Claim Missing Document
Check
Articles

Found 9 Documents
Search

Typo Checking Menggunakan Algoritma Rabin-Karp Irma Surya Kumala Idris; Yasin Aril Mustofa
Jambura Journal of Electrical and Electronics Engineering Vol 4, No 1 (2022): Januari - Juni 2022
Publisher : Teknik Elektro - Universitas Negeri Gorontalo

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (459.948 KB) | DOI: 10.37905/jjeee.v4i1.12150

Abstract

Kesalahan pengetikan merupakan hal yang biasa terjadi ketika membuat tulisan, misalnya  ketika membuat karya ilmiah, buku maupun lainnya. Kesalahan penulisan kata memang hal yang biasa terjadi tetapi dapat berakibat buruk sehingga perlu dilakukan pemeriksaan kata terhadap tulisan pada dokumen yang dibuat. Typo checking merupakan proses pemeriksaan kata yang dilakukan untuk mendeteksi kesalahan penulisan kata dan memberikan kandidat kata yang benar.  Pemeriksaan kesalahan penulisan membutuhkan waktu lama jika dilakukan secara manual, sehingga dibuat aplikasi untuk mendeteksi kesalahan penulisan kata menggunakan Algoritma Rabin-Karp, dengan mencocokkan string berdasarkan nilai hash pada teks dan pattern. Proses Pengecekan Penulisan Kata dilakukan dengan menghitung sampai indeks akhir dan didapatkan hasil seperti kata dan nilai hash. Proses hashing menggunakan modulo (sisa bagi) sebesar 107 dengan nilai k-gram k=3 pada setiap kata asal dan kata hasil. Proses hashing dilakukan dengan cara mengkonversi string menjadi nilai ASCII, sehingga diperoleh nilai hash a-z = 79-122. Berdasarkan hasil perhitungan manual yang telah dilakukan, jika terdapat kesalahan pengetikan akan diperoleh nilai hashing yang berbeda antara kata asal dan kata yang dihasilkan.   Typing errors are common when writing, for example, when writing scientific papers, books, and others. Word writing errors are common but can have bad consequences, so it is necessary to check the words on the writing in the document that is made. Typo checking is a word checking process that is carried out to detect word writing errors and provide the correct word candidate. Checking writing errors takes a long time if done manually, so an application is made to detect word writing errors using the Rabin-Karp Algorithm, by matching strings based on hash values in text and patterns. The process of Checking Word Writing is done by counting to the final index and getting results such as words and hash values. The hashing process uses a modulo (remaining for) of 107 with a value of k-gram k=3 for each word of origin and word of the result. The hashing process is done by converting the string into an ASCII value so that the hash value a-z = 79-122. Based on the results of manual calculations that have been carried out, if there are typing errors, a different hashing value will be obtained between the original word and the resulting word.
Optimasi Pendistribusian Barang Menggunakan Algoritma Artificial Bee Colony Irma Surya Kumala Idris
Jurnal Informatika Upgris Vol 5, No 2: Desember (2019)
Publisher : Universitas PGRI Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26877/jiu.v5i2.4608

Abstract

Distribution of goods is one of the important problems for a company. The spread of the customer location and the number of route choices and the absence of an information system application to determine the closest route, have an impact and influence on the distribution process. Delivery of goods carried out on time will increase customer satisfaction. The choice of route in distribution has an effect on the cost and time of travel, where the farther the distance traveled in the delivery of goods will lead to long delivery times resulting in delays in distribution and operational costs will be higher. Based on the settlement, optimization of the distribution process of goods is carried out. This study uses the Artificial Bee Colony algorithm to assist in finding the shortest route. The Artificial Bee Colony algorithm is an optimization algorithm that is considered quite good in the process of finding the shortest route.
Monitoring Fasilitas Pertamanan Kota Gorontalo Berbasis Sistem Informasi Geografis Irma Surya Kumala Idris; Yasin Aril Mustofa
Jurnal Informatika Upgris Vol 7, No 1: JUNI 2021
Publisher : Universitas PGRI Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26877/jiu.v7i1.5858

Abstract

City Park is part of the city's green open space, its existence has the meaning of securing natural ecosystems that have a great influence on the existence and survival of the city itself. The number of city parks in the city of Gorontalo also requires little cleaning and maintenance personnel. To find out the performance of officers in the field, we need a system that is able to monitor the results of the work, making it easier for the relevant offices to control the conditions, facilities and functions of the city park. This research is intended to build a geographic information system that will be used for monitoring park facilities equipped with related information that is easily accessible by the local government, especially the City Planning and Landscaping Office of Gorontalo City. This study uses the programming language PHP (PHP: Hypertext Preprocessor) and MySQL database, using descriptive methods, then implement this design to find out and measure the level of ease, speed of information, and accuracy of information. The results of the study based on the data obtained were then tested using the White Box Testing method and Bases Path Testing. From the data obtained then a flowgraph design was made. Flowgraph that is tested is the process of finding a location of a garden. From the results of the calculation of the White Box Testing and Bases Path Testing test methods, the results of the calculation results obtained that have met the requirements in terms of software feasibility. Based on the results of testing with the White Box Testing, and Base Path Testing method above, it can be concluded that true system logic can produce a system that is effective and efficiently logically, and is expected to facilitate the processing of said data.
Pendekatan Machine Learning yang Efisien untuk Prediksi Kanker Payudara Azminuddin I. S. Azis; Irma Surya Kumala Idris; Budy Santoso; Yasin Aril Mustofa
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 3 No 3 (2019): Desember 2019
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (881.95 KB) | DOI: 10.29207/resti.v3i3.1347

Abstract

Breast Cancer is the most common cancer found in women and the death rate is still in second place among other cancers. The high accuracy of the machine learning approach that has been proposed by related studies is often achieved. However, without efficient pre-processing, the model of Breast Cancer prediction that was proposed is still in question. Therefore, this research objective to improve the accuracy of machine learning methods through pre-processing: Missing Value Replacement, Data Transformation, Smoothing Noisy Data, Feature Selection / Attribute Weighting, Data Validation, and Unbalanced Class Reduction which is more efficient for Breast Cancer prediction. The results of this study propose several approaches: C4.5 - Z-Score - Genetic Algorithm for Breast Cancer Dataset with 77,27% accuracy, 7-Nearest Neighbor - Min-Max Normalization - Particle Swarm Optimization for Wisconsin Breast Cancer Dataset - Original with 97,85% accuracy, Artificial Neural Network - Z-Score - Forward Selection for Wisconsin Breast Cancer Dataset - Diagnostics with 98,24% accuracy, and 11-Nearest Neighbor - Min-Max Normalization - Particle Swarm Optimization for Wisconsin Breast Cancer Dataset - Prognostic with 83,33% accuracy. The performance of these approaches is better than standard/normal machine learning methods and the proposed methods by the best of previous related studies.
Quick Response Code Absensi Guru Menggunakan Secure Hashing Algorithm (SHA) Agriyanto Asiking; Asmaul Husnah N; Irma Surya Kumala Idris
JURNAL TECNOSCIENZA Vol. 6 No. 2 (2022): TECNOSCIENZA
Publisher : JURNAL TECNOSCIENZA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51158/tecnoscienza.v6i2.705

Abstract

Sistem Absensi guru yang diterapkan di sekolah masih dilakukan secara manual, yaitu guru menandatangani buku absen yang telah disediakan. Hal ini dikhawatirkan dapat meningkatkan potensi penyebaran COVID 19 dikarenakan menggunakan peralatan absensi yang sama. Berdasarkan permasalahan tersebut penelitian absensi akan dibuat menggunakan teknologi antara Quick Response Code yang menggunakan Secure Hash Algorithm (SHA) dan Smartphone android sehingga mengurangi kontak fisik atau penggunaan benda yang disentuh oleh banyak orang secara bergantian. Penelitian ini mengimplementasikan algoritma kriptografi SHA-256 untuk pembuatan Quick Response Code absensi. Hasil enkripsi dari SHA-256 akan dikombinasi dengan algoritma BCRYPT untuk menghindari serangan decode hash SHA-256. Pengamanan Quick Response Code dengan menggunakan enkripsi SHA-256 lebih optimal dengan mengkombinasikan fungsi BCRYPT pada Message yang telah dienkripsi SHA-256, sehingga menghindari serangan decode hash SHA-256
Prediksi Penjualan Pertalite Menggunakan Metode Support Vector Regression Rachmawan Sidik Laminullah; Haditsah Annur; Irma Surya Kumala I
Jurnal Cosphi Vol 4, No 1 (2020): Januari-Juli 2020
Publisher : Teknik Elektro - Universitas Ichsan Gorontalo

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (476.786 KB)

Abstract

Bahan Bakar Minyak atau BBM adalah salah satu komoditas sumber daya alam minyak dan gas bumi. Minyak dan gas bumi juga merupakan sumber daya alam yang tak terbarukan dan dikuasai oleh Negara. Kehidupan mayarakat Indonesia saat ini sangat bergantung pada BBM karena pengguna kendaraan bermotor yang semakin lama semakin bertambah banyak sehingga permintaan akan BBM pun makin melonjak. Maka dari itu, sistem prediksi sangat dibutuhkan untuk memprediksi penjualan guna meminimalisir resiko yang ditimbulkan akibat overload stok dan sangat diharapkan untuk dapat meningkatkan omset penjualan di SPBU tersebut. Metode Support Vector Regression adalah salah satu metode yang sering digunakan untuk prediksi data karena menghasilkan hasil akurasi prediksi yang tinggi, namun belum pernah digunakan untuk memprediksi hasil penjualan Pertalite. Tujuan dari penelitian ini adalah untuk mengetahui jumlah penjualan pada hari berikutnya pada SPBU Ulapato. Berdasarkan uji akurasi menggunakan MAPE, metode ini mengasilkan tingkat akurasi sebesar 92,31 % dengan tingkat error sebesar 7.695 %. Dengan demikian aplikasi yang dihasilkan layak untuk digunakan
Identifikasi Kualitas Udang Segar Menggunakan Metode Gray Level Co-Occurance Matrix dan Artificial Neural Network : - Wanda Aprilia Pangemanan; Irma Surya Kumala Idris
Jurnal Ilmiah Ilmu Komputer Banthayo Lo Komputer Vol 1 No 2 (2022): Edisi November (2022)
Publisher : Teknik Informatika Fakultas Ilmu Komputer Universitas Ichsan Gorontalo

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (781.361 KB) | DOI: 10.37195/balok.v1i2.168

Abstract

This study is conducted to know the fresh shrimp quality. In this study, the data collection is through images of shrimp of a variety of sizes and with the number of classes. There are two classes, namely fresh and not fresh. This study is observed independently. The methods used in this study are the Gray Level Co-occurrence Matrix and Artificial Neural Network methods. The performance of using the GLCM and ANN methods in the identification process of fresh shrimp quality indicates a very good performance as proven by the accuracy of 93%, recall of 100%, the precision of 90%, and an F1 score of 95%. Keywords: fresh shrimp quality, GLCM, ANN
Perancangan Game Edukasi Sebagai Media Pelestarian Bahasa Gorontalo Pada Anak Sekolah Dasar Moh. Rifandi R.M; Irma Surya Kumala Idris; Abd. Rahmat Karim Haba
Jurnal Ilmiah Ilmu Komputer Banthayo Lo Komputer Vol 2 No 1 (2023): Edisi Mei 2023
Publisher : Teknik Informatika Fakultas Ilmu Komputer Universitas Ichsan Gorontalo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37195/balok.v2i1.499

Abstract

The learning process using conventional methods does not provide optimal learning outcomes. For optimal learning, the selection of the learning model is very important which is accompanied by the selection of the right learning media. The use of games as learning media is not wrong because games can indirectly provide education. Playing games without educational content may negatively impact children. To achieve optimal learning results, this research takes the initiative to make Gorontalo language educational games that can be played through smartphone media based on the Android operating system. In educational game design, there are two main features, namely the play menu and the learning menu. To be able to complete the game on the play menu, players must capture Gorontalo vocabulary words following the available vocabulary images. While in the learning feature players can learn the vocabulary available in the game. Based on the results of black box testing, the features contained in the Gorontalo Language Educational Game can run properly without any errors occurring. Meanwhile, based on user acceptance testing, the game that has been designed can be accepted by students with a total score of 90.5% in the Very Feasible category.
Klasifikasi Klasifikasi Jenis Buah Tomat Menggunakan Convolutional Neural Network Ahmad; Idris, Irma Surya Kumala; Bode, Andi
Jurnal Ilmiah Ilmu Komputer Banthayo Lo Komputer Vol 2 No 2 (2023): November 2023
Publisher : Teknik Informatika Fakultas Ilmu Komputer Universitas Ichsan Gorontalo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37195/balok.v2i2.617

Abstract

Abstrac ; Some Indonesian people utilize food sources evenly. Tomatoes are known to have very good nutritional content so people can consume them every day. Many species/types of tomatoes have high similarity so it is difficult to distinguish them. Tomato fruit type recognition in this study employs Convolutional Neural Network. The stages of the method used are feature learning and classification. To classify tomato fruit types, the CNN network is trained with image training data. The training process is carried out by looking for a form of model that is following the data to be processed to get the best results. It is also used in the argumentation process on training and validation data so that overfitting does not occur in the CNN network. The experimental results show that the convolutional Neural Network method can recognize tomato types with an accuracy rate of 96.6%, recall of 100%, precision of 96.6%, and an F-1 Score of 96.28% of 30 images using Confusion Matrix testing.   Keywords: classification, tomato fruit type, Convolutional Neural Network