Garuda - Garba Rujukan Digital

Dimensionality Reduction using PCA and K-Means Clustering for Breast Cancer Prediction Ade Jamal; Annisa Handayani; Ali Akbar Septiandri; Endang Ripmiatin; Yunus Effendi
Lontar Komputer : Jurnal Ilmiah Teknologi Informasi Vol. 9, No. 3 December 2018
Publisher : Institute for Research and Community Services, Udayana University

Breast cancer is the most important cause of death among women. A prediction of breast cancer in early stage provides a greater possibility of its cure. It needs a breast cancer prediction tool that can classify a breast tumor whether it was a harmful malignant tumor or un-harmful benign tumor. In this paper, two algorithms of machine learning, namely Support Vector Machine and Extreme Gradient Boosting technique will be compared for classification purpose. Prior to the classification, the number of data attribute will be reduced from the raw data by extracting features using Principal Component Analysis. A clustering method, namely K-Means is also used for dimensionality reduction besides the Principal Component Analysis. This paper will present a comparison among four models based on two dimensionality reduction methods combined with two classifiers which applied on Wisconsin Breast Cancer Dataset. The comparison will be measured by using accuracy, sensitivity and specificity metrics evaluated from the confusion matrices. The experimental results have indicated that the K-Means method, which is not usually used for dimensionality reduction can perform well compared to the popular Principal Component Analysis.

Preferensi Dosen Pada Proses Penjadwalan Kuliah Menggunakan Algoritma Genetik Studi Kasus: Universitas Al Azhar Indonesia Dody Haryadi; Ade Jamal
JURNAL Al-AZHAR INDONESIA SERI SAINS DAN TEKNOLOGI Vol 3, No 2 (2015)
Publisher : Universitas Al Azhar Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36722/sst.v3i2.191

Abstrak - Proses penjadwalan kuliah di suatu Universitas merupakan suatu proses yang memiliki peran penting. Dengan adanya sistem yang dapat melakukan penjadwalan dengan mempersingkat proses dan tidak adanya jadwal yang bentrok, kegiatan perkuliahan akan berjalan secara tertib. Penelitian ini akan membahas mengenai proses penjadwalan kuliah di Universitas Al Azhar Indonesia (UAI) dengan menggunakan algoritma genetika. Analisa kebutuhan sistem dilakukan sesuai dengan proses bisnis penjadwalan kuliah di UAI. Pada algoritma genetika ini terdapat hard constrain dan soft constrain yang bisa ditentukan sesuai dengan kebutuhan, seperti satu jadwal kuliah tidak boleh ada yang beririsan dengan jadwal kuliah yang lainnya. Sistem dapat merekam jadwal yang dapat dipenuhi dan juga tidak dapat dipenuhi dosen, sehingga ketika dalam proses penjadwalan, sistem dapat mencari waktu pengganti lainnya. Terdapat perubahan proses bisnis penjadwalan kuliah di UAI, dan juga berdampak pada pengembangan sistem informasi penjadwalan kuliah. Terdapat input dan output file json yang digunakan untuk komunikasi antara sistem informasi penjadwalan kuliah yang ada dengan sistem penjadwalan algoritma genetik. Kata Kunci – Penjadwalan Kuliah, Algoritma Evolusi, Presensi Waktu Dosen Abstract - The process of scheduling a lecture at a university is a process that has an important role. With a system that can perform scheduling by shortening the process and the absence of conflicting schedules, lecture activities will run in an orderly manner. This research will discuss about the process of scheduling lecture at Al Azhar University of Indonesia (UAI) by using genetic algorithm. Analysis of system requirements is done in accordance with business process scheduling lectures at UAI. In this genetic algorithm there is a hard constrain and soft constrain that can be determined according to need, such as a lecture schedule should not be any that incline with other lecture schedules. The system can record schedules that can be met and also can’t be met lecturers, so that when in the process of scheduling, the system can find another replacement time. There is a change in the business process of lecture scheduling in UAI, and also has an impact on the development of lecture scheduling information system. There is an input and output json file that is used for communication between existing lecture scheduling information systems with genetic algorithm scheduling system. Keywords - Scheduling Lectures, Evolution Algorithm, Lecturer Time Presentation

A Continuous Topography Approach for Agent Based Traffic Simulation, Lane Changing Model Ade Jamal
JURNAL Al-AZHAR INDONESIA SERI SAINS DAN TEKNOLOGI Vol 2, No 1 (2013)
Publisher : Universitas Al Azhar Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36722/sst.v2i1.96

Traffic simulation has been being an interesting research subject for transport engineer and scientist, mathematicians and informatics scientist for different point of view. Transport scientists study the traffic complexity and behaviour of traffic participants by using statistical experiment or simulation. The earlier approach was based on macroscopic model deducted from hydrodynamics kinematic wave analogy. Later on the microscopic model was introduced first by invoking cellular automata and then agent based model takes important role in the traffic simulation world. Most of microscopic model are based on a multi-grid element topography model which is a natural environment of cellular automata. Just recently a software engineer started an ambitious work to develop a multipurpose framework for complex traffic simulation. The ingenious idea is to replace the traditional grid based element topography with a continuous two dimensional one from which a region of traffic road or street is built up. Traffic participant is modelled as agent whose physical properties such as its coordinate position, speed, and direction are governed by the kinematic Newtonian law. This article will present this new concept and show how the simple movement of lane changing model that is very well known from the beginning era of traffic simulation become a quite complex movement in the new continuous topography

Segmentasi Gigi pada Dental Panoramic Radiograph untuk Identifikasi Manusia Latifah Ramadhana Murilmiani Effendhi; Ade Jamal; Solechoel Arifin; Teguh Widodo
JURNAL Al-AZHAR INDONESIA SERI SAINS DAN TEKNOLOGI Vol 5, No 1 (2019)
Publisher : Universitas Al Azhar Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36722/sst.v5i1.320

Abstrak – Indonesia memiliki tingkat kerawanan tinggi terhadap bencana alam dan kecelakaan yang mengakibatkan terjadinya korban massal. Banyak cara untuk mengidentifikasi korban, salah satunya menggunakan citra gigi. Gigi merupakan bagian dari tubuh yang lebih tahan lama karena struktur gigi yang padat dan kuat. Identifikasi menggunakan sarana gigi dapat dilakukan dengan cara membandingkan data gigi yang telah diperoleh dari pemeriksaan gigi jenazah yang tidak dikenal (data postmortem) dengan data gigi yang sebelumnya pernah dibuat (data antemortem). Terdapat beberapa tahapan dalam melakukan identifikasi korban menggunakan citra gigi. Tahapan yang dilakukan oleh peneliti adalah tahap segmentasi gigi. Pertama, citra dilakukan cropping hingga mendapatkan dimensi berukuran 1564×589 piksel serta perbaikan citra menggunakan Histogram Equalization. Selanjutnya dilakukan pemisahan citra gigi menggunakan metode Integral Projection dilengkapi penggunaan Spline Interpolation untuk menggambar garis pemisah antara rahang atas-bawah serta gigi tunggal. Tiap citra memiliki nilai n-blok kolom yang berbeda sehingga dibutuhkan parameter sebesar 3 hingga 30 n-blok kolom untuk membentuk garis pemisah rahang atas-bawah. Citra gigi berjenis Dental Panoramic Radiograph. Hasil evaluasi kesalahan terkecil saat melakukan pemisahan rahang atas-bawah menggunakan Horizontal Integral Projection sebesar 56.8% dengan nilai n-blok kolom adalah 8 dan saat segmentasi gigi pada tahap Vertical Integral Projection sebesar 38.27% dengan nilai average filter adalah 17.Abstract – Indonesia has a high level of vulnerability to natural disasters and accidents that result in mass casualties. There are many ways to identify victims, especially by using dental images. The teeth are part of the body that are more durable because of the solid and strong tooth structure. Identification using dental images can be done by comparing dental data that has been obtained from unknown victim dental examination (postmortem data) with dental data previously made (antemortem data). There are several stages in identifying victims using dental images and researcher worked on tooth segmentation stage. First, the image need to cropped up to get dimensions size of 1564×589 pixels and improved contrast using Histogram Equalization method. Then, tooth separation is performed using Integral Projection method which is equipped with the use of Spline Interpolation to draw the separator line between the upper-lower jaws and single tooth. Each image has a different n-block column value, so researcher selected range number of n-block column is between 3-30. In this reseach, dental panoramic radiographs are used. The smallest error rate in the images is found when performing an Integral Projection to separate upper and lower jaws by 56.8% with n-block column value = 8 and when separating each tooth from the image by 38.27% with average filter value = 17.Keywords – Antemortem, Postmortem, Segmentation, Histogram Equalization, Integral Projection, Spline Interpolation

University Course Scheduling using the Evolutionary Algorithm Ade Jamal
JURNAL Al-AZHAR INDONESIA SERI SAINS DAN TEKNOLOGI Vol 1, No 1 (2011)
Publisher : Universitas Al Azhar Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36722/sst.v1i1.12

Course scheduling problem is hard and time-consuming to solve which is commonly faced by academic administrator at least two times every year. This problem can be solved using search and optimization technique with many constraints. This problem has been well studied in the past, and still becomes favorite subject for researchers. We will briefly discuss the convergence difficulty in our initial work on this subject using a modified hill-climbing search technique[8]. In this paper, an evolutionary algorithm is applied to solve the course scheduling problem and studying mutation techniques involved in the algorithm.

Aplikasi Berorientasi Objek untuk Perhitungan Bagian Waris Berdasarkan Hukum Islam Ade Jamal; Arif Supriyanto; Fatimah Ilona Asa; Annisa Utami; Bagus Mauludin
JURNAL Al-AZHAR INDONESIA SERI SAINS DAN TEKNOLOGI Vol 2, No 4 (2014)
Publisher : Universitas Al Azhar Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36722/sst.v2i4.159

Abstrak – Pembagian harta waris dalam keluarga merupakan hal yang krusial yang dapat memicu pertikaian yang menimbulkan keretakan hubungan dalam keluarga. Penyebabnya adalah kurangnya pemahaman ahli waris/ pihak-pihak yang terkait mengenai ilmu faraidh (Ilmu Waris). Teknologi informasi yang berkembang pesat idealnya mampu memberikan kontribusi kepada masyarakat Muslim untuk memudahkan dalam menghitung pembagian waris. Dalam penelitian ini, dibuat Perancangan Software aplikasi berorientasi objek untuk perhitungan bagian waris berdasarkan hukum waris Islam. Di dalam pemrograman berorientasi objek terdapat beberapa fitur berikut: Enkapsulasi (Encapsulation); Abstraksi (Abstraction); Pewarisan (Inheritance); dan Polimorfisme (Polymorphism). Tampilan aplikasi terdiri dari Menu Utama yang berisi seluruh ahli waris digunakan untuk memasukkan kelompok ahli waris, pilihan hukum waris berdasarkan Hukum kompilasi Islam RI dan Mazhab Syaf’i dan Hasil Hitung berupa tampil tabel dan cetak pdf. Abstract – The division an inheritance in the family is crucial, and has a potential to trigger conflicts in the family. The cause is a lack of understanding of the heir / related parties regarding the science of faraidh (the science of inheritance). Rapid development of information technology, ideally should be able to contribute to the Muslim community in calculating the division of inheritance. In this study, we designed an object-oriented application software to calculate inheritance based on the Islamic law. In the object-oriented programming are the following features: Encapsulation (Encapsulation); Abstraction, inheritance and polymorphism. Display application consists of a Main Menu that contains all the heirs, the choice of inheritance law based on compilation of Islamic Law in the Republic of Indonesia, and the mazhab (school) of Syaf’i result of the calculation which appear in the form of tables and print out pdf. Keyword – inheritance law, software, inheritance, object-oriented programming, count.

Pengembangan Database Genbank UAI-Bioinformatics Menggunakan Sistem Terdistribusi Ade Jamal; Denny Hermawan; Muhammad Nugraha
JURNAL Al-AZHAR INDONESIA SERI SAINS DAN TEKNOLOGI Vol 2, No 3 (2014)
Publisher : Universitas Al Azhar Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36722/sst.v2i3.138

Abstrak – Telah dilakukan penelitian tentang pengolahan terdistribusi data genbank menggunakan Hadoop Distributed Filesystem (HDFS) dengan tujuan mengetahui efektifitas pengolahan data genbank khususnya pada pencarian sequens dengan data masukan yang berukuran besar. Penelitian dilakukan di Laboratorium Jaringan Universitas Al Azhar Indonesia dengan menggunakan 6 komputer dan satu server dimana dalam Hadoop menjadi 7 node dengan rincian 1 namenode, 7 datanode, 1 secondary namenode. Dengan eksperimen HDFS menggunakan 1 node, 2 node, 4 node, 6 node, dan 7 node dibandingkan dengan Local Filesystem. Hasil menunjukan proses pencarian sequens data genbank menggunakan 1 – 7 node pada skenario eksperimen pertama dengan output yang menampilkan hasil 3 field (Locus, Definition, dan Authors), skenario eksperimen kedua dengan output yang menampilkan hasil 3 field (Locus, Authors, dan Origin), dan skenario eksperimen ketiga menggunakan HDFS dan LFS dengan output yang menampilkan seluruh field yang terdapat dalam data genbank (Locus, Definition, Accesion, Version, Keywords, Source, Organism, Reference, Authors, Title, Journal, Pubmed, Comment, Features, dan Origin). Evaluasi menunjukan bahwa proses pencarian sequens data genbank menggunakan HDFS dengan 7 node adalah 4 kali lebih cepat dibandingkan dengan menggunakan 1 node. Sedangkan perbedaan waktu pada penggunaan HDFS dengan 1 node adalah 1.02 kali lebih cepat dibandingkan dengan Local Filesystem dengan 4 core processor. Abstract - A research on distributed processing of GenBank data using Hadoop Distributed File System GenBank (HDFS) in order to know the effectiveness of data processing, especially in the search sequences with large input data. Research conducted at the Network Laboratory of the University of Al Azhar Indonesia using 6 computers and a server where the Hadoop to 7 nodes with details 1 namenode, 7 datanode, 1 secondary namenode. With HDFS experiments using 1 node, node 2, node 4, node 6, and 7 nodes compared with the Local Filesystem. The results show the search process of data GenBank sequences using 1-7 nodes in the first experiment scenario with an output that displays the results of 3 fields (Locus, Definition, and Authors), a second experiment scenario with an output that displays the results of 3 fields (Locus, Authors, and Origin) , and the third experiment scenarios using HDFS and LFS with output that displays all the data fields contained in GenBank (Locus, Definition, Accesion, Version, Keywords, Source, Organism, Reference, Authors, Title, Journal, Pubmed, Comment, Features, and Origin). Evaluation shows that the search process of data GenBank sequences using HDFS with 7 nodes is 4 times faster than using one node. While the time difference in the use of HDFS with one node is 1:02 times faster than the Local File System with 4 core processor. Keywords – genbank, sequens, distributed computing, Hadoop, HDFS

Pengembangan Sistem Informasi Perpustakaan Menggunakan Teknologi Google Web Toolkit (GWT) Winangsari Pradani; Ade Jamal; Arie Wahyu Triansyah; Annisa Utami
JURNAL Al-AZHAR INDONESIA SERI SAINS DAN TEKNOLOGI Vol 2, No 2 (2013)
Publisher : Universitas Al Azhar Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36722/sst.v2i2.130

Abstrak - Stock opname merupakan salah satu kegiatan penting pada perpustakaan dalam pemeliharaan koleksi pustaka. Kegiatan stock opname adalah melakukan pencocokan data antara koleksi pustaka yang ada di rak-rak buku dengan pangkalan data yang dimiliki perpustakaan. Pada saat ini kegiatan stock opname pada Perpustakaan SMP/SMA Al-Azhar Kebayoran Baru belum dilaksanakan secara rutin karena keterbatasan tenaga SDM. Perpustakaan SMP/SMA Al Azhar telah menggunakan aplikasi Senayan Library Management System (SLiMs) yang bersifat open source. Di lain pihak, Teknik Informatika UAI juga memiliki satu sistem aplikasi perpustakaan yaitu Sistem Informasi Perpustakaan berbasis desktop (SIAP). Modul mobile stock opname telah ada di aplikasi SIAP. Dalam kegiatan penelitian ini modul stock opname SIAP akan ditempelkan kepada sistem SLiMS. Dengan modul aplikasi mobile stock opname yang ada pada handset atau komputer tablet, pustakawan dapat langsung memasukkan data hasil pemeriksaan pada saat kegiatan berlangsung. Langkah mencetak daftar koleksi dan pencatatan manual tidak diperlukan lagi. Jika sebelumnya kegiatan stock opname dilakukan 3 langkah, dengan sistem baru menjadi 1 langkah. Waktu yang dibutuhkan untuk pencatatan berkurang hingga tinggal 50% dari waktu semula. Abstract - Stock opname is one of the important activities of the library in the maintenance of library collections. Stock opname is doing data matching between the existing library collections in bookshelves with a database owned by the library. At this time, stock opname actifity in the library SMP / SMA Al-Azhar Kebayoran Baru has not been implemented on a regular basis due to limited human resources personnel. Library SMP / SMA Al Azhar have used the application Senayan Library Management System (SLiMs), which is open source. On the other hand, Information Engineering UAI also has a library application system is Sistem Informasi Perpustakaan berbasis desktop (SIAP). Mobile module inventory check has existed in the SIAP. In this research activity, stock opname module in SIAP will be attached to the SLiMs. With the mobile application modules existing inventory check on the handset or tablet computer, librarians can directly enter data at the time of examination activities take place. Step print a list of collection and manual recording is not required anymore. If previous activities carried out stock taking three steps, with the new system into one step. The time required for recording reduced to 50% of the original time.

PENGENALAN DAN PELATIHAN PEMROGRAMAN DASAR BLOCKLY KEPADA SISWA SMA AL AZHAR 1, 2 DAN 3 Riri Safitri; Ade Jamal; Endang Ripmiatin; Denny Hermawan; Arif Supriyanto
Jurnal Pemberdayaan Masyarakat Universitas Al Azhar Indonesia Vol 1, No 1 (2019)
Publisher : Universitas Al Azhar Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36722/jpm.v1i1.331

Abstrak Teknologi komputer mempengaruhi setiap bidang kehidupan saat ini. ia masuk dan mengubah setiap bidang di dunia, mulai dari industri dan bisnis, transportasi, komunikasi, kesehatan, dan lain-lain. Setiap siswa memiliki kesempatan yang sama untuk mempleajari dan menguasai teknologi, belajar coding, menguasai algoritma, mempelajari bagaimana cara membuat aplikasi, bagaimana internet bekerja, dalam rangka memupuk kreativitas dan keterampilan menyelesaikan masalah (problem solving) yang akan sangat berguna bagi kehidupan mereka di masa depan. Program komputer/perangkat lunak atau software akan menjadi hal yang sangat penting, bahkan mungkin akan menjadi bahasa dunia ke depan. Tidak menguasai programming atau bahasa komputer di masa depan, akan sama efeknya dengan tidak bias baca tulis saat ini. Belajar ilmu komputer tidak hanya belajar tentang teknologi itu sendiri, namun juga belajar logika, penyelesaian masalah (problem solving), dan kreativitas. Oleh karena itu perlu adanya pengenalan dan pelatihan pemrograman untuk siswa sekolah untuk melatih kemampuan logika dan problem solving. Pelatihan pemrograman diberikan dalam bentuk simulasi Blockly berupa games yang menarik dan interaktif. Hasil dari pelatihan didapatkan bahwa siswa SMA peserta pelatihan merasa kegiatan ini sangat menarik dan bermanfaat dan dapat menambah pamahaman dan keterampilan mereka dalam hal IT dan penerapannya.Kata kunci: Coding, Komputer, Pemrograman, TIKAbstractComputer technology affects every area of life today. he entered and changed every field in the world, starting from industry and business, transportation, communication, health, and others. Every student has the same opportunity to learn and master technology, learn coding, master algorithms, learn how to make applications, how the internet works, in order to foster creativity and problem solving skills that will be very useful for their lives in the future . Computer / software or software programs will be very important, maybe even become the world language in the future. Not mastering programming or computer language in the future, it will have the same effect as the current non-literacy. Learning computer science not only learns about technology itself, but also learns logic, problem solving, and creativity. Therefore there is a need for introduction and programming training for school students to practice logic and problem solving skills. Programming training is provided in the form of Blockly simulations in the form of interesting and interactive games. The results of the training found that high school students participating in the training felt this activity was very interesting and useful and could add to their understanding and skills in terms of IT and its application. Keywords: Coding, Computer, Computer Science, Programming

Embryo Grading after In Vitro Fertilization using YOLO Dewi Ananta Hakim; Ade Jamal; Anto Satriyo Nugroho; Ali Akbar Septiandri; Budi Wiweko
Lontar Komputer : Jurnal Ilmiah Teknologi Informasi Vol 13 No 3 (2022): Vol. 13, No. 3 December 2022
Publisher : Institute for Research and Community Services, Udayana University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/LKJITI.2022.v13.i03.p01

In vitro fertilization is an implementation of Assistive Reproductive Technology. This technology can produce embryos outside the mother's womb by manipulating gametes outside the human body. The success rate of in vitro fertilization is the selection of good-grading embryos. In this study, the authors used Yolo Version 3 to perform object detection objectively by introducing grades for each embryo image. The author uses an embryo image sourced from the Indonesian Medical Education and Research Institute with information on the quality of the embryo. In this study, the author separated the data into two schemes. The first scheme separates data into training data of 70%, 15% validation data, and 15% for testing data. The second scheme uses a Stratified K-Fold Cross-Validation with a fold value =3. In training, the writer configures the values ??of Max Batches=6000, Steps=4800,5400, Batch=64, and Subdivision=16 by doing image augmentation (saturation=1.5, exposure=1.5, hue=0.1, jitter=0.3, random=1). For each of the obtained mAP (Mean Average Precision) values ??for data separation schemes, one is 100.00% in the 6000th iteration, while for the two-data separation scheme, the highest mAP is 97.33%.% in the fold=3 and 5000th iteration. It means that both separation schemes are sufficient in terms of mAP.

Title Search

Found 11 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 11 Documents
Search