Articles

Found 34 Documents
Search

Rancang bangun sistem pakar diagnosa penyakit tanaman stroberi menggunakan metode certainty factor berbasis web Fajriah, Nina Mauliana Noor; Azhar, Yufis; Marthasari, Gita Indah
Jurnal Repositor Vol 1, No 1 (2019): November 2019
Publisher : Universitas Muhammadiyah Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (16.496 KB) | DOI: 10.22219/repositor.v1i1.18

Abstract

Expert system is one of the AI Development fields. AI (Artificial Intelligence) is part of a computer science which used the computer to imitate the human thoughts and behavior. The usage of a method in Expert System is very important. Thus, the most compatible method to use is the Certainty Factor method. This method is suitable to be used on Expert System to measure things and diagnosed it, will it be very sure or unsure. For example, Expert System to diagnose disease on strawberry plants. This software allows the user to diagnose the disease on strawberry plants before taking a further action. This software is using PHP programming language and store the data using MySQL system database. When the user consulting to the software, the software will show the symptoms of the disease and the user can choose the level of certainty from the chosen disease symptom. The final result from the software is a form which includes the guide of how to take the measurement of the disease based on the chosen symptoms.
Penerapan algoritma C5.0 pada analisis faktor-faktor pengaruh kelulusan tepat waktu mahasiswa Teknik Informatika UMM Pramudita, Andriani Eka; Azhar, Yufis; Rahmayanti, Vinna
Jurnal Repositor Vol 1, No 2 (2019): Desember 2019
Publisher : Universitas Muhammadiyah Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22219/repositor.v1i2.545

Abstract

 Timely graduation of college students is one of the problems that is difficult to overcome by each college, as well as in the Department of Informatics, University of Muhammadiyah Malang. This problem must be resolved immediately, considering the quality of students will affect the accreditation of university and its majors. So, it is necessary to analyze the factors that influence the timely graduation of Informatics Engineering students in UMM. This study uses the C5.0 algorithm to do feature selection and regression analysis to estimate the opportunities of timely graduation. The independent variables used are gender, regional origin, entry status, academic credit system in 4th semester, academic credit system in 6th semester, grade point of 2nd semester, grade point of 4th semester, grade point of 6th semester, grade point average of 2nd semester, grade point average of 4th semester, grade point average of 6th semester, type of senior high school, status of senior high school, parent?s education, and parent?s job. The results of the implementation of the C5.0 algorithm in this study were able to do feature selection by producing 8 out of total 15 features with better accuracy than the value of accuracy using all features. And this study is able to provide a regression model with an accuracy value of 82%. 
Pengelompokan kata berdasarkan kemiripan ucapan pada kamus menggunakan algoritma metaphone pada sistem operasi Android Maryanto, Aditya Dwi; Munarko, Yuda; Azhar, Yufis
Jurnal Repositor Vol 1, No 1 (2019): November 2019
Publisher : Universitas Muhammadiyah Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (426.072 KB) | DOI: 10.22219/repositor.v1i1.7

Abstract

Indonesia is an archipelagic country consisting of various tribes and cultures and different languages. One of them is the Sumbawa language used by the people of the western part of the island of Sumbawa. Sumbawa language has 4 dialects namely Samawa, Taliwang, Jereweh, and Tongo. In Sumbawa there are also homophonic, homonim, and homograph words. Grouping words based on the similarity of speech to the Sumbawa dictionary used Metaphone algorithm on the android operating system is discussed in this study. Metaphone algorithms can be applied to multiple languages with rules that have been modified according to the desired language characteristic. Based on the results of testing the recall and precision on the new rules Metaphone algorithm can be concluded that the grouping of words based on similarity of speech in Sumbawa language can be said to be effective. The average percentage index of the recall test is 98,97% and the precision is 78,52%.
Prediksi harga emas menggunakan univariate convolutional neural network Halimi, Imam; Marthasari, Gita Indah; Azhar, Yufis
Jurnal Repositor Vol 1, No 2 (2019): Desember 2019
Publisher : Universitas Muhammadiyah Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22219/repositor.v1i2.612

Abstract

Investing activities deal with predicting the prices to avoid loss. Advanced technology is required to access various information regarding the fluctuating price everyday even every hour. In the context of this research, investors, especially investors in gold commodities should be able to predict the gold price before making transactions. Hence, investors will be able to buy or sell their stocks precisely. Regarding to those reasons, the researcher is interested in conducting research on the prediction of global gold price which results will be beneficial for investors and broader community to help them making precise decision to buy or sell gold commodities and stocks. Making precise prediction is meant to minimize the chance of making mistakes as it closes the gap between what has been expected and the outcome. Predictions cannot be guaranteed precise, yet predictions might be close to the outcome. In this research, Convolutional Neural Network (CNN) algorithm will be used. CNN belongs to the Deep Learning (DL), a sub field of Machine Learning (ML) in which basic ANN algorithm with more layers is employed. A univariate CNN approach and several tests involving CNN model parameters were administered which results showed the score for model 1 of parameter; filters = 64, kernel = 2, pooling = 2, epochs = 2.000 and dense = 50 and RMSE outcome of 690,40 
METODE HYBRID MAXIMUM TSALLIS ENTROPY DAN HONEY BEE MATING OPTIMIZATION UNTUK PENCARIAN MULTILEVEL THRESHOLD PADA CITRA GRAYSCALE Azhar, Yufis; Maskur, Maskur; Kholimi, Ali S
JUTI: Jurnal Ilmiah Teknologi Informasi Vol 10, No 1, Januari 2012
Publisher : Teknik Informatika, ITS Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (607.459 KB)

Abstract

Thresholding merupakan metode yang cukup populer untuk segmentasi suatu gambar. Untuk mensegmentasi suatu gambar grayscale menjadi gambar biner, bi-level thresholding bisa digunakan. Sedangkan untuk mensegmentasi citra grayscale ke dalam beberapa varian digunakanlah multi-level thresholding. Metode Maximum Tsallis Entropy (MTT) adalah salah satu metode yang bisa digunakan.untuk pencarian multi threshold pada suatu citra grayscale. Akan tetapi metode ini memiliki waktu komputasi yang sangat besar jika jumlah threshold yang dicari semakin banyak. Oleh karena itu, suatu metode baru diusulkan dalam penelitian ini yang merupakan penggabungan antara metode Maximum Tsallis Entropy dan algoritma Honey Bee Mating Optimization (HBMO) untuk mendapatkan multilevel threshold dari suatu citra grayscale dalam waktu yang relatif singkat. Metode penggabungan yang diusulkan ialah dengan memfungsikan algoritma MTT sebagai alat untuk mencari nilai fitness dari suatu individu dalam algoritma HBMO. Semakin baik nilai fitness yang dimiliki oleh individu, semakin baik pula threshold yang ditemukan. Hasil yang didapat dari ujicoba menunjukkan bahwa algoritma hybrid ini mampu mencari multi threshold dengan tingkat akurasi mencapai 98% dan waktu komputasi hingga 10 kali lebih cepat dibandingkan dengan waktu komputasi dari metode MTT untuk mencari 3 level threshold.
Pelabelan Klaster Fitur Secara Otomatis pada Perbandingan Review Produk Rozi, Fahrur; Wijoyo, Satrio Hadi; Isanta, Septiyan Andika; Azhar, Yufis; Purwitasari, Diana
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 1, No 2 (2014)
Publisher : Fakultas Ilmu Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (711.042 KB)

Abstract

Abstrak Penggunaan review produk sebagai suatu sumber untuk mendapatkan informasi dapat dimanfaatkan untuk mengoptimalkan pemasaran suatu produk. Situs belanja online merupakan salah satu sumber yang dapat digunakan untuk pengambilan review produk. Analisa terhadap produk dapat dilakukan dengan membandingkan antara dua buah produk berbeda berdasarkan fitur produk tersebut. Fitur dari suatu produk didapatkan melalui ekstraksi fitur dengan metode double propagation. Fitur yang terdapat dalam sebuah review sangat banyak serta terdapat beberapa kata yang memiliki arti yang sama yang mewakili suatu fitur tertentu, sehingga diperlukan suatu pengelompokan terhadap fitur tersebut. Pengelompokan suatu fitur produk dapat dilakukan secara otomatis tanpa memperhatikan kamus kata, yaitu dengan menggunakan teknik clustering. Hierarchical clustering merupakan salah satu metode yang dapat digunakan untuk pengelompokan terhadap fitur produk. Pengujian dengan metode hierarchical clustering untuk pengelompokan fitur menunjukkan bahwa metode average linkage memiliki nilai recall dan f-measure yang paling tinggi. Sementara untuk pengujian pelabelan menunjukkan bahwa semantic similarity antar fitur lebih berpengaruh dari pada kemunculan fitur di dokumen. Kata kunci: clustering, fitur produk, pelabelan Abstract Product review can be used as a source for acquire information and to optimize the marketing of product. Online shopping sites are one of source that can be used to get product reviews. Analysis of the product can be done by comparing two different products based on product’s features. Features of a product can be obtained through extraction of features with double propagation method. In the product review there are many feature that can be found, and there are some words that have the same meaning which represents a particular feature, so we need a grouping on the feature. Hierarchical clustering is one method that can be used for grouping the features of the product. Based on testing, hierarchical clustering method for grouping feature indicate that the average linkage method has the highest recall and f-measure. As for testing in labeling indicates that the semantic similarity between features is more influential than the appearance of features in the document. Keywords: clustering, features of the product, labeling
SISTEM REKOMENDASI PENYEWAAN PERLENGKAPAN PESTA MENGGUNAKAN COLLABORATIVE FILTERING DAN PENGGALIAN ATURAN ASOSIASI Indah Marthasari, Gita; Azhar, Yufis; Kurnia Puspitaningrum, Dwi
Jurnal Simantec Vol 5, No 1 (2015)
Publisher : Jurnal Simantec

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

ABSTRAKE-commerce berbasis web merupakan salah satu media yang efektif dalam jual beli. Banyak usaha yang telah memanfaatkan fasilitas ini. Salah satunya adalah bidang jasa persewaan alat-alat pesta. Untuk memberikan layanan yang lebih baik, e-commerce dilengkapi dengan fitur lain antara lain sistem rekomendasi. Sistem ini memudahkan konsumen menentukan barang untuk dibeli dengan cara menampilkan produk yang terkait dengan salah satu produk lain yang dibeli atau dilihat konsumen. Salah satu mekanisme untuk membangun sistem ini adalah collaborative filtering. Cara kerja collaborative filtering adalah dengan membangun sebuah basis data yang menyimpan produk-produk yang disukai konsumen. Transaksi baru yang dibuat oleh seorang konsumen akan dicocokkan dengan basis data tersebut untuk mengetahui data historis mana yang paling sesuai dengan data baru tersebut. Data historis yang paling sesuai akan ditampilkan sebagai rekomendasi bagi konsumen yang melakukan transaksi tersebut.Salah satu teknik yang dapat digunakan adalah penggalian aturan asosiasi menggunakan Algoritma Apriori. Pada penelitian ini, dibuat sebuah website persewaan alat-alat pesta dengan menerapkan sistem rekomendasi. Sistem rekomendasi dibangun menggunakan aturan-aturan yang dihasilkan oleh Algoritma Apriori. Untuk dapat menampilkan barang rekomendasi digunakan nilai support 20, sedangkan nilai confidence digunakan untuk menentukan N-teratas barang untuk direkomendasikan.Kata kunci : sistem rekomendasi, collaborative filtering, algoritma apriori. ABSTRACTWeb-based e-commerce is an effective media for buying and selling. Many businesses have taken the advantages of this facility. One of them is the party tools rental services. To provide better service, e-commerce is equipped with other features such as a recommendation mechanism. Thismechanism allows consumers specify the goods to be purchased by displaying products that are related to another purchased product or customer visits. One mechanism for establishing this system is collaborative filtering. Collaborative filtering works by building a database that stores the products which are preferred by consumers. New transactions made by a consumer will be matched with the database to find out which data are related the most. The most appropriate historical data to be displayed as a recommendation for consumers who conduct such transactions. One technique that can be used is extracting association rules using Apriori Algorithm. In this study, a website of party tools rental service is created to implement the recommendation system. A recommendation system built using rules generated by Apriori Algorithm. To be able to display items used on the value of the support 20, while the confidence value is used to determine the N-top items to be recommended.Keywords: recommender system, collaborative filtering, apriori algorithm.
APLIKASI WIRELESS SENSOR NETWORK UNTUK SISTEM MONITORING DAN KLASIFIKASI KUALITAS UDARA Arya, Tri Fidrian; Faiqurahman, Mahar; Azhar, Yufis
SISTEMASI Vol 7, No 3 (2018): SISTEMASI
Publisher : Fakultas Teknik dan Ilmu Komputer Universitas Islam Indragiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (742.308 KB) | DOI: 10.32520/stmsi.v7i3.312

Abstract

Indonesia merupakan salah satu negara yang memiliki perkembangan yang pesat pada sektor industri, hal tersebut tentunya berpengaruh pada lingkungan hidup termasuk kualitas udara. Polusi udara yang dikeluarkan dari cerobong asap kawasan industri apabila tidak dikelola dengan baik maka akan berdampak buruk pada kesehatan manusia. Diantaranya dapat berpengaruh terhadap status faal paru-paru, perubahan respon kekebalan tubuh, bahkan menyebabkan kematian pada makhluk hidup. monitoring tingkat polusi udara menjadi suatu hal yang urgent dilakukan. Pada penelitian ini dibuat aplikasi berbasis Wireless Sensor Network (WSN) untuk monitoring dan klasifikasi kualitas udara secara online, dengan menggunakan modul NRF24L01 untuk komunikasi antara sensor node dan base station yang biayanya relatif cukup terjangkau dan murah.
The Analysis of Proximity Between Subjects Based on Primary Contents Using Cosine Similarity on Lective Al-rizki, Muhammad Andi; Wicaksono, Galih Wasis; Azhar, Yufis
Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control Vol 2, No 4, November-2017
Publisher : Universitas Muhammadiyah Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (663.327 KB) | DOI: 10.22219/kinetik.v2i4.271

Abstract

In education world, recognizing the relationship between one subject and another is imperative. By recognizing the relationship between courses, performing sustainability mapping between subjects can be easily performed.  Moreover, detecting and reducing any duplicated contents in several subjects will be also possible to execute. Of course, these conveniences will benefit lecturers, students and departments. It will ease the analysis and discussion processes between lecturers related to subjects in the same domain. In addition, students will conveniently choose a group of subjects they are interested in. Furthermore, departments can easily create a specialization group based on the similarity of the subjects and combine the courses possessing high similarity. In this research, given a good database, the relationship between subjects was calculated based on the proximity of the primary contents of the subjects. The feature used was term feature, in which value was determined by calculating TF-IDF (Term Frequency Inverse Document Frequency) from each term. In recognizing the value of proximity between subjects, cosine similarity method was implemented. Finally, testing was done utilizing precision, recall and accuracy method. The research results show that the precision and accuracy values are 90,91% and the recall value is 100%.
Peringkasan Tweet Berdasarkan Trending Topic Twitter Dengan Pembobotan TF-IDF dan Single Linkage Angglomerative Hierarchical Clustering Annisa, Annisa; Munarko, Yuda; Azhar, Yufis
Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control Vol 1, No 1, May-2016
Publisher : Universitas Muhammadiyah Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (539.422 KB) | DOI: 10.22219/kinetik.v1i1.7

Abstract

Fitur yang paling sering digunakan pada Twitter ialah Trending Topic. Trending Topic merupakan fitur yang menampilkan beberapa hashtag berisi topik yang sedang trend saat ini. Jika pengguna ingin mengetahui informasi mengenai suatu trending topic, pengguna bisa mengklik salah satu hashtag dan barulah muncul beberapa tweet terkait dengan hashtag tersebut. Agar menghemat waktu pengguna Twitter dalam membaca suatu trending topic tanpa perlu membaca beberapa tweet terlebih dahulu, maka dilakukanlah analisa dengan tujuan membuat text summarization untuk trending topic pada Twitter menggunakan algoritma TF-IDF dan Single Linkage Agglomerative Hierarchical Clustering. Penelitian ini menggunakan 100 trending topic untuk data tes pada sistem dan setiap trending topic terdiri atas 50 tweet berbahasa indonesia, sedangkan untuk pengujian digunakan 30 data trending topic diambil secara acak (data mewakili trending topic dengan sub tema minimal 2 dan maksimal 9 dari 100 data tes pada sistem). Dari 30 data pengujian, 1 data menghasilkan semua ringkasan sama persis dengan ahli,  dan 29 data menghasilkan 1-4  ringkasan sama persis dengan ahli (terdiri atas 2-9 ringkasan untuk setiap trending topic).