Claim Missing Document

Found 5 Documents

Metode K-Means SAW dalam Seleksi Penerima Dana akat pada Badan Amil akat Yunita; Rusdi Efendi; Dian Palupi Rini
Teknomatika Vol 9 No 02 (2019): Teknomatika Vol 09 No 02 September 2019
Publisher : Sekolah Tinggi Manajemen Informatika dan Komputer PalComTech

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


akat is an obligation for Muslims as the implementation of the Five Pillars of Islam including sadaah and infa. The higher the communitys awareness to pay zakat, the more amil zakat boards establish in the community, one of them is Pertaminass amil zakat body (BAMA) in Palembang. The problem currently encountered is that the determination of the recipient of zakat funds must compare the results of the survey one by one so that it is obtained who is most entitled to receive the zakat funds. This procedure may cause relatively high complexity both of time, the accuracy of the results and may affect the target recipient of zakat. The purpose of this study is to minimize the mistakes of BAMA officers in the distribution of zakat funds, so that a decision support system is needed in determining the recipient of zakat funds where the system has been determined based on criteria. K-Means Clustering is a method that groups data according to each cluster. Simple Additive Weighting (SAW) is a method used for the ranking process by using preference values. In this study, the K-Means Clustering method will divide the zakat recipient data according to the distance calculated from the initial position between the zakat recipient data, then the SAW method will sort the zakat recipient data based on each cluster.
Skin Lesion Classification Based on Convolutional Neural Networks Renny Amalia Pratiwi; Siti Nurmaini; Dian Palupi Rini
Computer Engineering and Applications Journal Vol 8 No 3 (2019)
Publisher : Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (490.711 KB) | DOI: 10.18495/comengapp.v8i3.290


Melanoma causes the majority of skin cancer deaths. The population level of melanoma has increased over the past 30 years. It kills around 9.320 people in the US every year. Melanoma can often be found early, when it is most likely to be cured. Medical diagnoses using digital imaging with machine learning methods have become popular because of their ability to recognize patterns in digital images. Image diagnosis accuracy allows disease cured at an early stage. This paper proposes a simulation that can be used for early detection of skin cancer that can help dermatologists to distinguish melanomas from other pigmented lesions on the skin. Some researchers have developed a system using machine learning algorithms used to classify skin lesions from dermoscopy images of human skin. In this study, we proposed Convolutional Neural Network (CNN) to our model. CNN is very efficient for image processing because feature extractors can be optimized, applied to each feature image position. The results of skin lesion classification of benign nevi and melanoma based on CNN models produces high accuracy (area under the receiver operator characteristics (ROC) curve (AUC) is 92.59 %, sensitivity is 89.47%, specificity is 100.0%, precision is 100 % and F1 score is 94.44 %).
Author Matching Classification with Anomaly Detection Approach for Bibliomethric Repository Data Zaqqi Yamani; Siti Nurmaini; Dian Palupi Rini
Computer Engineering and Applications Journal Vol 9 No 2 (2020)
Publisher : Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (564.294 KB) | DOI: 10.18495/comengapp.v9i2.335


Authors name disambiguation (AND) is a complex problem in the process of identifying an author in a digital library (DL). The AND data classification process is very much determined by the grouping process and data processing techniques before entering the classifier algorithm. In general, the data pre-processing technique used is pairwise and similarity to do author matching. In a large enough data set scale, the pairwise technique used in this study is to do a combination of each attribute in the AND dataset and by defining a binary class for each author matching combination, where the unequal author is given a value of 0 and the same author is given a value of 1. The technique produces very high imbalance data where class 0 becomes 98.9% of the amount of data compared to 1.1% of class 1. The results bring up an analysis in which class 1 can be considered and processed as data anomaly of the whole data. Therefore, anomaly detection is the method chosen in this study using the Isolation Forest algorithm as its classifier. The results obtained are very satisfying in terms of accuracy which can reach 99.5%.
Peningkatan Akurasi Prediksi Cnn-Lstm Dan Cnn-Gru Untuk Mendiagnosa Skizofrenia Melalui Sinyal Eeg Gabriel Ekoputra Hartono Cahyadi; Sukemi Sukemi; Dian Palupi Rini
Jurnal Sistem Informasi Vol 14, No 2 (2022)
Publisher : Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36706/jsi.v14i2.19071


AbstrakSkizofrenia adalah gangguan jiwa yang umumnya muncul dalam bentuk halusinasi pendengaran, paranoia, atau cara berbicara dan berpikir yang kacau. Diagnosa penderita Skizofrenia dapat dilakukan dengan menggunakan pemeriksaan sinyal EEG. Penelitian ini melakukan analisa perbandingan metode yang terbaik untuk melakukan klasifikasi EEG menggunakan metode Deep Learning (DL). Penulis menggunakan metode 1D Convolutional Neural Network (1D CNN) yang menggunakan layer berbeda. 1D-CNN pertama menggunakan layer Long short-term memory (LSTM) dan 1D-CNN kedua menggunakan layer Gated Recurrent Unit (GRU). Dataset yang digunakan adalah 28 jenis sinyal EEG yang terdiri dari 14 penderita Skizofrenia dan 14 subjek normal. Hasil pengujian akurasi F1 Score dari CNN yang menggunakan layer LSTM memiliki nilai sebesar 95% dan CNN yang menggunakan layer GRU memiliki nilai 96%. Pengujian kedua metode tersebut menunjukkan bahwa nilai dari CNN-GRU lebih besar dari CNN-LSTM.   
Dermatitis Atopic and Psoriasis Skin Disease Classification by using Convolutional Neural Network Dwi Mei Rita Sari; Siti Nurmaini; Dian Palupi Rini; Ade Iriani Sapitri
Computer Engineering and Applications Journal Vol 12 No 1 (2023)
Publisher : Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18495/comengapp.v12i1.419


Skin is the one of the body parts that play a large role in human physical body. There are so many functions of the skin such as offering protection against fungal infection, bacteria, allergy, viruses and controls the temperature of the body. But, the reported shown that the skin disease is the most common disease in humans among all age groups and a significant root of infection. The diagnosis of skin diseases involves several tests. Due to this, the diagnosis process is seen to be intensely laborious, time-consuming and requires an extensive understanding aspecially for the skin disease that have similar symptoms. Two skin diseases that have similar symptoms and most misdiagnosed are atopic dermatitis and psoriasis. Convolutional Neural Network for image processing and classifying have been developed for more accurate classification of skin diseases with different architectures. However, the accuracy in determining skin lesions using CNNs is on the average level. The factors that affect the accuracy result of a CNN is the depth where gradients vanished as the network goes deeper. Another factor is the variance in the training set which means the need of the large size of training set. Hence, in this study we tried 10 CNN architecture to get the best result for classifying dermatitis atopic and psoriasis. These are VGG 16, VGG 19, ResNet 50, ResNet 101, MobileNet, MobileNet V2, DenseNet 121, DenseNet 201, Inception and Xception. Experimental result shown that the inception V3 architecture give the best result with accuracy for data testing 84%, accuracy for unseen data 82% and confusion matrix with True positive obtained is 248, True Negative is 61, False positive is 54 and False Negative 298.