Water Availability Forecasting Using Univariate and Multivariate Prophet Time Series Model for ACEA (European Automobile Manufacturers Association)

Time series is one of method to forecasting the data. The ACEA company has competition with opened the data in the Water Availability and uses the data to forecast. The dataset namely, Aquifers-Petrignano in Italy in water resources field has five parameters e.g. rainfall, temperature, depth to groundwater, drainage volume, and river hydrometry. In our research will be forecast the depth to groundwater data using univariate and multivariate approach of time series using Prophet Method. Prophet method is one of library which develop by Facebook team. We also use the other approach to making the data clean, or the data ready to forecast. We use handle missing data, transforming, differencing, decomposition time series, determine lag, stationary approach, and Augmented Dickey-Fuller (ADF). The all approach will be uses to make sure that the data not appearing the problem while we tried to forecast. In the other describe, we already get the results using univariate and multivariate Prophet method. The multivariate approach has presented the value of MAE 0.82 and RMSE 0.99, it’s better than while we forecast using univariate Prophet.

The Inflation Forecasting of Major Cities In East Kalimantan: A Comparison Of Holt-Winters And SARIMA Model

This research aims to compare the performance of Holt Winters and Seasonal Autoregressive Integrate Moving Average (SARIMA) models in predicting inflation in Balikpapan and Samarinda, two biggest cities in East Kalimantan province. The importance of East Kalimantan province cannot be overstated since it has been declared as the venue for the capital of Indonesia. Hence, inflation prediction of the two cities will give valuable insights about the economic nature of the province for the country’s new capital. The data used in this study extended from January 2015 to September 2021. The data were divided into training and test data. The training data were used to model the time series equation using Holt winters and SARIMA models. Later, the models derived from training data were employed to produce forecasts. The forecasts were compared to the actual inflation data to determine the appropriate model for forecasting. Test data were from January 2015 to December 2020 and test data extended from January 2021 to September 2021. The result showed that Holt-Winters performed better than SARIMA in prediction inflation. The Root Mean Squared Error (RMSE) values are lower for Holt-Winters Exponential Smoothing for both cities. It also predicts better timing of cyclicality than SARIMA model.

Soil Movement Monitoring System Based on IoT using Fuzzy Logic

Landslide is one of the disasters that often occurs in several areas in Indonesia, especially in hilly areas, valleys, and volcanoes. Soil conditions in some parts of Indonesia are classified as prone to landslides. The latest data from the Central Statistics Agency related to landslides in 2018 occurred as many as 10,246 events with the highest incidence on the island of Java IoT-based ground motion monitoring using fuzzy logic is a tool that is able to detect ground movements that can trigger landslides. The manufacture of this tool is based on the ig-norance of the community in predicting the occurrence of landslides. To avoid this, an early warning tool is needed in the delivery of information that is easily understood by anyone, especially the public. This tool consists of a Microcontroller, Weather Sensor, Rain Sensor, Ground Movement Sensor, and GSM Shield as well as programs to make it hap-pen. This system was created to provide information to the public directly in land-slide-prone areas. With this early warning system, it is hoped that people who are in landslide-prone loca-tions will know more quickly and can monitor the condition of landslide-prone areas so that they will be more alert to possible dangers that come suddenly, especially fatalities, can be minimized. Through this tool can also be known when the weather is cloudy, raining as well as movement or signs of ground movement, can be monitored and monitored automatically. directly by everyone from mobile phones through "SIPEGERTA" Land Movement System in Wonosalam District, Jombang Regency

Integrated System for Evaluation of Implementation of Internal Quality Audits and ISO 9001; 2015 Case Study : Universitas Pembangunan Nasional “Veteran” Jawa Timur

The Internal Quality Assurance System (SPMI) is a system to ensure quality in the process of providing education. All components in the process of providing education support the achievement of aspects of SPMI. An important role in SPMI is the scope of the study program (Prodi), faculties, Institute for Learning Development and Quality Assurance (LP3M), and reviewers. Study program/faculty as SPMI document compiler. LP3M acts as system manager and decision maker at SPMI. Reviewers as assessors who assess the results of the SPMI study program documents. In SPMI activities, study programs / faculties fill out the required form files. Then the reviewer can evaluate the completed file with a score from 1 to 4. However, the evaluation process which is also called Internal Quality Audit (AMI) is still manual. This makes it less easy for LP3M managers to monitor evaluation values ​​and make decisions. From the description above, this proposal proposes a system that can perform an integrated evaluation of AMI online. Not only focusing on AMI, SITEPAMIS can also conduct evaluations to meet ISO 9000;2015. ISO 9000;2015 is a standard for quality management. This research is divided into two years. In the first year, the creation of a web technology-based system with evaluation features of AMI and ISO 9000;2015 values ​​until the implementation process. The output of this stage is a SITEPAMIS web application, reputable national journals, national seminars, and copyrights. In the second year, the mobile version of SITEPAMIS was started. The output of this stage is a SITEPAMIS mobile application, international journals, international seminars, and textbooks, so that at the end of the research results in an Integrated System Application for Evaluation of Internal Quality Audit Implementation and an ISO version of SITEPAMIS which is purely Web-based.

Negative Binomial Time Series Regression – Random Forest Ensemble in Intermittent Data

Intermittent dataset is a unique data that will be challenging to forecast. Because the data is containing a lot of zeros. The kind of intermittent data can be sales data and rainfall data. Because both sometimes no data recorded in a certain period. In this research, the model is created to overcome the problem. The approach that is used in this research is the ensemble method. Mostly the intermittent data comes from the Negative Binomial because the variance is over the mean. We use two datasets, which are rainfall and sales data. So, our approach is creating the base model from the time series regression with Negative Binomial based, and then we augmented the base model with a tree-based model which is random forest. Furthermore, we compare the result with the benchmark method which is The Croston method and Single Exponential Smoothing (SES). As the result, our approach can overcome the benchmark based on metric value by 1.79 and 7.18.

Analysis and Development of KEBI 1.0 Checker Framework as an Application of Indonesian Spelling Error Detection

At educational institutions, especially at University, writing scientific papers is a skill that must be possessed by academics such as educators and students. However, writing scientific papers is not easy, there are many provisions and rules that need to be fulfilled. Several studies show that there are still many academics who make mistakes in writing their scientific papers. Some of the mistakes made include punctuation errors, typographic writing errors and the use of non-standard words in Indonesian. Researchers in Indonesia have developed various spelling error detection applications in Indonesian-language scientific papers. This study tries to analyze the development of an application framework for detecting Indonesian spelling errors from various assessment indicators. This study tries to compare the application framework for detecting spelling errors between other studies with proposed application that named KEBI 1.0 Checker. KEBI 1.0 Checker as a spelling error detection application has 3 main features, namely detecting errors in the use of punctuation marks, writing typography, and using non-standard words in accordance with the standards of the Big Indonesian Dictionary and the General Guidelines for Indonesian Spelling. In addition, this study tries to objectively examine the complexity of the features, advantages and disadvantages, methods and the level of accuracy of each application. The results of the analysis show that KEBI 1.0 Checker has the completeness of features, fast computation time, easy application access, and an attractive user interface. However, it is still necessary to improve the precision in correcting spelling errors in typographic words.

Visitor Forecasting Wisata Bahari Lamongan (WBL) Using Hybrid Particle Swarm Optimization (PSO) and Seasonal ARIMA

The revenue of city is determined by some factors, one of them is tourism sector. A problem of tourism sector is forecasting visitors Wisata Bahari Lamongan (WBL). Because data of the number of visitors WBL are fluctuating and seasonal, then it is required Seasonal ARIMA method. In the Seasonal ARIMA method, there are some parameters that should be optimized for producing forecasting with small mean square error (MSE). In this research, Seasonal ARIMA parameters will be optimized by Particle Swarm Optimization (PSO). PSO is optimization algorithm inspired by behavior of birds group in searching food. Based on simulation results, PSO algorithm can optimize Seasonal ARIMA parameter which is optimal and it can produce forecasting result with small MSE.

Word Search on the "SITUK" Application Using the Levenshtein Distance Algorithm

Integrated System for Online Competency Certification Test (SITUK) is an application used to carry out the assessment process (competency certification) at LSP (Lembaga Sertifikasi Profesional) UPN (University of Pembangunan Nasional) “Veteran” Jawa Timur, each of which is followed by approximately five hundred (500) assessments. Thus the data stored is quite a lot, so to find data using a search system. Often, errors occur in entering keywords that are not standard spelling or typos. For example, the keyword "simple," even though the default spelling is "simple." Of course, the admin will get incomplete information, and even the admin fails to get information that matches the entered keywords. To overcome the problems experienced in conducting data searches on the SITUK application, we need a string search approach method to maximize the search results. One of the algorithms used is Levenshtein which can calculate the distance of difference between two strings. Implementation of the Levenshtein algorithm on the data search system in the SITUK application has been able to overcome the problem of misspelling keywords with the mechanism of adding, inserting, and deleting characters.

Model Selection For Forecasting Rainfall Dataset

The objective of this research is to obtain the best method for forecasting rainfall in the Wonorejo reservoir in Surabaya. Time series and causal approaches using statistical methods and machine learning will be compared to forecast rainfall. Time series regression (TSR), autoregressive integrated moving average (ARIMA), linear regression (LR), and transfer function (TF) are used as a statistical method. Feedforward neural network (FFNN) and deep feed-forward neural network (DFFNN) is used as a machine learning method. Statistical methods are used to capture linear patterns, whereas the machine learning method is used to capture nonlinear patterns. Data about hourly rainfall in the Wonorejo reservoir is used as a case study. The data has a seasonal pattern, i.e. monthly seasonality. Based on the cross-validation and information criteria, the results showed that DFFNN using the time series approach has a more accurate forecast than other methods. In general, machine learning methods have better accuracy than statistical methods. Furthermore, additional information is obtained, through this research the parameter that best to make a neural network model is known. Moreover, these results are also not in line with the results of M3 and M4 competition, i.e. more complex methods do not necessarily produce better forecasts than simpler methods.

Selection of Notification Based on Priority Scale with Fuzzy Algorithm

Notification is one method that works as a marker that there is information waiting to be read. But along with the times, notifications are increasingly filled with information that is considered less important for device users. So there needs to be a breakthrough to overcome this. This study aims to design a system that can help users sort out notifications that are considered important. It is proven that the system can sort notifications based on the given metrics.