Claim Missing Document
Check
Articles

Found 31 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%
Implementasi SOM Dalam Clustering Hasil Ikan Laut Kabupaten Pekalongan Bagus Nur Bakti Aji; Nur Nafiiyah; Miftahus Sholihin
Jurnal Elektronika, Listrik, dan Teknologi Informasi Terapan Vol 2 No 1 (2020): Jurnal ELTI III
Publisher : LPPM Politeknik Jambi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37338/e.v2i1.114

Abstract

Data from sea fish in Pekalongan Regency can be processed, one of which is clustered. Clusters are grouping data based on the same criteria. The purpose of doing clustering is to be able to help in sorting and dividing a situation based on the same criteria. Clustering of marine fish products in Pekalongan Regency will be grouped into three groups, namely: a small group of marine fish products, a medium group of marine fish products, and a large group of marine fish products. The clustering process uses the SOM algorithm, and the data is taken from the website data.go.id/dataset. Data is processed in order to show which fish yields are small, medium and large. The processing process uses variable types of fish, years and results of sea fish that are stored in Excel files and then processed using Matlab. The results show that there are fish species that are classified as low and moderate clusters, namely shrimp, squid, serimping, grouper, turmeric, and ray species. The types of fish that enter the cluster and many are Tigawaja. The types of fish that enter the medium cluster are Beloso, Pihi, Pepetek, and those who enter the low cluster are 18 fish species, while those who enter the low, medium and many clusters are Petek.
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.
Identifikasi Kesegaran Ikan Berdasarkan Citra Insang dengan Metode Convolution Neural Network Miftahus Sholihin
JATISI (Jurnal Teknik Informatika dan Sistem Informasi) Vol 8 No 3 (2021): JATISI (Jurnal Teknik Informatika dan Sistem Informasi)
Publisher : Lembaga Penelitian dan Pengabdian pada Masyarakat (LPPM) STMIK Global Informatika MDP

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/jatisi.v8i3.939

Abstract

This study aims to create a fish freshness identification system based on the image of fish gills. With this system, it is hoped that the community will find it easier to determine fresh fish. The method used in this study is CNN. The data used in this study amounted to 150 fish gill image data which were categorized into three classes, namely fresh, not fresh, and rotten fish classes. This research provides 100% accuracy for the training process and 97.7% for the testing process.
PENERAPAN ALGORITMA COLABORATIVE FILTERING UNTUK PEMBERIAN REKOMENDASI PADA PRODUK KAIN TENUN (Studi Kasus Kain Tenun Parengan) Miftahus Sholihin
Joutica Vol 2, No 1 (2017): Jurnal Informatika UNISLA
Publisher : Universitas Islam Lamongan

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (351.037 KB) | DOI: 10.30736/jti.v2i1.27

Abstract

Electronic commerce (e-commerce) is a concept that can be described as a process of buying and selling goods on the internet or the process of buying and selling or exchange of products, services, and information through information networks including the Internet. In developing e-commerce should be able to provide recommendations to customers. This recommendation aims to provide an overview of information about products that are considered in accordance with the wishes of customers. The method used in this research is Item Based Collaborative Filtering, where the system will look for similarity purchase model (similarity item) With others. The system will search for ratings between items by level The similarities exist. Once the item-to-item rating is obtained, this rating will be used to calculate the value Similarity between items using the Adjusted Cosine Similarity approach. The last process is to calculate the rating prediction value that customers have never done to a particular item. This approach uses Weigted Sum formula results from predicted value will be made recommendations to customers
Implementasi Algoritma Dijkstra pada Aplikasi Sistem Informasi Geografis Pencarian Rute Terpendek Wisata Dikabupaten Lamongan Berbasis Web Prisma Nanda; M. Ghofar Rohman; Miftahus Sholihin
Joutica Vol 7, No 1 (2022): Maret
Publisher : Universitas Islam Lamongan

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (515.697 KB) | DOI: 10.30736/jti.v7i1.802

Abstract

Pariwisata merupakan salah satu aspek yang penting bagi perekonomian dan kesejahteraan masyarakat di suatu daerah. Kabupaten Lamongan memiliki potensi  pariwisata yang sangat baik. Terdapat banyak objek wisata di Lamongan, diantaranya objek wisata religi, wisata alam, wisata buatan, dan oleh-oleh khas. Dalam penelitian ini dibuatlah aplikasi yang berjudul Implementasi Algoritma Dijkstra pada Aplikasi pencarian rute terpendek wisata di Kabupaten Lamongan berbasis Web. Dengan menggunakan algoritma Dijkstra untuk menentukan rute terpendek dari lokasi objek wisata satu menuju objek wisata lainnya. Perhitungan algoritma Dijkstra diawalai dengan menetukan node–node yang akan dibentuk menjadi sebuah graf. Node merupakan objek wisata yang ada di Kabupaten Lamongan. Algoritma Dijkstra menetukan bobot terkecil dari node awal menuju node akhir dan pada setiap perhitungan dari node awal menuju node selanjutnya akan diperbarui jika menemukan jarak terpendek. Dari segi pemanfaatannya sistem algoritma Dijkstra dalam menentukan rute terpedek lokasi objek wisata di Kabupaten Lamongan ini dapat menjadi media untuk promosi dan sebagai informasi rute perjalanan wisatawan menuju objek wisata di Kabupaten Lamongan. Pada penelitian ini ada 21 Data wisata diKabupaten Lamongan yang meliputi wisata alam wisata buatan dan wisata religi. Hasil akurasi yang diperoleh dalam sistem Algoritma Dijkstra pencarian Rute terpendek wisata diKabupaten Lamongan adalah 95% dengan jumlah data wisata sebanyak 21wisata.
Aplikasi Pengisian Data Alumni Prodi Teknik Universitas Islam Lamongan Berbasis Android Megawati Indriani; Miftahus Sholihin; Nurul Ftria ApriLliani
Joutica Vol 1, No 2 (2017)
Publisher : Universitas Islam Lamongan

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (364.67 KB) | DOI: 10.30736/jti.v1i2.48

Abstract

The rapid technological developments at this time had impact on all aspects of human life. The impact that is clearly visible is that the technology has made it easier to assist all human activities. There is no doubt that now all the things that used to be done manually has now been changed into automatically. The technology allows the users to search for information easily, one of information is about alumni profile data information. Alumni profile database filling application can be done easier for the alumni to access variety of information. As one of the developing universites, Lamongan Islamic University has many alumni therefore it is needed alumni profile database filling application to facilitate the alumni to gain the information. Inside alumni profile database there are “Forum” menu and also “Info Lowongan Kerja” menu that can make the alumni easier to find a job and keep in touch with other students. This alumni profile database filling application can only be used by the alumni from Study Program of Engineering by using NIM as a username and password. Alumni profile database filling application is created using Android system and MySQL database. The results of the test demonstrate that the application works well.
Penerapan Algoritma ID3 untuk Penentuan Penerima Bantuan Program Keluarga Harapan (Studi Kasus : Desa Kelolarum Kabupaten Lamongan) Zumrotus Shalekhah; Miftahus Sholihin; M. Ghofar Rohman
CYBERNETICS Vol 4, No 02 (2020): CYBERNETICS
Publisher : Universitas Muhammadiyah Pontianak

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29406/cbn.v4i02.2407

Abstract

Dalam pemberian bantuan PKH (Program Keluarga Harapan) di Desa Kelorarum Kecamatan Tikung belum berjalan secara optimal, karena pada saat pemilihan bantuan belum ada sistem yang mendukung sehingga masih kurang objektif. Sedikit atau banyak warga terkadang protes karena warga yang seharusnya layak mendapatkan bantuan tetapi menjadi tidak layak mendapatkan bantuan, begitupun sebaliknya. Pada penelitian ini bertujuan untuk membuat sebuah sistem pendukung keputusan dalam pemberian bantuan sosial PKH dengan menggunakan metode Algoritma ID3 Decision Tree. Kriteria yang digunakan ada enam kriteria yaitu keadaan dinding rumah, keadaan lantai rumah, pekerjaan, kepemilikan balita/ibu hamil, kepemilikan anak sekolah, dan kepemilikan lansia/disabilitas. Data training yang digunakan dalam penelitian ini sebanyak 154 data dan data testing sebanyak 39 data . Hasil penelitian dengan menggunakan metode algoritma ID3 decision tree dapat diketahui bahwa dari pohon keputusan menghasilkan 18 rule dan diakar utama dalam menentukan penerima bantuan PKH adalah dinding rumah dengan perolehan nilai gain sebesar 0,514518.
KLASIFIKASI KUALITAS MUTU TELUR AYAM RAS BERDASARKAN FITUR WARNA DAN TEKSTUR Miftahus Sholihin; M Ghofar Rohman
Jurnal Teknika Vol 10, No 2 (2018)
Publisher : Universitas Islam Lamongan

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (176.571 KB) | DOI: 10.30736/teknika.v10i2.244

Abstract

Egg quality is determined by the quality of the inside and outside of the egg. To find out the quality of eggs canbe by looking at the outside in the form of skin condition, shape, size, and egg weight. In this study a system isdesigned to function to determine the quality of egg quality based on color and texture features. Broadlyspeaking, the system built consists of 4 main processes. This process begins with pre-processing which aims toimprove image quality and also to change the image size. The next process is segmentation to get the egg object.The next process is feature extraction which aims to get the characteristics of each egg object. The last processis a classification that aims to determine the class of egg images entered by the user, the method used is knearest neighbor. The data used in this study were 147 egg images consisting of 85 eggs of data testing and 62eggs of training data. The highest accuracy obtained from this study is 82.3% with a value of 8
SISTEM PENENTUAN KUALITAS PISANG MENGGUNAKAN METODE FUZZY TSUKAMOTO Rofika Arista; Miftahus Sholihin; Nur Nafi'iyah
Journal of Information System Management (JOISM) Vol. 1 No. 1 (2019): Juli
Publisher : Universitas Amikom Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (676.057 KB) | DOI: 10.24076/joism.2019v1i1.22

Abstract

Pisang adalah buah yang memiliki rasa sangat manis dan aroma yang harum. Buah ini menjadi favorit banyak orang karena harganya yang terjangkau dan memiliki banyak manfaat dan nutrisi untuk tubuh. Penentuan kualitas pisang telah ditetapkan berdasarkan SNI 7422-2009 pisang. Tetapi kurangnya pengetahuan perusahaan ataupun konsumen dalam menentukan kualitas pisang mengakibatkan kesehatan menurun karena kesalahan mengkonsumsi buah pisang. Proses menentukan kualitas pisang berdasarkan 3 variabel kriteria, yaitu: ukuran, kecacatan dan kesegaran. Di mana hasil kualitas pisang terdapat kategori kelas C, B, A dan Super. Metode Tsukamoto dalam menentukan kualitas pisang menggunakan defuzzifikasi nilai rata-rata, dan menggunakan kriteria kualitas pisang yang terdiri dari tiga variable, yaitu ukuran, kecacatan, dan kesegaran. Hasil penelitian ini didapatkan kelas pisang berdasarkan kriteria yang diinputkan dan memiliki nilai akurasi sebesar 78%.
Co-Authors Abdul Kholiq Abdul Kholiq Ahmad Fauzi Hendratmoko Alfarisi, Muhammad Nur Fikri AlMuhibbi, Muhammad Rayendra Anam, M. Khairul Ansori, Yulian Arief Rahman Arief Rahman Arshad, Mohamad Syafwan Asmaraningtyas, Kinanthi Trah Asshiddieqie, Rafi Ramadhan Atia Sonda Aulia Ikhsan Azizah, Luluk Nur Azza Abidatin Bettaliyah AZZA ABIDATIN BETTALIYAH Bagus Nur Bakti Aji Bagus Nur Bakti Aji bin MD. Fudzee, Mohd Farhan Cindy Suryanti Darnis, Febriyanti Delano, M. Fabian Reinhard Dinar Mahdalena Leksana 1 Erna Hayati Erna Hayati, Erna Erry Anggraini ERRY ANGGRAINI Farizki, Achmad Nurasel FATHARANI, ATIKA Fatkhul U, M. Miftah Febriyanti Darnis Firdaus, Muhammad Alvin Fudzee, Mohd Farhan Md Gusman, Taufik Hamid, Rahayu A Ismail, Mohd Norasri Izz, Aiz Ahmad Fa’iz Dliya’ul KIKI SEPTARIA Lilik Anifah M. Ghofar Rohman M. Rosidi Zamroni M. ZAKI QOMARUDDIN Mahuda, Isnaini Masruroh MASRUROH Megawati Indriani Mohd Farhan MD Fudzee, Mohd Farhan Mufrody, Moh Adam Mustain Mustain Nafiiyah, Nur Nur Nafi'iyah Nur Nafi’iyah Nurroziqin, M Chabib Nurul Aswa Omar Nurul Ftria ApriLliani Pertiwi, Dinda Dwi Anugrah Prastowo, Diko Pratiwi, Putri Septiani Indah Prisma Nanda Prsatama, Febrian Abie Rahayu A Hamid Retno Wardhani Rofika Arista Sari, Putri Dina Setia Budi, Agus Sika Azkia, Czidni Siti Mujilahwati Sulaiman, Akhmad Nurali Surojuddin, Eko Titin Nurbella Udiansyah, Naufal Arrafi Ulum, M. Miftah Fatkhul Umam, Moch. Zuhrul Vanesta Ikhsana Putri Maulana Wati, Efi Neo Yulian Ansori Zirby, Qonit Zumrotus Shalekhah