Claim Missing Document
Check
Articles

Found 25 Documents
Search

Optimasi Hyperparameter TensorFlow dengan Menggunakan Optuna di Python: Study Kasus Klasifikasi Dokumen Abstrak Skripsi Mujilahwati, Siti; Sholihin, Miftahus; Wardhani, Retno
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 5, No 3 (2021): Juli 2021
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v5i3.3090

Abstract

In today's rapidly growing digital era, the role of computing in artificial intelligence is needed to be able to help business people. Both in the fields of economy, health, and education. The use of machine learning will help related parties in viewing, analyzing, and making decisions. With machine learning, all problems related to data can be solved quickly and precisely. The problem is that the thesis document will increase every year, it will become a useless document if the data processing is not carried out. Past thesis data can be used for analysis and decision-making in the next thesis era. Python is one of the most popular programming languages used for machine learning. One reason is that there are many python-based libraries. Keras is a python-based machine learning library. TensorFlow can be used when dealing with large amounts of data processing, including thesis abstract data. Thus, this study classified 140 thesis abstract documents using hard-TensorFlow with the aim that based on the abstract content it would be classified into 6 classes, namely Android Applications, Data Mining, RPL, SPK, Digital Image Processing, and Expert Systems. The results of the classification with training data as many as 82 documents with model setting batch size = 12 and epoch = 2 with an Accuracy value of 89.04%. While the test loss test data has a higher value than the Accuracy value obtained by 66.66%. By utilizing maximizing TensorFlow performance by adding a parameter that Scikit Learn has, namely Optuna. The test data was optimized with a trial value of 500, the Accuracy increased to 76.19%
ANALISA POLA TRANSAKSI PENJUALAN IKAN DI TPI BRONDONG LAMONGAN Nur Nafi’iyah; Retno Wardhani
SPIRIT Vol 9, No 2 (2017): Jurnal SPIRIT
Publisher : STMIK YADIKA BANGIL

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (91.865 KB) | DOI: 10.53567/spirit.v9i2.80

Abstract

Abstract: How is the relationship between fish data one with other fish in sales at TPI Brondong Lamongan. An analysis of the linkage of fish sales to one another using Apriori. And to see the linkage and sales pattern using confidence value 40% and support value 50%. The total data analyzed were 140 records of transactions, and the analyzed fish, they were: Tongkol, Togek, Kuniran, Teri, Kakap Merah. From the result of this research produce pattern, that is if buying of Cowkol then definitely buy Togek, and if buy Togek then buy Teri. The confidence value is rounded to 1 digit behind the comma. Keywords: Pattern, Apriori, Fish.
Fuzzy C-Mean untuk Mengcluster Pemain Football FIFA (Studi Kasus: Data Kaggle) Mohammad Afan; Retno Wardhani; Nur Nafi’iyah
Jurnal Ilmu Komputer dan Desain Komunikasi Visual Vol 4 No 2 (2019): Jurnal Ilmu Komputer dan Desain Komunikasi Visual (JIKDISKOMVIS)
Publisher : Fakultas Ilmu Komputer Universitas Nahdlatul Ulama Sidoarjo

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

Abstract

From the data set in the internet world, we want to do the management. The purpose of managing existing data on the internet especially Kaggle is to find out how the clustering process is and how to apply the c-mean fuzzy algorithm. Fuzzy c-mean is used to cluster and get the centroid value of each cluster. The results of the centroid value of each cluster are used to group new data or the dataset itself. We use the FIFA Football Kaggle dataset to cluster into 2 and 3 groups. Fuzzy c-mean algorithm is implemented to cluster data with 2499 rows with 46 variables. The tool used to process data is matlab. Keywords— FIFA Fottbal, Clustering, Fuzzy C-mean, Matlab
CLASSIFICATION OF BATIK LAMONGAN BASED ON FEATURES OF COLOR, TEXTURE AND SHAPE Miftahus Sholihin; Siti Mujilahwati; Retno Wardhani
Jurnal Ilmiah Kursor Vol 9 No 1 (2017)
Publisher : Universitas Trunojoyo Madura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28961/kursor.v9i1.114

Abstract

Classification aims to classify object into specific classes based on the value of the attribute associated with the object being observed. In this research designed a system that serves to classify Lamongan batik cloth based on color features using color moment, texture using Gray Level Co-occurence Matrix (GLCM), and shape using moment invariant, classification using K-Nearest Neighbors (K-NN) method. In outline the system was built consists of three main processes namely pre-processing, feature extraction, and classification. The highest accuracy rate in this study was 90.4% when the value of k = 6.
SISTEM PENDUKUNG KEPUTUSAN PENJURUSAN SISWA PADA SMA PANCAMARGA 1 LAMONGAN MENGGUNAKAN METODE FUZZY Ahmad Fathoni; Mustain Mustain; Retno Wardhani
Joutica Vol 3, No 1 (2018)
Publisher : Universitas Islam Lamongan

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (618.528 KB) | DOI: 10.30736/jti.v3i1.202

Abstract

must know what factors affect the performance of teachers. The results of the analysis will be beneficial to make the education development program optimally and it is very necessary to advance the quality of education. Students need special attention from the government and society therefore the government regulates the improvement of the quality of teachers or teachers nationally through Law No. 20 of 2003 on National education system. In order to enforce the law, the government issued Regulation No. 19 of 2004 on the National Education standard. Therefore developed sebi student decision support system on the sma pancamarga 1 Lamongan using fuzzy.
SISTEM PENILAIAN KINERJA GURU PADA MI TARBIYATUS SHIBYAN MENGGUNAKAN BOOTSTRAP FRAMEWORK Moh Muslikh; Retno Wardhani; Nur Nafiiyah
Joutica Vol 1, No 2 (2017)
Publisher : Universitas Islam Lamongan

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (659.984 KB) | DOI: 10.30736/jti.v1i2.51

Abstract

Teacher performance assessment system is a system that can help the problem of teacher assessment in the schools in in delivering the value of accurate and right on target, one of them is MI Tarbinyatus Shibyan Kemantren Paciran Lamongan which implement the performance appraisal of teachers to know the process of teaching is good and right for all student and for the promotion of teacher. Performance assessment of the teacher themselves were taken from the four criteria, namely Pedagogic, social, personality, there are four criteria of Professional the fourteen competencies. Thus is created the system of teacher performance assessment based on login step, the content of the data content of the teacher, the teacher's grades, report the results of the result value. Teacher performance assessment system is made as easy as possible, the system can be easily dioprasikan to assist the principal in the giving of value accurate and right on target.
SITEM INFORMASI GEOGRAFIS LOKASI PRAKTEK DOKTER SPESIALIS DAN APOTEK YANG DISARANKAN DI LAMONGAN DAN GRESIK BERBASIS ANDROID Kemal Farouq Mauladi; Toni Muji Pangestu; Retno Wardhani
Joutica Vol 1, No 2 (2017)
Publisher : Universitas Islam Lamongan

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (473.823 KB) | DOI: 10.30736/jti.v1i2.53

Abstract

Geographic information systems (GIS) is a information system of processing and presention the data about the geographic condition into a range of accurate information. A specialist is a health worker who runs an important task in the Health, they are called specialists as because they in a specific area. Many people do not know the location of practices specialist, whether it is in Lamongan and Gresik, especially the people who live far from urban areas. With the problem, it is required system to inform the location of specialist practice and pharmacies in Gresik and Lamongan to facilitate good the people of the native or newcomers and wherever they are. In the development of this applications uses the Android operating system which is one of the most popular mobile phone operating system today, combined with the utilization of geographic information systems is certainly efficient for answering those questions. The utilization of Google Map API will certainly be very helpful in giving information on the location of the doctor and the pharmacies because the users can easily see the directions to the nearest way so it can be done more quickly, then the researcher makes the system with the title Geographic Information System Of Specialist Practice Location And The Pharmacies Suggested In Lamongan And Gresik Regency Based On Android.
APLIKASI GAME WIN START LA BERBASIS ANDROID Roiduddin Al Adib; Nurul Fuad; Retno Wardhani
Joutica Vol 1, No 2 (2017)
Publisher : Universitas Islam Lamongan

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (720.717 KB) | DOI: 10.30736/jti.v1i2.49

Abstract

Game is one of the entertainment that is fun and interesting way to spend leisure time or relieve boredom at the time of waiting, a variety of games or game has been created and produced many free or paid. Starting from a brain teaser game theme, sports, to adventure. An android based games can provide entertainment for players. The purpose of this study was to design and build a game that can be played in your spare time and eliminate boredom when waiting. The method used in designing and building this game is the method of "Multimedia Development". Stages in the process of this study is Phase Concept , Design , Material Collection and Testing. By using the Unity Game Engine programming language and Android SDK, will produce an android game titled "Application-Based Android Game Win Start" to increase knowledge in making games with the theme of brain teasers and applying the lessons of artificial intelligence (Playing Game) with a greedy algorithm, uses 2D graphics and is designed for a single player
IMPLEMENTASI FUZZY C-MEANS UNTUK CLUSTERING MAHASISWA BERDASARKAN NILAI MASUK PERGURUAN TINGGI Siti Mujilahwati; Retno Wardhani
Joutica Vol 6, No 1 (2021): Jurnal Teknik Informatika
Publisher : Universitas Islam Lamongan

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (291.34 KB) | DOI: 10.30736/jti.v6i1.582

Abstract

Penyaringan tes ujian pada penerimaan mahasiswa baru atau biasa disingkat dengan PMB, merupakan salah satu tahapan selain melengkapi berkas administratif. Pada Universitas Islam Lamongan (Unisla), tes penyaringan ini digunakan untuk melihat potensi calon mahasiswa berdasarkan nilai yang diperoleh. Dilihat dari hasil tes ini, maka langkah selanjutnya adalah panitia PMB dapat menentukan calon mahasiswa yang harus mengikuti kuliah matrikulasi atau tidak. Untuk saat ini penentuan dari hasil nilai tes dilakukan secara mengurutkan dari nilai tertinggi. Panitia juga akan memberikan nilai batas minimal dari nilai rata-rata tes yang diberikan untuk menentukan calon mahasiswa yang berhak tidak mengikuti kuliah matrikulasi. Pada penelitian ini akan membuat pengujian model klaster untuk menentukan kelompok calon mahasiswa yang tidak wajib mengikuti kuliah matrikulasi dan yang wajib mengikuti. Metode klaster yang digunakan adalah Fuzzy C-Means. Dengan menggunakan data uji sebanyak 400 data calon mahasiswa dan menggunakan 5 atribut nilai dari hasil tes PMB. Dan pengujian metode ini diimplementasikan pada Software Matlab telah mendapatkan hasil klaster 1 (Tidak Mengikuti kuliah matrikulasi) sebanyak 178 dengan nilai tes rata-rata 273,039 sedangkan pada klaster 2 (Wajib mengikuti kuliah matrikulasi) sebanyak 222 dengan nilai tes rata-rata 212,610.
SISTEM PAKAR MENDIAGNOSA PENYAKIT PADA UNGGAS DENGAN METODE TEOREMA BAYES BERBASIS WEB Achmad Rido'i; Retno Wardhani; Masruroh masruroh
Joutica Vol 2, No 2 (2017)
Publisher : Universitas Islam Lamongan

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (146.856 KB) | DOI: 10.30736/jti.v2i2.64

Abstract

Poultry has many benefits such as its eggs and meat that cannot be separated from the needs of daily consumption. However, there is a major problem that almost experienced every year for the breders. The disease in poultry is a serious problem that becomes obstacles for the breeders. Based on this problem, the application maker made an expert system application to diagnose the disease in poultry with Bayes theorem method. This application is expected to help the breeders in diagnosing the disease in poultry, therefore the death of poultry can be minimized. This application has been successfully designed and implemented using notepad ++ and php MySQL through several steps of main menu design system, those are; consultation, diseases, and aid. The coding making is done in notepad ++ application. Then making the database is done in php MySQL. The result reveals that this application is made to identify the disease based on the existing symptoms. In testing, 10 breeders stated that this application can help diagnose the disease in poultry.