature for information on the ripeness of tomatoes. The total data of tomato images used in this research were 400 images from four sides. The maturity level of tomatoes uses five levels, namely green, turning, pink, light red, and red. The process of divide data uses K-Fold Cross Validation with ten folds. The method used for classification is k-Nearest Neighbor (kNN). The scenario of the test performed is to combine the image size with the parameter value of the neighbor (k). The image sizes tested are 100x100 pixels, 300x300 pixels, 600x600 pixels and 1000x1000 pixels. The “k” values tested were 1, 3, 5, 7, 9, 11, and 13. The highest accuracy reached 92.5% in the image size 1000x1000 pixels with a parameter “k” is 3. The result of the experiment showed that the image size has a significant influence of accuracy, but the parameter value of neighbor (k) has an influence that is not too significant.

Implementation the Knuth Morris Pratt (KMP) Algorithm in Interactive Web Monitoring and Recording Rabbit Reproduction System

Recording and monitoring rabbit reproduction data at Balai Penelitian Ternak (Balitnak) are yet integrated using systematic recording and searching system approach. Thus the purpose of this study is to build an interactive web monitoring and recording rabbit reproduction system as well as implementing the Knuth Morris Pratt (KMP) algorithm in order to provide a reliable search function. This research produced an interactive monitoring of recording rabbit reproduction data which record important information about rabbit codes, dates (mating, palpation, childbirth, 21 days, 35 days), weight (mating, palpation, after giving birth, 21 days, 35 days ), the number of children born alive or dead (giving birth, 21 days, 35 days). The results of the implementation of the KMP algorithm generated a search with a time of 0.015095 milliseconds with an algorithm test based on the search for rabbit names as many as 20 types of rabbits.

Data Mining Predictive Modeling for Prediction of Gold Prices Based on Dollar Exchange Rates, Bi Rates and World Crude Oil Prices

Gold is an investment instrument that is quite safe from inflationary attacks, and gold is one aspect of initiating investment. Can by buying gold in physical form and then selling when the price has risen high or by digitally investing gold. One of them is by trading gold online. To maximize the benefits of gold trading, a gold price prediction (XAUUSD) is needed for traders. This study aims to (1) Analyze various factors that influence the price of gold (2) Provide recommendations about the prediction of gold prices. Materials that will be used as objects of research to produce gold price predictions include historical XAUUSD (Gold) data itself, historical crude oil data, historical dollar data (USD IDR) and BI 7-Day Repo Rate (BI Rate). ), in producing the prediction of the gold price used Mining Predictive Modeling data using the linear regression function. The results to be achieved from this study is to provide accurate gold price predictions so that it can be used as a reference in making decisions to buy / sell positions in trading. The prediction of the XAUUSD gold price generated is expected to provide significant interest to the investment players (traders) in order to maximize the profit generated.From the results of the trading tests that have been carried out, the implementation of predictive modeling data mining using a linear regression function produces recommendations for gold price predictions (XAUUSD) with an accuracy of 85%.