Claim Missing Document
Check
Articles

Found 38 Documents
Search

Classification of Lexile Level Reading Load Using the K-Means Clustering and Random Forest Method Rosyid, Harits Ar; Pujianto, Utomo; Yudhistira, Moch Rajendra
Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control Vol. 5, No. 2, May 2020
Publisher : Universitas Muhammadiyah Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22219/kinetik.v5i2.897

Abstract

There are various ways to improve the quality of someone's education, one of them is reading. By reading, insight and knowledge of various kinds of things can increase. But, the ability and someone's understanding of reading is different. This can be a problem for readers if the reading material exceeds his comprehension ability. Therefore, it is necessary to determine the load of reading material using Lexile Levels. Lexile Levels are a value that gives a size the complexity of reading material and someone's reading ability. Thus, the reading material will be classified based a value on the Lexile Levels. Lexile Levels will cluster the reading material into 2 clusters which is easy, and difficult. The clustering process will use the k-means method. After the clustering process, reading material will be classified using the reading load Random Forest method. The k-means method was chosen because of the method has a simple computing process and fast also. Random Forest algorithm is a method that can build decision tree and it’s able to build several decision trees then choose the best tree. The results of this experiment indicate that the experiment scenario uses 2 cluster and SMOTE and GIFS preprocessing are carried out shows good results with an accuracy of 76.03%, precision of 81.85% and recall of 76.05%.
Pelabelan Kelas Kata Bahasa Jawa Menggunakan Hidden Markov Model Mursyit, Mohammad; Wibawa, Aji Prasetya; Zaeni, Ilham Ari Elbaith; Rosyid, Harits Ar
Mobile and Forensics Vol 2, No 2 (2020)
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/mf.v2i2.2450

Abstract

Part of Speech Tagging atau POS Tagging adalah proses memberikan label pada setiap kata dalam sebuah kalimat secara otomatis. Penelitian ini menggunakan algoritma Hidden Markov Model (HMM) untuk proses POS Tagging. Perlakuan untuk unknown words menggunakan Most Probable POS-Tag. Dataset yang digunakan berupa 10 cerita pendek berbahasa Jawa terdiri dari 10.180 kata yang telah diberikan tagsetBahasa Jawa. Pada penelitian ini proses POS Tagging menggunakan dua skenario. Skenario pertama yaitu menggunakan algoritma Hidden Markov Model (HMM) tanpa menggunakan perlakuan untuk unknown words. Skenario yang kedua menggunakan HMM dan Most Probable POS-Tag untuk perlakuan unknown words. Hasil menunjukan skenario pertama menghasilkan akurasi sebesar 45.5% dan skenario kedua menghasilkan akurasi sebesar 70.78%. Most Probable POS-Tag dapat meningkatkan akurasi pada POS Tagging tetapi tidak selalu menunjukan hasil yang benar dalam pemberian label. Most Probable POS-Tag dapat menghilangkan probabilitas bernilai Nol dari POS Tagging Hidden Markov Model. Hasil penelitian ini menunjukan bahwa POS Tagging dengan menggunakan Hidden Markov Model dipengaruhi oleh perlakuan terhadap unknown words, perbendaharaan kata dan hubungan label kata pada dataset.  Part of Speech Tagging or POS Tagging is the process of automatically giving labels to each word in a sentence. This study uses the Hidden Markov Model (HMM) algorithm for the POS Tagging process. Treatment for unknown words uses the Most Probable POS-Tag. The dataset used is in the form of 10 short stories in Javanese consisting of 10,180 words which have been given the Javanese tagset. In this study, the POS Tagging process uses two scenarios. The first scenario is using the Hidden Markov Model (HMM) algorithm without using treatment for unknown words. The second scenario uses HMM and Most Probable POS-Tag for treatment of unknown words. The results show that the first scenario produces an accuracy of 45.5% and the second scenario produces an accuracy of 70.78%. Most Probable POS-Tag can improve accuracy in POS Tagging but does not always produce correct labels. Most Probable POS-Tag can remove zero-value probability from POS Tagging Hidden Markov Model. The results of this study indicate that POS Tagging using the Hidden Markov Model is influenced by the treatment of unknown words, vocabulary and word label relationships in the dataset.
Single Exponential Smoothing-Multilayer Perceptron Untuk Peramalan Pengunjung Unik Jurnal Elektronik Ferdinand, Miftakhul Anggita Bima; Wibawa, Aji Prasetya; Zaeni, Ilham Ari Elbaith; Rosyid, Harits Ar
Mobile and Forensics Vol 2, No 2 (2020)
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/mf.v2i2.2034

Abstract

Jumlah kunjungan rerata pengunjung unik per hari pada jurnal elektronik menunjukkan bahwa hasil terbitan karya ilmiah website tersebut menarik. Sehingga jumlah pengunjung unik dijadikan indikator penting dalam mengukur keberhasilan sebuah jurnal elektronik untuk memenuhi perluasan, penyebaran dan percepatan sistem akreditasi jurnal. Pengunjung Unik merupakan jumlah pengunjung per Internet Address (IP) yang mengakses sebuah jurnal elektronik dalam kurun waktu tertentu. Terdapat beberapa metode yang biasa digunakan untuk peramalan, diantaranya adalah Multilayer Perceptron (MLP).  Kualitas data berpengaruh besar dalam membangun model MLP yang baik, karena sukses tidaknya permodelan pada MLP sangat dipengaruhi oleh data input. Salah satu cara untuk meningkatkan kualitas data adalah dengan melakukan smoothing pada data tersebut. Pada penelitian ini digunkan metode peramalan Multilayer Perceptron berdasarkan penelitian sebelumnya dengan kombinasi data training dan testing 80%-20% dengan asitektur 2-1-1 dan learning rate 0,4. Selanjutnya untuk meningkatkan kualitas data dilakukan smoothing dengan menerapkan metode Single Exponential Smoothing. Dari penelitian yang dilakukan diperoleh hasil terbaik menggunakan alpha 0.9 dengan hasil akurasi MSE 94.02% dan RMSE 75.54% dengan lama waktu eksekusi 580,27 detik. The number of visits by the average unique visitor per day on electronic journals shows that the published scientific papers on the website are interesting. So that the number of unique visitors is used as an important indicator in measuring the success of an electronic journal to meet the expansion, dissemination and acceleration of the journal accreditation system. Unique Visitors is the number of visitors per Internet Address (IP) who access an electronic journal within a certain period of time. There are several methods commonly used for forecasting, including the Multilayer Perceptron (MLP). Data quality has a big influence in building a good MLP model, because the success or failure of modeling in MLP is greatly influenced by the input data. One way to improve data quality is by smoothing the data. In this study, the Multilayer Perceptron forecasting method was used based on previous research with a combination of training data and testing 80% -20% with a 2-1-1 architecture and a learning rate of 0.4. Furthermore, to improve data quality, smoothing is done by applying the Single Exponential Smoothing method. From the research conducted, the best results were obtained using alpha 0.9 with MSE accuracy of 94.02% and RMSE 75.54% with a long execution time of 580.27 seconds.
Single Exponential Smoothing-Multilayer Perceptron Untuk Peramalan Pengunjung Unik Jurnal Elektronik Ferdinand, Miftakhul Anggita Bima; Wibawa, Aji Prasetya; Zaeni, Ilham Ari Elbaith; Rosyid, Harits Ar
Mobile and Forensics Vol. 2 No. 2 (2020)
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/mf.v2i2.2034

Abstract

Jumlah kunjungan rerata pengunjung unik per hari pada jurnal elektronik menunjukkan bahwa hasil terbitan karya ilmiah website tersebut menarik. Sehingga jumlah pengunjung unik dijadikan indikator penting dalam mengukur keberhasilan sebuah jurnal elektronik untuk memenuhi perluasan, penyebaran dan percepatan sistem akreditasi jurnal. Pengunjung Unik merupakan jumlah pengunjung per Internet Address (IP) yang mengakses sebuah jurnal elektronik dalam kurun waktu tertentu. Terdapat beberapa metode yang biasa digunakan untuk peramalan, diantaranya adalah Multilayer Perceptron (MLP). Kualitas data berpengaruh besar dalam membangun model MLP yang baik, karena sukses tidaknya permodelan pada MLP sangat dipengaruhi oleh data input. Salah satu cara untuk meningkatkan kualitas data adalah dengan melakukan smoothing pada data tersebut. Pada penelitian ini digunkan metode peramalan Multilayer Perceptron berdasarkan penelitian sebelumnya dengan kombinasi data training dan testing 80%-20% dengan asitektur 2-1-1 dan learning rate 0,4. Selanjutnya untuk meningkatkan kualitas data dilakukan smoothing dengan menerapkan metode Single Exponential Smoothing. Dari penelitian yang dilakukan diperoleh hasil terbaik menggunakan alpha 0.9 dengan hasil akurasi MSE 94.02% dan RMSE 75.54% dengan lama waktu eksekusi 580,27 detik. The number of visits by the average unique visitor per day on electronic journals shows that the published scientific papers on the website are interesting. So that the number of unique visitors is used as an important indicator in measuring the success of an electronic journal to meet the expansion, dissemination and acceleration of the journal accreditation system. Unique Visitors is the number of visitors per Internet Address (IP) who access an electronic journal within a certain period of time. There are several methods commonly used for forecasting, including the Multilayer Perceptron (MLP). Data quality has a big influence in building a good MLP model, because the success or failure of modeling in MLP is greatly influenced by the input data. One way to improve data quality is by smoothing the data. In this study, the Multilayer Perceptron forecasting method was used based on previous research with a combination of training data and testing 80% -20% with a 2-1-1 architecture and a learning rate of 0.4. Furthermore, to improve data quality, smoothing is done by applying the Single Exponential Smoothing method. From the research conducted, the best results were obtained using alpha 0.9 with MSE accuracy of 94.02% and RMSE 75.54% with a long execution time of 580.27 seconds.
Pelabelan Kelas Kata Bahasa Jawa Menggunakan Hidden Markov Model Mursyit, Mohammad; Wibawa, Aji Prasetya; Zaeni, Ilham Ari Elbaith; Rosyid, Harits Ar
Mobile and Forensics Vol. 2 No. 2 (2020)
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/mf.v2i2.2450

Abstract

Part of Speech Tagging atau POS Tagging adalah proses memberikan label pada setiap kata dalam sebuah kalimat secara otomatis. Penelitian ini menggunakan algoritma Hidden Markov Model (HMM) untuk proses POS Tagging. Perlakuan untuk unknown words menggunakan Most Probable POS-Tag. Dataset yang digunakan berupa 10 cerita pendek berbahasa Jawa terdiri dari 10.180 kata yang telah diberikan tagset Bahasa Jawa. Pada penelitian ini proses POS Tagging menggunakan dua skenario. Skenario pertama yaitu menggunakan algoritma Hidden Markov Model (HMM) tanpa menggunakan perlakuan untuk unknown words. Skenario yang kedua menggunakan HMM dan Most Probable POS-Tag untuk perlakuan unknown words. Hasil menunjukan skenario pertama menghasilkan akurasi sebesar 45.5% dan skenario kedua menghasilkan akurasi sebesar 70.78%. Most Probable POS-Tag dapat meningkatkan akurasi pada POS Tagging tetapi tidak selalu menunjukan hasil yang benar dalam pemberian label. Most Probable POS-Tag dapat menghilangkan probabilitas bernilai Nol dari POS Tagging Hidden Markov Model. Hasil penelitian ini menunjukan bahwa POS Tagging dengan menggunakan Hidden Markov Model dipengaruhi oleh perlakuan terhadap unknown words, perbendaharaan kata dan hubungan label kata pada dataset. Part of Speech Tagging or POS Tagging is the process of automatically giving labels to each word in a sentence. This study uses the Hidden Markov Model (HMM) algorithm for the POS Tagging process. Treatment for unknown words uses the Most Probable POS-Tag. The dataset used is in the form of 10 short stories in Javanese consisting of 10,180 words which have been given the Javanese tagset. In this study, the POS Tagging process uses two scenarios. The first scenario is using the Hidden Markov Model (HMM) algorithm without using treatment for unknown words. The second scenario uses HMM and Most Probable POS-Tag for treatment of unknown words. The results show that the first scenario produces an accuracy of 45.5% and the second scenario produces an accuracy of 70.78%. Most Probable POS-Tag can improve accuracy in POS Tagging but does not always produce correct labels. Most Probable POS-Tag can remove zero-value probability from POS Tagging Hidden Markov Model. The results of this study indicate that POS Tagging using the Hidden Markov Model is influenced by the treatment of unknown words, vocabulary and word label relationships in the dataset.
Pengembangan aplikasi web dengan gamifikasi sebagai media pendukung pembelajaran untuk mata pelajaran pemrograman dasar Rahadyan Fannani Arif; Harits Ar Rosyid
TEKNO: Jurnal Teknologi Elektro dan Kejuruan Vol 29, No 2 (2019)
Publisher : Universitas Negeri Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (712.668 KB) | DOI: 10.17977/um034v29i2p161-176

Abstract

Siswa SMK dan MAK program keahlian Rekayasa Perangkat Lunak dituntut memiliki kemampuan pemrograman web. Mata pelajaran ini sangat penting dikarenakan banyak digunakan diindustri saat ini. Dan pengembangan dari teknologi web sendiri sangat beragam. Sehingga Mata Pelajaran ini penting untuk dipahami oleh siswa SMK jurusan RPL. Sedangkan penunjang untuk pembelajaran web di SMK masih kurang, dikarenakan siswa masih menggunakan cara konvensional. Permasalahannya adalah siswa banyak yang kurang memahami saat mengikuti instruksi yang ada di modul. Penelitian ini bertujuan mengembangkan Web Application sebagai penunjang pembelajaran dengan unsur gamifikasi. Metode yang digunakan dalam penelitian ini adalah metode penelitian dan pengembangan. Penelitian dan pengembangan ini menggunakan model pengembangan media model ADDIE dan model Prototyping. Hasil uji validasi yang dilakukan oleh para ahli, media yang dikembangkan dinyatakan valid, dengan persentase sebesar 95,24% oleh ahli materi dan 94,17% oleh ahli media. Berdasarkan uji coba kelayakan yang telah dilaksanakan di SMKN 4 Malang, diperoleh persentase sebesar 87,63% untuk uji coba kelompok kecil, dan 91,93% untuk uji coba kelompok besar. Dari rangkaian uji validasi dan uji coba tersebut, dapat dinyatakan bahwa secara keseluruhan, media yang dikembangkan telah valid dan layak digunakan sebagai penunjang proses pembelajaran mata pelajaran Pemrograman Dasar.
Implementasi metode Dempster-Shafer dalam diagnosa penyakit pada tanaman Cabai Merah Keriting Agusta Rakhmat Taufani; Harits Ar Rosyid; Khoirudin Asfani
TEKNO: Jurnal Teknologi Elektro dan Kejuruan Vol 29, No 1 (2019)
Publisher : Universitas Negeri Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (550.625 KB) | DOI: 10.17977/um034v29i1p13-25

Abstract

Komoditas cabai terdiri dari berbagai varian, yaitu cabai besar yang terdiri dari cabai merah besar dan cabai merah keriting, serta cabai rawit yang terdiri dari cabai rawit hijau dan cabai rawit merah. Di antara varian tersebut, cabai merah keriting adalah cabai yang paling sering dikonsumsi oleh masyarakat. Sepanjang 2015-2016 cabai merah dan cabai rawit berkontribusi terhadap inflasi nasional. Dengan kondisi tersebut, para petani khususnya petani tanaman cabai merah keriting harus terus berinovasi agar produksinya terus meningkat. Perkembangan budidaya tanaman ini juga terus meningkat sehingga terjadi kompetisi yang semakin ketat. Permasalahannya, semakin banyak petani yang mencoba membudidayakan tanaman tersebut tidak diimbangi dengan pengetahuan mengenai cara penanganan apabila terserang penyakit. Banyak kendala yang dihadapi para petani dalam proses menanam atau budidayanya, salah satunya penyakit yang menyerang tanaman tersebut. Hama penyakit tanaman ini merupakan OPT (Organisme Pangganggu Tanaman) yang harus diperhatikan karena dapat mempengaruhi kondisi maupun produktifitasnya. Organisme Pangganggunya selain sebagai hama juga sebagai vektor pembawa penyakit. Dalam penelitian kali ini, sistem dikembangkan menggunakan metode Dempster-Shafer sebagai media diagnosia penyakit tanaman cabai merah keriting. Tujuan dari penelitian ini untuk membantu pengguna sistem khususnya para petani tanaman jenis tersebut agar dapat mengetahui atau mengidentifikasi penyakit ketika terkena penyakit serta cara menanggulanginya. Dari kasus uji coba yang telah dilakukan, didapatkan hasil yang menunjukkan bahwa aplikasi berfungsi dengan baik sesuai dengan metode Dempster-shafer dengan teknik inferensi forward chaining.
Comparison of Naïve Bayes Algorithm and Decision Tree C4.5 for Hospital Readmission Diabetes Patients using HbA1c Measurement Utomo Pujianto; Asa Luki Setiawan; Harits Ar Rosyid; Ali M. Mohammad Salah
Knowledge Engineering and Data Science Vol 2, No 2 (2019)
Publisher : Universitas Negeri Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (655.467 KB) | DOI: 10.17977/um018v2i22019p58-71

Abstract

Diabetes is a metabolic disorder disease in which the pancreas does not produce enough insulin or the body cannot use insulin produced effectively. The HbA1c examination, which measures the average glucose level of patients during the last 2-3 months, has become an important step to determine the condition of diabetic patients. Knowledge of the patient's condition can help medical staff to predict the possibility of patient readmissions, namely the occurrence of a patient requiring hospitalization services back at the hospital. The ability to predict patient readmissions will ultimately help the hospital to calculate and manage the quality of patient care. This study compares the performance of the Naïve Bayes method and C4.5 Decision Tree in predicting readmissions of diabetic patients, especially patients who have undergone HbA1c examination. As part of this study we also compare the performance of the classification model from a number of scenarios involving a combination of preprocessing methods, namely Synthetic Minority Over-Sampling Technique (SMOTE) and Wrapper feature selection method, with both classification techniques. The scenario of C4.5 method combined with SMOTE and feature selection method produces the best performance in classifying readmissions of diabetic patients with an accuracy value of 82.74 %, precision value of 87.1 %, and recall value of 82.7 %.
Comparison of Indonesian Imports Forecasting by Limited Period Using SARIMA Method Harits Ar Rosyid; Mutyara Whening Aniendya; Heru Wahyu Herwanto
Knowledge Engineering and Data Science Vol 2, No 2 (2019)
Publisher : Universitas Negeri Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (565.881 KB) | DOI: 10.17977/um018v2i22019p90-100

Abstract

The development of Indonesia's imports fluctuate over years. Inability to anticipate such rapid changes can cause economic slump due to inappropriate policy. For instance, recent years imports in rice led to the extermination of rice reserves. The reason is to maintain the market price of rice in Indonesia. To overcome these changes, forecasting the amount of imports should assist the Government in determining the optimum policy. This can be done by utilizing an algorithm to forecast time series data, in this case the amount of imports in the next few months with a high degree of accuracy. This study uses data obtained from the official website of the Indonesian Ministry of Trade. Then, Seasonal Autoregressive Integrated Moving Average (SARIMA) method is applied to forecast the imports. This method is suitable for the interconnected dependent variables, as well as in forecasting seasonal data patterns. The results of the experiment showed that 6-period forecast is the most accurate results compared to forecasting by 16 and 24 periods. The research resulted in the best model, that is ARIMA (0, 1, 3)(0, 1, 1)12 produces forecasting with a MAPE value of 7.210 % or an accuracy rate of 92.790 %. By applying this imports forecast model, the government can have a forward strategic plans such as selectively imports products and carefully decide the amount of the incoming products to Indonesia. Hence, it could maintain or improve the economic condition where local businesses can grow confidently. 
Sistem Tutorial Berbasis Kecerdasan Buatan Pada Proses Pengambilan Keputusan Perawatan dan Perbaikan Gitar Agusta Rakhmat Taufani; Harits Ar Ar Rosyid
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 3 No 1 (2019): April 2019
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1074.35 KB) | DOI: 10.29207/resti.v3i1.842

Abstract

Guitar is a popular musical instrument in the world and is a metronome for every use in various music events and its correlation. As a metronome, the guitar must be well standardized on the quality of each part so that sound that comes in line with the user's expectations in this case is the guitarist. Damage to the guitar is something normal because of its intense use so it needs proper handling in the repair process. The easiest thing is to bring a broken guitar to the experts, but when there are not many guitar service experts or a long enough distance to reach it, then guitar repairs need to be done immediately. Therefore, it is necessary to develop a system that can act as a tutor in the maintenance and repair of guitars by utilizing artificial intelligence embedded in the system. With the help of artificial intelligence, it is expected that the system can assist in the decision making of guitar technicians in the process of making guitar repair decisions based on the symptoms that occur. Decision making used uses the certainty factor method based on certainty factors. After going through the equivalence partitioning testing process, in general this system produces a total percentage of 100% on the success of the item test by experts in the testing process of the 25 items tested. Thus the application meets the requirements for making the program, which is readable and valid.