Browsing by Author "Bahri, Zaiful"

Now showing 1 - 20 of 27
  • No Thumbnail Available
    Item
    ANALISIS SENTIMEN TWITTER TERHADAP KENAIKAN HARGA BAHAN BAKAR MINYAK INDONESIA MENGGUNAKAN METODE SUPPORT VECTOR MACHINE
    (Elfitra, 2023-03) Adhawiyah, Rosa; Bahri, Zaiful
    Sentiment analysis is a process that aims to determine positive or negative polarity. Twitter, as a social media platform, is used as a space for public information and opinions in responding to issues, including the increase in fuel prices. The government officially increased fuel prices, which was met with criticism from the public. This study aims to categorize the sentiment polarities of the public and determine the accuracy level in sentiment analysis. The method used in this study is Support Vector Machine with linear, RBF, polynomial, and sigmoid kernels, with the linear kernel being obtained as the best kernel. Based on the results of the testing done on sentiment data related to the increase in fuel prices in Indonesia on Twitter, which consists of 1130 data (485 positive and 645 negative), evaluation was done using a confusion matrix to see how well the model can classify correctly. The results show that the Support Vector Machine method produces an accuracy rate of 88.49%.
  • No Thumbnail Available
    Item
    ANALISIS TATA KELOLA TEKNOLOGI INFORMASI PADA “AMIK TRI DHARMA” PEKANBARU MENGGUNAKAN COBIT 2019
    (Elfitra, 2022-07) Pratama, M.Ikhwan; Bahri, Zaiful
    Information Technology (IT) is an important part of an educational institution, including AMIK Tri Dharma. IT is here used as a tool to be able to achieve the expected goals, vision and mission therefore it is important for AMIK Tri Dharma to evaluate or analyze how the current system is running. AMIK Tri Dharma Pekanbaru currently does not have a regular assessment of how mature the current system is so it is not known which areas can be improved and maintained to optimize the current IT Governance. The COBIT Governance analysis here uses the latest COBIT Framework, the 2019 version in the Alignment and plan organize (APO) domain focusing on the APO 02 sub domain. This domain is based on an agreement with AMIK Tri Dharma. Data collection techniques in this study were interviews and direct observation. Generates Capability level 1 which means Gap two levels below the set target. The expected target is at level 3 but the capability of the current system is at level 1. AMIK Tri Dharma has never implemented the COBIT framework and does not have a reference for improvement recommendations and the management is not organized in this organization. Based on these findings, recommendations for improvements to Governance at AMIK Tri Dharma are given.
  • No Thumbnail Available
    Item
    Aplikasi Graph Dalam Masalah Arus Maksimum Pada Network Aktifiti
    (2015-04-08) Agusni; Bahri, Zaiful
    Suatu Graph dapat dipergunakan sebagai model suatu network dari saluran dimana beberapa komoditas diangkut dari suatu tempat ke tempat lain. Masalah umum dalam network transportasi semacam ini adalah memaksimumkan arus biaya dari suatu arus yang telah ditctapkan. Dalam penelilian ini akan diteliti bagaimana masalah network aktifiti tranpsortasi dapat diformulasi dan diselesaikan melalui graph.
  • No Thumbnail Available
    Item
    ATURAN ASOSIASI MENGGUNAKAN ALGORITMA APRIORI UNTUK MENDAPATKAN POLA TRANSAKSI (STUDI KASUS : HOTEL D’LIRA)
    (Elfitra, 2022-07) Mel, Lutfi Agusta; Bahri, Zaiful
    Hotel is one of the accommodation which is important element in tourism. D'Lira hotel is one of the hotels in Pekanbaru City, Riau. However, D'Lira hotel has a high probability of losing customers. Therefore, the hotel requires recommendation of business strategies that can be obtained from transaction data which is usually stored in the database. A collection of room rent transaction data can be obtained the information in the form of transaction patterns. The transaction pattern will be the basis of formulating strategic recommendations for owner representative of D'Lira hotel. Research is conducted on 3204 transactions data from January-December 2021 with the value of minimum support 2% and minimum confidence 60% used python programming language. The attribute data used are 6 items, namely room types with the bed sizes, extra bed, breakfast package, gender, regional origin, and customer profession. This research results in 6 association rules where if the hotel customers is apparatus/state official and rent a deluxe room with double bed, then the customers is male with a support value 8.24% and a confidence value 60.41%. The results of these association rules can be used as a strategic recommendations that are appropriate for the hotel and expect to overcome the hotel problems and gain more income that will be obtained by D'Lira hotel.
  • No Thumbnail Available
    Item
    DETEKSI OBJEK PENGENALAN TINGKAT KEMATANGAN TANDAN BUAH SEGAR KELAPA SAWIT MENGGUNAKAN CENTERNET BERBASIS ANDROID
    (Elfitra, 2023-06) Satria, Muhamad Ilsyam; Bahri, Zaiful
    The maturity level of oil palm Fresh Fruit Bunches (FFB) is a determining factor for the quality of Crude Palm Oil (CPO). The sorting method after harvest or before entering the boiling process is generally done manually relying on vision and experience. This method is prone to subjective errors. Imaging methods are developing rapidly due to advances in computers and image processing techniques, particularly for sorting and grading systems. CenterNet is an architecture for object detection that is significantly enhanced with the help of deep learning, CenterNet is a method for exploring the center of a geometric grid. Plus a keypoint. This study used 18,000 FFB image data, the model can detect the maturity level of oil palm from five maturity levels, namely ripe 1 in the black-red color category, ripe 2 in the red color category, ripe 3 in the red-yellow color category, in the yellow-orange category, and tanko with gray color category. The performance of the results of the model has an accuracy rate of 88%.
  • No Thumbnail Available
    Item
    KLASIFIKASI BERITA MENGGUNAKAN SUPPORT VECTOR MACHINE UNTUK MENGETAHUI JENIS KONTEN E-GOVERNMENT
    (2020-10) Erlinda, Ella; Bahri, Zaiful
    The development of technology today has provided a lot of convenience, one of which is in terms of the spread of news. Now, news delivery can be through the website. The website makes it easy for people to access news and makes it easier for news service providers to spread the word. This ease also results in the increase of news text documents so that it takes the process of extracting information from a large set of data into usable information. The extracting process can be done by utilizing text mining. This research aims to classify documents using the Support Vector Machine (SVM) method on the e-Government website managed directly by KEMKOMINFO-RI. Stages in this study include data collection, data preprocessing, TF-IDF weighting, classification with Support Vector Machine (SVM) and evaluation using confusion matrix. Based on the results of the study, it was obtained that SVM method can be implemented well in the classification of news categories with the highest performance results namely the amount of training data more than testing data in the first data sharing scenario with a data training ratio and testing data of 90% : 10% with a classification accuracy score of 100% including the excellent classification group
  • No Thumbnail Available
    Item
    LAYANAN AKADEMIK MENGGUNAKAN METODE FORWARD CHAINING BERBASIS APLIKASI CHATBOT (STUDI KASUS: SMK NEGERI 2 PEKANBARU)
    (Elfitra, 2023-10) Putra, Rafi Perdana; Bahri, Zaiful
    A chatbot is a digital communication application that has the potential to facilitate users in finding information. The limitation of oral communication has been one of the challenges for the academic staff at SMK Negeri 2 Pekanbaru in obtaining information such as scholarships, internship programs, E-repor, and others. This research uses the forward chaining method. With this method, the chatbot can provide answers related to the services of SMK Negeri 2 Pekanbaru based on the collected facts. There are 8 categories in this research that will be incorporated into the application system using forward chaining reasoning techniques. The results of this research show that the forward chaining method has been successfully applied to the academic service chatbot, providing information based on the responses given by the chatbot.
  • No Thumbnail Available
    Item
    MENENTUKAN POLA PENJUALAN ALAT KESEHATAN MENGGUNAKAN ALGORITMA APRIORI (STUDI KASUS: ALKES JANTRA)
    (Elfitra, 2022-01) Iasya, Shania; Bahri, Zaiful
    The amount of competition, especially in the medical device industry, requires medical device owners to find a strategy in order to increase sales of medical devices, namely by knowing the sales pattern of medical device products so that owners can implement appropriate steps to increase selling power. Sales data can be used to determine sales patterns of medical devices. Sales data can be processed into information by applying data mining methods with association rule techniques with apriori algorithms. Processing of medical device sales data of 840 transaction data with a minimum support of 8 and a minimum confidence of 20% resulted in 33 association rules. In the lift ratio test, there were 28 association rules with a value of more than 1, meaning that there was a dependency between the antecedent and the consequent so that the rule can be used as a prediction for the emergence of a medical device due to the emergence of other medical devices and can be used as a reference in product recommendations for medical devices.
  • No Thumbnail Available
    Item
    NORMALISASI PLAT NOMOR KENDARAAN DENGAN MEKANISME DESKEW
    (2014-05-22) Bahri, Zaiful
    This paper discusses a normalization of a number plate of vehicle with deskew mechanism. The fundamental problem of this mechanism is to determine an angle, under which the plate is skewed. Then the plate was evaluated for normalized (deskew) with a transformation. Matlab is used to implement and simulate this mechanism
  • No Thumbnail Available
    Item
    OPTIMASI PENUGASAN KARYAWAN MENGGUNAKAN ALGORITMA HUNGARIAN (STUDI KASUS: HOLLYWOOD STUDIO)
    (Elfitra, 2022-10) Hidayatullah, Muhammad Rasyid; Bahri, Zaiful
    Placement of employee duties in each type of work is one of the problems that often occurs in a company. The assignment problem is one of the linear programming. Common assignment problems include n tasks that must be assigned to m employees, where each employee has different competencies in completing a task. Hollywood Studio is a business that is engaged in photography services and there are problems regarding the processing time which feels long and inefficient. One of the methods used to solve this assignment problem is to use the Hungarian algorithm. The aims of this study are to optimize employee assignments in terms of minimum work completion time to see the occurrence of work time efficiency before and after using the Hungarian algorithm and to make a web-based job assignment optimization calculation program using the Hungarian algorithm. Data used in this study was collected by taken directly to the field, in the form of data on the completion time of each type of work carried out by each employee from July 4 to August 6, 2022, totaling 133 data. The result of the calculation before using the Hungarian algorithm is 50.4 minutes and the calculation after using the Hungarian algorithm is 42 minutes, resulting in an efficiency of 8.4 minutes of work completion and system design using Unified Modeling Language (UML) which consists of use cases, classes diagrams, activity diagrams, and sequence diagrams.
  • No Thumbnail Available
    Item
    PENDETEKSI PLAGIAT PADA PROPOSAL SKRIPSI MAHASISWA FMIPA UNIVERSITAS RIAU MENGGUNAKAN ALGORITMA BOYER MOORE BERBASIS WEB
    (2020-08) Sandi, Mezi Mei; Bahri, Zaiful
    The process of selecting thesis proposal titles submitted manually by Information System Department’s students in University of Riau is considered to be less effective and efficient because the number of student thesis titles will increase every year. The purpose of this study is to facilitate the mechanism by detecting similarities plagiarism in the title of the documents using Boyer Moore's algorithm and supported by Text Preprocessing, TF and Cosine Similarity method. This system was developed using python programming language with MySQL as the database server and UML as the system design. The result obtained from this study was a similarity percentage from the thesis proposal title submitted against the existing thesis titles in which the higher the percentage indicated, the higher the degree of similarity between the two titles.
  • No Thumbnail Available
    Item
    PENDUKUNG KEPUTUSAN PENENTUAN GURU SEKOLAH DASAR BERPRESTASI TINGKAT KABUPATEN SIAK MENGGUNAKAN METODE PERBANDINGAN EKSPONENSIAL BERBASIS WEB
    (2020-11) Sintia, Yunike; Bahri, Zaiful
    The Exponential Comparison Method (MPE) is one method for determining the priority order of alternative decisions in the plural. This technique is used as a helper for individual decision-making to use a well-defined model design at the process stage. Determination of district-level high achieving elementary school teachers using a decision support system created aims to design a computer-based system to determine the best value of the tests conducted by the committee of achieving teachers using the exponential comparison method. Where the criteria and sub-criteria become requirements to carry out the calculation process in the case study. This system was developed using PHP and HTML programming languages and is accompanied by MySQL as a database that is tailored to the needs of the system design process. The things contained in this system include various information such as information on criterion data, sub-criteria data, prospective teacher data and detailed results of calculations.
  • No Thumbnail Available
    Item
    PENERAPAN ALGORITMA FUZZY HUNGARIAN UNTUK OPTIMALISASI PENUGASAN PEKERJA DENGAN MELIBATKAN SEGITIGA FUZZY PADA PONDOK JAMUR MADANI
    (Elfitra, 2023-10) Shabrina, Mutya; Bahri, Zaiful
    Assignment problems can affect a company's ability to produce products, if not handled properly it will reduce productivity and even hinder the company's growth. Pondok Jamur Madani is a mushroom cultivation business that produces oyster mushrooms. The production process starts from preparing the planting medium, nursery, maintenance, and harvesting. Inaccurate placement of workers is one of the causes of the lack of efficiency in mushroom production time, therefore it is necessary to optimize the assignment of workers using the Fuzzy Hungarian algorithm. This study aims to obtain optimal assignments by finding the minimum work completion time in order to see time efficiency before and after using the Fuzzy Hungarian algorithm and create a web-based assignment calculation program to calculate the optimization of work completion time using the Fuzzy Hungarian algorithm. The assignment system is designed using the PHP programming language with data flow design using the Unified Modeling Language (UML) which consists of Use Case Diagrams, Class Diarams, and Sequence Diagrams. The data used is primary data in the form of completion time for each type of work by each worker taken from 22 March to 9 June 2023, totaling 80 data. The results of calculation using Fuzzy Hungarian show that there is an efficiency of 4.4 hours with a total time before using the Fuzzy Hungarian algorithm is 30.4 hours and the total time after using the Fuzzy Hungarian algorithm is 26 hours.
  • No Thumbnail Available
    Item
    PENERAPAN DATA MINING UNTUK MEMPREDIKSI PENJUALAN PRODUK BENIH TERLARIS MENGGUNAKAN METODE NAÏVE BAYES
    (Elfitra, 2023-02) Bangun, Nurul Aini Br; Bahri, Zaiful
    PT. Citra Seeds, Karo Asia Regency, is a company that sells horticultural plant seeds. Seed buyers come from various regions in Karo Regency, because farming activities are the majority of the people's work there. PT Benih Citra Asia does not have a sales strategy so there is often a problem of out of stock which of course if no solution is found it can cause a decrease in the sales chart. In addition, sales data is also increasing, this can be a solution in overcoming the problems faced. Therefore, a data mining process was carried out using the Naïve Bayes method on the sales data of PT. Asian Citra Seeds. The initial data obtained were 507 data, after cleaning the data produced 484 data. From the 484 data, the preprocessing and implementation stages of Naïve Bayes were carried out. Initial accuracy obtained in this study is 52,58%. To improve research accuracy, K-fold Cross Validation was used, with the highest accuracy value being in the 2nd iteration with an accuracy value of 72.51%, 80.49% precision and 89.19% recall. The best-selling product results obtained from this research are Natavi products
  • No Thumbnail Available
    Item
    PENERAPAN METODE TOPSIS DAN SIMPLE ADDITIVE WEIGHTING SEBAGAI SISTEM PENDUKUNG KEPUTUSAN UNTUK MENERIMA BANTUAN OPERASIONAL SEKOLAH
    (2020-11) Fransisco, G. Hartono; Bahri, Zaiful
    According to UUD 1945, Indonesia government has mandated to give educational access to the all people.. This assistance is usually in the form of funds to support costs or expenses incurred by students during their education. With this assistance, it is hoped that students can complete their education without any disturbances, especially those related to student finances until they complete or graduate at the education level. It is hoped that the SAW and TOPSIS methods can help speed up the selection of BOS fund recipients, and the system can unravel mistakes so that it can be a decision used by schools in the process of providing scholarships to their students.
  • No Thumbnail Available
    Item
    PENGUKURAN KUALITAS LAYANAN WEBSITE PEMERINTAH KOTA PEKANBARU BERBASIS WEB MENGGUNAKAN METODE WEBQUAL 4.0
    (Elfitra, 2021-12) Suprayogi, Pandu; Bahri, Zaiful
    Pekanbaru City is currently developing rapidly in urban development and governance. In accordance with the vision and mission of the Mayor of Pekanbaru, namely the realization of Pekanbaru as a smart civil city, improvements are needed in the form of services. Technological advances make it easier to communicate freely, without being limited by space, distance and time, so the role of the website is very supportive of technological advances in the city of Pekanbaru. For this reason, it is necessary to evaluate the website services owned by the city government. The method used is webqual 4.0, which is measuring based on end user perceptions. There are three aspects that will be assessed by end users, namely from the aspect of usability, information quality and interaction quality. Data analysis uses Importance Performance Analysis (IPA), which is a measurement of the level of conformity to find out how much users are satisfied with the performance of the website. After taking measurements, one aspect that needs to be improved by the Pekanbaru City Communications, Informatics, Statistics and Encoding Department was found, namely providing fairly detailed information. Improvements need to be made because these aspects have a high importance but the performance is not satisfactory and the level of conformity is 91.5%, it can be concluded that users are satisfied with the performance of the website and service providers are considered to have understood what users want.
  • No Thumbnail Available
    Item
    PERAMALAN PERSEDIAAN OBAT PADA APOTEK SINAR ABADI MENGGUNAKAN METODE EXPONENTIAL SMOOTHING
    (Elfitra, 2022-03) Lase, Jasmarianus; Bahri, Zaiful
    Forecasting is estimating the situation in the future through past circumstances. Forecasting aims to minimize losses that will occur in the future by applying methods related to forecasting. Sinar Abadi Pharmacy is one of the pharmacies that sells and has a stock of medicines. Drug supplies are very important for a pharmacy to meet consumer or customer needs and support smooth business management at Sinar Abadi Pharmacy. Drug supplies that are too piled up are not a little cost borne for the procurement of drugs. Inventories of drugs that are too little also cannot met the needs of consumers or customers. Therefore, it is necessary to have a drug supply forecast system at Sinar Abadi Pharmacy. Made a Drug Inventory Forecast system at the Sinar Abadi Pharmacy aims to predict drug inventory at the pharmacy and to design and create an information system for forecast drug inventory to assist the work management of Sinar Abadi Pharmacy in obtaining drug inventory information based on the results of forecast past drug sales used the Triple Exponential Smoothing from Brown. Method Triple Exponential Smoothing from Brown very suitable for made forecasted things that fluctuated or experienced tidal waves, meant that the increased or decreased in the amounted of data usually occurred suddenly and is difficult to determined. The method stepped carried out in this studied are needed analysis, data collection, data analysis, and forecasted used the Triple Exponential Smoothing. Next, designed the system used the Unified Modeling Language (UML), which consisted of designed a system used Unified cased diagram, class diagrams, activities diagrams, and sequences diagrams. The forecasted resulted obtained from this studied are the resulted of the forecasted of the Triple Exponential Smoothing on Acetylcysteine is founded at alpha 0.1 with a valued of 48 and the lowest levelled of accuracy for forecasted based on MAPE is 42%.
  • No Thumbnail Available
    Item
    PREDIKSI PRESTASI AKADEMIK MAHASISWA FMIPA UNIVERSITAS RIAU MENGGUNAKAN ALGORITMA K-NEAREST NEIGHBOR BERBASIS WEB
    (2021-03) Lattivah, Zakyatul; Bahri, Zaiful
    This study aims to predict the academic achievement of FMIPA Riau University students using the K-Nearest Neighbor algorithm. The results of the predictions are achievement in terms of the category of cumulative grade point average (IPK) "High" or "Low", this is because new students cannot know their estimated future achievements, so with this prediction system new students can see their achievement predictions. in the future (sixth semester) by looking at the school of origin majors, the average national exam, college motivation, and work at the beginning of college which can be used as a reference and motivation for maximum achievement. The system is designed using the PHP programming language and the database server uses MySQL and the system design uses UML. The comparison of training data and test data is 70%: 30%. The results obtained from this study get an average level of accuracy of 80%.
  • No Thumbnail Available
    Item
    SISTEM DETEKSI TINGKAT KEMATANGAN TANDAN BUAH SEGAR KELAPA SAWIT MENGGUNAKAN METODE CONVNET BERBASIS ANDROID
    (Elfitra, 2022-06) Wardana, Fiqra; Bahri, Zaiful
    One of the oil palms harvesting processes is to determine the maturity level of Fresh Fruit Bunches (FFB). FFB maturity is one of the determinants quality productions of palm oil processing materials. In general, FFB maturity can be checked manually by farmers by direct observation. Manual selection of FFB, of course, requires time and experienced farmers to be able to determine maturity correctly. ConvNet is a machine learning method that can be used to quickly determine the maturity level of oil palm FFB. ConvNet allows the model to recognize the shape, color, and edge of each TBS training data. Using 900 FFB image data, the model can detect the maturity level of oil palm from three classes, namely raw, ripe, and empty bunches. The results of the training model have an accuracy of 86% with a precision and recall of more than 90%.
  • No Thumbnail Available
    Item
    SISTEM DETEKSI TINGKAT KEMATANGAN TANDAN BUAH SEGAR KELAPA SAWIT MENGGUNAKAN METODE CONVNET BERBASIS ANDROID
    (Elfitra, 2022-06) Wardana, Fiqra; Bahri, Zaiful
    One of the oil palms harvesting processes is to determine the maturity level of Fresh Fruit Bunches (FFB). FFB maturity is one of the determinants quality productions of palm oil processing materials. In general, FFB maturity can be checked manually by farmers by direct observation. Manual selection of FFB, of course, requires time and experienced farmers to be able to determine maturity correctly. ConvNet is a machine learning method that can be used to quickly determine the maturity level of oil palm FFB. ConvNet allows the model to recognize the shape, color, and edge of each TBS training data. Using 900 FFB image data, the model can detect the maturity level of oil palm from three classes, namely raw, ripe, and empty bunches. The results of the training model have an accuracy of 86% with a precision and recall of more than 90%.