Claim Missing Document
Check
Articles

Found 10 Documents
Search

Sistem Pendukung Keputusan Pemilihan Forum Mahasiswa dengan Metode Weighted Product Lia Farokhah; Adriani Kala'lembang
Jurnal Ilmiah Teknologi Informasi Asia Vol 11 No 2 (2017): Volume 11 Nomor 2 (8)
Publisher : LP2M INSTITUT TEKNOLOGI DAN BISNIS ASIA MALANG

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (3159.1 KB) | DOI: 10.32815/jitika.v11i2.219

Abstract

The Selection of forums for students to find a quality forum and can answer their problems that they face about the theme of the lecture is not easy. Generally, students or users face confusion with the many variations of forums on the internet media. In this study, the decision support system designed the selection of student forums in providing the best forum selection solution. The method used in this case study is Weighted Product with the criteria used are the date of posting, the number of answers (answer), the number of people who see (views) and ranking from the Alexa site. Test results from the application are able to select the best alternative for forum selection. In this case, the alternative is the recommendation of the forum that will be recommended to the students based on the weighting of the criteria specified. In general, the results of the four tests wirh verification and validation testing can be concluded that the recommended forum is in accordance with the weighting that is done with the value of accuracy of 100%.
Implementasi Metode SCRUM dalam Perancangan Produk Backlog Sistem Cerita Desa Lia Farokhah; Fadhli Almu'iini Ahda; Lilis Widayanti; Vivi Aida Fitria
Jurnal Informatika: Jurnal Pengembangan IT Vol 5, No 1 (2020): JPIT, Januari 2020
Publisher : Politeknik Harapan Bersama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30591/jpit.v5i1.1658

Abstract

Abstract  The village is the smallest part of governance. Data from the Central Statistics Agency in 2018, villages have poverty greater than cities. The village has various weaknesses and strengths such as economics, psychology, engineering, skills, capital, successful application of hydroponic agriculture and others. On the other hand, collages have mandatory programs for the entire academic such as society dedication, research and internship programs for students. In the business sector, there are companies that are required to carry out CSR (Corporate social responsibility) to follow regulations in Indonesia. The problem of all actors is the inaccurate target of the distribution of aid in their soft skills and hard skills to bring their contribution to village development. Documentation and classification of problems and strengths in the village need to be mapped. Both of these relationships will be mutually beneficial subjects and objects in a development cycle. This study will examine the importance of the backlog product of the system model that will be developed using the SCRUM method. The results of the level of importance and priority of the backlog product will be used in system development and have an influence in determining the next stage of the Scrum method namely sprint planning meeting, sprint execution and scrum analysis. The results of the college backlog priority analysis are facilities 1,3,4,5,8,2 and 6. On the other hand, the priority order of backlog products for villages / communities is facility 1, 4,2,3,6,7,9, and 8 while Facility 5 is a very undesirable only 36%. The conclusions of the synchronization of two stakeholders based on their respective needs are facility 1, which is about the community's need for assistance from tertiary institutions and the needs of objects by tertiary institutions. Abstrak - Desa merupakan bagian terkecil dalam tata kelola pemerintahan. Data Badan Pusat Statistik tahun 2018, desa memiliki tingkat kemiskinan lebih besar dari kota. Desa memiliki berbagai kekurangan dan kelebihan seperti masalah, perekonomian, psikologi, bidang teknik, skill, permodalan, keberhasilan penerapan pertanian hidroponik dan yang lainnya. Disisi lain, perguruan tinggi memiliki banyak program wajib untuk seluruh civitas akademika dosen seperti pengabdian, penelitian dan program magang atau kuliah kerja nyata (KKN) bagi mahasiswa. Pada bidang bisnis, ada perusahan yang wajib melakukan CSR (Corporate social responsibility) sesuai aturan yang diberlakukan di Indonesia. Permasalahan ketiga aktor tersebut adalah kurang tepatnya sasaran penyaluran bantuan dalam softskill maupun hardskill yang mereka miliki untuk membawa kontribusinya bagi pembangunan desa. Dokumentasi dan klasifikasi permasalahan serta kelebihan yang ada di desa perlu dipetakan. Kedua hubungan ini akan menjadi subjek dan objek yang saling menguntungkan dalam sebuah siklus pembangunan.  Penelitian ini akan menguji tingkat kepentingan produk backlog dari model sistem yang akan dikembangkan menggunakan metode SCRUM. Hasil dari tingkat kepentingan dan prioritas produk backlog akan dipakai dalam pengembangan sistem dan memiliki pengaruh dalam menentukan tahap metode scrum berikutnya yaitu sprint planning  meeting, eksekusi sprint dan analisis scrum. Hasil analisis prioritas backlog perguruan tinggi adalah fasilitas 1,3,4,5,8,2 dan 6. Disisi lain, urutan prioritas produk backlog untuk desa/masyarakat adalah fasilitas 1, 4,2,3,6,7,9, dan 8 sedangkan Fasilitas 5 menjadi fasilitas yang sangat tidak diinginkan karena hanya 36 %. Adapun simpulan singkronisasi dua stakeholder berdasarkan kebutuhan masing-masing adalah adalah fasilitas 1 yaitu tentang kebutuhan masyarakat akan bantuan dari perguruan tinggi dan kebutuhan objek oleh perguruan tinggi. Kata Kunci - Teknologi, Desa, Permasalahan, Solusi, Singkronisasi
Perbandingan Metode Deteksi Wajah Menggunakan OpenCV Haar Cascade, OpenCV Single Shot Multibox Detector (SSD) dan DLib CNN Lia Farokhah
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 5 No 3 (2021): Juni 2021
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v5i3.3125

Abstract

Comparison of methods in face detection is needed to provide recommendation of best method. This study compared three methods in face detection, namely OpenCV haar cascade, OpenCV Single Shot Multibox Detector (SSD) and Dlib CNN. Face detection is focused on five challenging conditions, namely face detection in head position obstacles, wearing face masks, lighting, background images that have a lot of noise, differences in expression. Data testing is taken randomly on google with reference to one image consisting of more than one detected face with wild condition. The results of the comparative analysis in wild condition show that the OpenCV haar cascade has more weaknesses with a performance percentage of 20% compared OpenCV SSD and Dlib CNN method. Performance results of SSD and Dlib CNN have the same performance in the five conditions tested, which is about 80%.
IMPLEMENTASI K-MEANS KLUSTERING UNTUK REKOMENDASI TEMA TUGAS AKHIR PADA STMIK ASIA MALANG Lia Farokhah; Rendy Aditya
Jurnal Teknologi dan Manajemen Informatika Vol 3, No 2 (2017): Juli 2017
Publisher : Universitas Merdeka Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26905/jtmi.v3i2.1329

Abstract

DOI: https://doi.org/10.26905/jtmi.v3i2.1329
Implementasi Convolutional Neural Network untuk Klasifikasi Variasi Intensitas Emosi pada Dynamic Image Sequence Lia Farokhah
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 4 No 6 (2020): Desember 2020
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v4i6.2644

Abstract

Facial emotion recognition (FER) is a research topic that focuses on the analysis of human facial expressions. There are many FER research has been conducted on single images or photo. Emotion analysis on single images has many disadvantages compared to dynamic image sequences or videos. This is due to human emotions or expressions within a certain time. The classification of emotions becomes complicated when considering different emotions. There are some people who are very expressive, there are some people who have low or moderate expressions. Predictions of emotion with variety intensities has decresed error due to data sets that provide only a few emotions intensities. Data annotation is a major problem in recognition fields that require a lot of time and effort to annotate new data. This study aims to find information about facial emotions with emotional intensity from subtle to sharp in a sequence images or videos. The dataset will be trained using Convolutional neural network by augmentation to add data annotations. The proposed method was evaluated using the public BP4D-Spontaneous dataset. The evaluation results show that the average emotion recognition in video sequences using the holdout method is 18%. Evaluation of the loss function parameter shows overfitting where the curve generalization gap is too high. The last evaluation is the evaluation of the emotion class between the real class and the prediction class in 14.28%. This shows that the classification of emotion recognition in dynamic image sequences is quite low.
IMPLEMENTASI DECISION TREE C4.5 DALAM PENENTUAN PINJAMAN UANG DI KOPERASI XYZ di BANJARMASIN Lia Farokhah; Rina Dewi Indahsari
KLIK- KUMPULAN JURNAL ILMU KOMPUTER Vol 6, No 3 (2019)
Publisher : Lambung Mangkurat University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20527/klik.v6i3.268

Abstract

Bad credit is an important problem faced by all financial institutions or business entities. Savings and Loan Cooperative xyz is one of the financial business entities that faces these problems. This cooperative has quite a number of customers / borrowers, namely 10,135 customers. Cooperative xyz customers have a current history of returning 9545 people and 590 people stuck in return. Bad loans that occur disrupt the financial rotation of the cooperative because it is related to business entity finance and employee salaries. Processing and analyzing customer / borrower data to obtain knowledge that can help stakeholders in the cooperative in determining a lending decision is urgently needed so that bad loans can be suppressed so that the financial flow of the business entity remains smooth. The data collected has sixteen attributes and one target attribute that is whether lending is accepted or rejected. The method used in processing and analyzing borrower data is the Tree C4.5 method which is a refinement of the ID3 (Iterative Dichotomiser) method. This method is known as an easy to understand method because it will produce a very clear rule in the decision tree. Results of model testing using cross validation random subsampling, this method has an accuracy of 70% with 5 aspects of important attributes namely loan history, other debts, community valuation, salary and electricity data when the data is pruned with four depth levels.Keywords: Classification, Cooperative, Savings and Loans, Data, Method C4.5Kredit macet merupakan permasalahan penting  yang dihadapi semua lembaga atau badan usaha keuangan. Koperasi simpan pinjam xyz merupakan salah satu badan usaha keuangan masyarakat yang menghadapi permasalahan tersebut. Koperasi ini memiliki nasabah/peminjam cukup banyak yaitu 10.135 nasabah/peminjam. Nasabah koperasi xyz memiliki riwayat lancar dalam pengembalian sebanyak 9545 orang dan 590 orang macet dalam pengembalian. Kredit macet yang terjadi menganggu perputaran keuangan koperasi karena  terkait keuangan badan usaha dan gaji pegawai. Pengolahan dan analisis data nasabah/ peminjam untuk memperoleh suatu pengetahuan yang bisa membantu stakeholder di koperasi dalam menentukan sebuah keputusan peminjaman uang sangat dibutuhkan agar kredit macet bisa ditekan sehingga perputaran keuangan badan usaha tetap lancar. Data yang terkumpul memiliki enam belas atribut dan satu target atribut yaitu apakah peminjaman uang diterima atau ditolak. Metode yang dipakai dalam pengolahan dan analisis data peminjam adalah metode Tree C4.5 dimana merupakan penyempurnaan metode ID3 (Iterative Dichotomiser). Metode ini dikenal dengan metode yang mudah dimengerti karena akan menghasilkan sebuah aturan yang sangat jelas dalam pohon keputusan. Dari hasil pengujian model yang terbentuk menggunakan cross validation random subsampling, metode ini memiliki akurasi sebesar 70% dengan 5 aspek atribut penting yaitu riwayat pinjaman, hutang lain, penilaian masyarakat, gaji dan data listrik ketika data di prunning dengan empat kedalaman level.Kata kunci: Klasifikasi, Koperasi, Simpan Pinjam, Data, Metode C4.5
Perbandingan Metode Deteksi Wajah Menggunakan OpenCV Haar Cascade, OpenCV Single Shot Multibox Detector (SSD) dan DLib CNN Lia Farokhah
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 5 No 3 (2021): Juni 2021
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v5i3.3125

Abstract

Comparison of methods in face detection is needed to provide recommendation of best method. This study compared three methods in face detection, namely OpenCV haar cascade, OpenCV Single Shot Multibox Detector (SSD) and Dlib CNN. Face detection is focused on five challenging conditions, namely face detection in head position obstacles, wearing face masks, lighting, background images that have a lot of noise, differences in expression. Data testing is taken randomly on google with reference to one image consisting of more than one detected face with wild condition. The results of the comparative analysis in wild condition show that the OpenCV haar cascade has more weaknesses with a performance percentage of 20% compared OpenCV SSD and Dlib CNN method. Performance results of SSD and Dlib CNN have the same performance in the five conditions tested, which is about 80%.
PELATIHAN PEMBUATAN DESAIN PROTOTIPE APLIKASI MENGGUNAKAN PROTO IO UNTUK MENUMBUHKAN MINAT PEMBELAJARAN PEMROGRAMAN di SMK NASIONAL MALANG Lia Farokhah; Fadhli Almu'iini Ahda; Suastika Yulia Riska
SELAPARANG Jurnal Pengabdian Masyarakat Berkemajuan Vol 3, No 1 (2019): November
Publisher : Universitas Muhammadiyah Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (510.956 KB) | DOI: 10.31764/jpmb.v3i1.1033

Abstract

ABSTRAKMata pelajaran pemrograman merupakan salah satu mata kuliah kosentrasi atau jurusan di Sekolah Menengah Kejuruan (SMK)  atau perguruan tinggi berbasis komputer. Mata kuliah pemrograman menjadi salah satu kesulitan yang dihadapi siswa-siswi maupun mahasiswa dalam menempuh pembelajaran sesuai kosentrasi atau jurusan mereka. Hal ini sangat kontradiksi dengan jurusan yang mereka ambil sehingga perlu di ujicoba pengembangan pedagogi pengajaran untuk menunjang motivasi belajar dalam pemrograman. Pengembangan pembelajaran menjadi sangat penting karena selain kita berada pada abad teknologi yang membutuhkan lebih banyak aplikasi yang harus dikembangan untuk membantu kehidupan manusia. Pengembangan pedagogi pengajaran juga digunakan untuk menumbuhkan motivasi belajar pemrograman agar siswa-siswi atau mahasiswa dengan jurusan atau kosentrasi computer bisa menyukai mata pelajaran pemrograman dimana pada akhirnya menunjang kualitas lulusan yang dihasilkan sesuai bidangnya. Dalam pengembangan pedagogi pada pengabdian masyarakat yang dilakukan di SMK Nasional Malang dilakukan dengan melakukan pre test pertanyaan kuesioner sebelum dan sesudah diadakannya pelatihan pembuatan prototipe aplikasi menggunakan software instan PROTO IO. Hasil yang didapat dari analisis kuesioner didapatkan peningkatan motivasi belajar pemrograman sebesar 76,67% dan peningkatan motivasi minat menjadi programmer sebesar 16,66%. Kata kunci: pedagogi, pemrograman, motivasi belajar, aplikasi ABSTRACTProgramming lesson is one of the concentration courses or majors in Vocational Schools (SMK) or computer-based colleges. Programming lesson become one of the difficulties faced by students according to their concentration or their majors. This is very contradictory with their majors so that  it is necessary to test the development of teaching pedagogy to support learning motivation in programming lesson. The development of learning is very important because besides we are in the technology era that requires more applications that must be developed to help human life. The development of teaching pedagogy is also used to foster motivation to learn programming lesson so students with majors or concentrations of computers can like programming lesson which ultimately support the quality of graduates produced in their fields. In the development of pedagogy on society service carried out in SMK Nasional Malang, questionnaire were conducted before and after the training on making prototype applications using PROTO IO with instant software. The results obtained from questionnaire showed that an increase in programming learning motivation with 76.67% and an increase in motivation to become a programmer of 16.66%. Keywords: pedagogy, programming, learning motivation, application
Implementasi K-Nearest Neighbor untuk Klasifikasi Bunga Dengan Ekstraksi Fitur Warna RGB Lia Farokhah
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 7, No 6: Desember 2020
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jtiik.2020722608

Abstract

Era computer vision merupakan era dimana komputer dilatih untuk bisa melihat, mengidentifikasi dan mengklasifikasi seperti kecerdasan manusia. Algoritma klasifikasi berkembang dari yang paling sederhana seperti K-Nearest Neighbor (KNN) sampai Convolutional Neural Networks. KNN merupakan algoritma klasifikasi yang paling sederhana dalam mengklasifikasikan sebuah gambar kedalam sebuah label. Metode ini mudah dipahami dibandingkan metode lain karena mengklasifikasikan berdasarkan jarak terdekat dengan objek lain (tetangga). Tujuan penelitian ini untuk membuktikan kelemahan metode KNN dan ekstraksi fitur warna RGB dengan karakteristik tertentu. Percobaan pertama dilakukan terhadap dua objek dengan kemiripan bentuk tetapi dengan  warna yang  mencolok di salah satu sisi objek. Percobaan kedua terhadap dua objek yang memiliki perbedaan karakteristik bentuk meskipun memiliki kemiripan warna. Empat objek tersebut adalah bunga coltsfoot, daisy, dandelion dan matahari. Total data dalam dataset adalah 360 data. Dataset memiliki tantangan variasi sudut pandang, penerangan, dan  gangguan dalam latar. Hasil menunjukkan bahwa kolaborasi metode klasifikasi KNN dengan ekstraksi fitur warna RGB memiliki kelemahan terhadap percobaan pertama dengan akurasi 50-60% pada K=5. Percobaan kedua memiliki akurasi sekitar 90-100% pada K=5. Peningkatan akurasi, precision dan recall terjadi ketika menaikkan jumlah K yaitu dari K=1menjadi K=3 dan K=5.Kata kunci: k-nearest neighbour, RGB, kelemahan, kemiripan, bunga  IMPLEMENTATION OF K-NEAREST NEIGHBOR FOR FLOWER CLASSIFICATION WITH EXTRACTION OF RGB COLOR FEATURESThe era of computer vision is an era where computers are trained to be able to see, identify and classify as human intelligence. Classification algorithms develop from the simplest such as K-Nearest Neighbor (KNN) to Convolutional Neural Networks. KNN is the simplest classification algorithm in classifying an image into a label. This method is easier to understand than other methods because it classifies based on the closest distance to other objects (neighbors). The purpose of this research is to prove the weakness of the KNN method and the extraction of RGB color features for specific characteristics. The first  experiment on two objects with similar shape but with sharp color on one side of the object. The second experiment is done on two objects that have different shape characteristics even having a similar colors. The four objects are coltsfoot, daisy, dandelion and sunflower. Total data in the dataset is 360 data. The dataset has the challenge of varying viewpoints, lighting and background noise. The results show that the collaboration of the KNN classification method with RGB color feature extraction has weakness in the first experiment with the level of accuracy about 50-60% at K = 5. The second experiment has an accuracy of around 90-100% at K = 5. Increased accuracy, precision and recall occur when increasing the amount of K, from K = 1 to K = 3 and K = 5.  Keywords: k-nearest neighbour, RGB, weakness, similar, flower
Implementasi Convolutional Neural Network untuk Klasifikasi Variasi Intensitas Emosi pada Dynamic Image Sequence Lia Farokhah
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 4 No 6 (2020): Desember 2020
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v4i6.2644

Abstract

Facial emotion recognition (FER) is a research topic that focuses on the analysis of human facial expressions. There are many FER research has been conducted on single images or photo. Emotion analysis on single images has many disadvantages compared to dynamic image sequences or videos. This is due to human emotions or expressions within a certain time. The classification of emotions becomes complicated when considering different emotions. There are some people who are very expressive, there are some people who have low or moderate expressions. Predictions of emotion with variety intensities has decresed error due to data sets that provide only a few emotions intensities. Data annotation is a major problem in recognition fields that require a lot of time and effort to annotate new data. This study aims to find information about facial emotions with emotional intensity from subtle to sharp in a sequence images or videos. The dataset will be trained using Convolutional neural network by augmentation to add data annotations. The proposed method was evaluated using the public BP4D-Spontaneous dataset. The evaluation results show that the average emotion recognition in video sequences using the holdout method is 18%. Evaluation of the loss function parameter shows overfitting where the curve generalization gap is too high. The last evaluation is the evaluation of the emotion class between the real class and the prediction class in 14.28%. This shows that the classification of emotion recognition in dynamic image sequences is quite low.