Claim Missing Document
Check
Articles

Found 20 Documents
Search

Aplikasi Sistem Pakar Berbasis Android untuk Diagnosa Awal Penyakit Ginjal Manusia Menggunakan Metode Forward Chaining Winda Wahyuti; Inggih Permana; Febi Nur Salisah
Seminar Nasional Teknologi Informasi Komunikasi dan Industri 2018: SNTIKI 10
Publisher : UIN Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (388.247 KB)

Abstract

Penyakit ginjal manusia membutuhkan dokter spesialis untuk mendiagnosanya. Saat ini jumlah dokter spesialis ahli ginjal di Indonesia masih sedikit. Keterbatasan jumlah dokter di bidang ini menyulitkan masyarakat dalam mendiagnosa penyakit ginjal. Oleh sebab itu, paper ini membangun aplikasi sistem pakar untuk memudahkan masyarakat dalam melakukan diagnosa awal penyakit ginjal. Basis pengetahuan sistem pakar ini dibuat dalam bentuk if-then rule. Metode inferensi yang digunakan adalah forward chaining. Rule yang dihasilkan pada proses pembuatan basis pengetahuan berjumlah 18, terdiri dari 8 penyakit dan 49 gejala. Aplikasi sistem pakar ini dibuat berbasis Android agar bisa digunakan oleh masyarakat kapan saja dan dimana saja. Berdasarkan hasil unit test aplikasi yang dibuat telah berhasil melakukan inferensi secara forward chaining dengan benar. Berdasarkan uji black box fitur-fitur di aplikasi berjalan baik, dengan tingkat keberhasilan 100%. Berdasarkan hasil user acceptance test penerimaan aplikasi sistem pakar ini sangat baik, yaitu 83,8%.
An Nation: Aplikasi Pembelajaran Berbasis Android untuk TK Islam Fadil Rahmat Andini; Inggih Permana; Febi Nur Salisah
Seminar Nasional Teknologi Informasi Komunikasi dan Industri 2018: SNTIKI 10
Publisher : UIN Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (642.341 KB)

Abstract

Yayasan Taman Kanak-Kanak (TK) XYZ adalah lembaga pendidikan Islam untuk anak usia dini. Untuk mempermudah peserta didik dalam memahami materi pembelajaran, TK ini menggunakan berbagai macam media pembelajaran. Akan tetapi, jumlah media pembelajaran pada TK ini terbatas. Keterbatasan tersebut membuat tidak semua peserta didik dapat menggunakan media pembelajaran secara maksimal. Studi ini telah membangun aplikasi pembelajaran berbasis Android untuk mengatasi permasalahan tersebut. Aplikasi ini diberi nama An Nation. Pengembangan aplikasi ini menggunakan Metode Waterfall. Aplikasi yang sudah dibangun memiliki fitur pembelajaran tentang angka, huruf, objek anggota tubuh, hafalan doa pendek, dan surah sehari-hari. Masing-masing fitur memiliki tiga bahasa, yaitu Indonesia, Inggris, dan Arab. Berdasarkan hasil uji black box, fitur-fitur yang dibuat berjalan dengan tingkat keberhasilan 100%. Berdasarkan hasil user acceptance test, tingkat penerimaan Aplikasi An Nation sangat baik, yaitu 92,07%.
SISTEM PENDUKUNG KEPUTUSAN BERBASIS RULE UNTUK PEMILIHAN MODEL HIJAB Uci Indah Sari; Inggih Permana; Febi Nur Salisah
Seminar Nasional Teknologi Informasi Komunikasi dan Industri 2017: SNTIKI 9
Publisher : UIN Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (766.191 KB)

Abstract

Pemilihan model hijab yang tepat tergantung pada bentuk wajah dan tempat pemakaian. Beragamnya model hijab menyebabkan muslimah kesulitan memilih model hijab yang tepat tersebut. Oleh sebab itu, studi ini membangun sistem pendukung keputusan (SPK) berbasis if-then rule untuk pemilihan model hijab berdasarkan bentuk wajah dan tempat pemakaian. SPK ini diimplementasikan pada aplikasi Android. Metode inferensi yang digunakan pada penelitian ini adalah forward chaining. Pada SPK ini terdapat 50 keputusan model hijab. Berdasarkan hasil analisa, SPK ini membutuhkan 19 kriteria dan 1970 rule. Hasil uji black box menunjukkan fitur-fitur pada aplikasi SPK berjalan 100%. Hasil user acceptance test yang dilakukan oleh 30 muslimah menunjukkan tingkat penerimaan aplikasi adalah 98.33%.
Pemanfaatan Google Earth Imagery untuk Segmentasi Lahan Hijau Nesdi Evrilyan Rozanda; Ismail Marzuki; Inggih Permana
Seminar Nasional Teknologi Informasi Komunikasi dan Industri 2012: SNTIKI 4
Publisher : UIN Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (701.494 KB)

Abstract

Google Earth merupakan sebuah virtual globe yang merekam hasil rekaman satelit secara langsung. Citra permukaan bumi ditampilkan oleh aplikasi Google Earth dengan resolusi yang berbeda sesuai dengan kepentingan dan interest points penggunanya. Salah satu pemanfaatan citra hasil rekaman Google Earth ini sudah dimanfaatkan untuk kepentingan penelitian.Para peneliti menggunakan Google Earth untuk beragam bidang penelitian karena kemudahan dan originalitas citra yang diberikan. Pada penelitian ini, pemanfaatan Google Earth imagery digunakan untuk proses segmentasi lahan hijau di Kota Pekanbaru dengan teknik pengolahan citra yang mengimplemtasikan metode K-Means Clustering. Jumlah cluster yang diharapkan ada dua, yaitu cluster sebaran lahan hijau dan cluster tidak lahan hijau. Hasil yang diperoleh adalah bahwacitra Google Earth terbukti dapat dijadikan sebagai bahan penelitian untuk segmentasi citra dengan menggunakan metode K-Means Clustering. Dua cluster output yang diharapkan berhasil di cluster dengan metode ini.
Comparison of Classification Algorithm Performance for Diabetes Prediction Using Orange Data Mining Hafiz Aryan Siregar; Muhammad Zacky Raditya; Aditya Nugraha Yesa; Inggih Permana
Indonesian Journal of Data and Science Vol. 4 No. 3 (2023): Indonesian Journal of Data and Science
Publisher : yocto brain

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56705/ijodas.v4i3.103

Abstract

Diabetes is a disease that contributes to a relatively high mortality rate. The human death rate due to diabetes is a widespread issue globally. The primary goal of this research is to predict individuals suffering from diabetes using a publicly available dataset from the UCI Repository with the Diabetes Disease dataset. To obtain the best classification algorithm, a comparison is made among three algorithms: KNN, Naive Bayes, and Random Forest, commonly used for predicting diabetes. The comparison results indicate that the Random Forest algorithm is the appropriate and accurate algorithm for predicting individuals with diabetes, with an accuracy rate of 97%.
Analisis Kepuasan Mahasiswa Pekanbaru Pada Aplikasi Flip dengan Metode End User Computing Satisfaction (EUCS) Anggi Widya Atma Nugraha; Inggih Permana; Febi Nur Salisah; Tengku Khairil Ahsyar; M. Afdal
Journal of Informatics, Electrical and Electronics Engineering Vol. 4 No. 4 (2025): June 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/jieee.v4i4.2439

Abstract

A Flip is a Financial Technology (fintech) company providing admin fee-free money transfer services that has been used by more than 10 million users. Along with technological developments in the financial sector, Flip must be able to compete and survive against similar service providers. Efforts that can be made to compete include measuring satisfaction levels in using Flip. The purpose of this study is to assess the level of satisfaction of Flip users so that the results of this research can be used to provide recommendations for evaluating the Flip information system. In conducting satisfaction level analysis, the End User Computing Satisfaction (EUCS) approach can be applied. EUCS is able to evaluate usage satisfaction in using information systems in the areas of content, accuracy, format, ease of use, and timeliness based on information system usage experience. The research was conducted with sample data from university student users of the Flip application in Pekanbaru City. Based on the test results, the highest result with a percentage value of 80% in the Very Satisfied category was observed in the Ease of Use variable from the Likert scale results. The average satisfaction level of Flip application users was 77% in the Satisfied category. The Classical Assumption Test results showed that in the normality test, the testing was normal, and in the multicollinearity testing, it was found that multicollinearity did not occur in the test results. In the Multiple Linear Regression Test, the variable equation result obtained was Y = 0.158 + 0.114X1 + 0.031X2 + 0.054X3 + 0.111X4 + 0.001X5. Based on the Coefficient of Determination Test results, it was found that the content variable, accuracy variable, format variable, ease of use variable, and timeliness variable were able to explain their relationship to the dependent variable and showed an influence of 53%.
Pengukuran Retensi Pelanggan Insyira Oleh-Oleh Berdasarkan Analisis Sentimen Pengguna Instagram Fiki; Inggih Permana; Febi Nur Salisah; Eki Saputra; Arif Marsal
Journal of Informatics, Electrical and Electronics Engineering Vol. 4 No. 4 (2025): June 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/jieee.v4i4.2473

Abstract

Instagram as a social media platform has opened new opportunities for businesses to market their products creatively and efficiently. Through interactive features such as the comments section, users can express their opinions about the products or services offered. These comments contain sentiments that can be analyzed to understand customer perceptions. This study aims to measure customer retention using sentiment analysis of Instagram user comments. The comment data was collected using web scraping techniques from the Instagram page, followed by labeling using a lexicon-based approach and sentiment classification into positive, negative, and neutral categories through sentiment analysis. This analysis is linked to the concept of customer retention, which is an important strategy for maintaining long-term relationships with consumers. Furthermore, the results of customer retention analysis in this study show that positive sentiment has a retention rate of 53.4% (303 out of 567 comments), neutral sentiment 6.9% (45 out of 650 comments), and negative sentiment 15.1% (22 out of 146 comments). Overall, 370 out of 1,363 comments, or 27.1%, were categorized as contributing to retention. In terms of the proportion of sentiment contributing to total retention, positive comments dominate with 81.9% (303 out of 370). These findings suggest that although neutral comments are the most frequent, positive sentiment contributes the most to customer retention. This indicates that positive sentiment is a strong predictor of customer loyalty, highlighting the importance for companies to foster positive experiences through quality products, reliable services, and active engagement on social media. Insyira is capable of maintaining customer retention, especially from those who express positive sentiment, which reflects satisfaction with its products, services, and interactions on social media
Evaluating the Impact of Data Balancing Techniques on the k-Nearest Neighbors Algorithm for Microarray Data Classification Febi Nur Salisah; Inggih Permana; Sanusi; Shir Li Wang
Jurnal Inotera Vol. 10 No. 2 (2025): July - December 2025
Publisher : LPPM Politeknik Aceh Selatan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31572/inotera.Vol10.Iss2.2025.ID497

Abstract

Microarray data classification poses significant challenges in bioinformatics due to the nature of the data, which has a very high number of features but a limited number of samples, and an unbalanced class distribution. This condition can cause a decrease in the performance of classification models, including k-Nearest Neighbor (kNN). This study aims to evaluate the performance of the kNN algorithm in classifying unbalanced and balanced data. The balancing techniques used are Random Undersampling (RUS), Random Oversampling (ROS), and Synthetic Minority Over-sampling Technique (SMOTE). The datasets used in this study are three leukemia datasets with different class structures, namely two, three, and four classes. The experimental results show that the ROS and SMOTE techniques consistently improve the performance of kNN, with the best accuracy reaching more than 97%. In the two-class dataset, ROS gave the best performance (99.4%), while in the three-class dataset, SMOTE showed the most optimal results (98.5%). In the four-class dataset, the performance improvement due to balancing was very significant; SMOTE and ROS were able to improve the accuracy from 89.7% (without balancing) to 99.0% and 98.8%, respectively. Although RUS recorded perfect accuracy of 100%, the results were anomalous and inconsistent. RUS showed less stable performance and was often lower than the condition without balancing, especially on datasets with four classes. Overall, the SMOTE technique proved to be the most stable and effective for various class structures. This study shows the importance of balancing strategies in the classification of complex and imbalanced microarray data.
Sistem Pakar Diagnosa Gizi Buruk Pada Balita Menggunakan Metode Forward Chaining M Zaky Ramadhan Z; Fitriani Muttakin; Zarnelly; Inggih Permana
KLIK: Kajian Ilmiah Informatika dan Komputer Vol. 4 No. 5 (2024): April 2024
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/klik.v4i5.1776

Abstract

During a child's growth and development, inadequate nutrition can impede both physical and intellectual development. Although many people perceive these issues as commonplace, neglecting them can lead to severe consequences. To address the challenge of a limited number of nutritionists and a growing number of patients, this final project introduces an expert system designed to identify malnutrition in toddlers. The expert system conducts a diagnosis of malnutrition based on observed symptoms and offers recommendations for addressing the issues associated with malnutrition in toddlers. This expert system aims to empower parents to independently identify their children's malnutrition types, potentially alleviating the shortage of nutritionists in the healthcare system. The expert in this study is a nutritionist working at Puskesmas Berkilau Pangkalan Kerinci 2. If the knowledge base and production rules, which consist of comprehensive and accurate information, are in place, they can be applied to develop an inference engine. In this phase, the application guides users in inputting facts (characteristics), enabling the generation of conclusions related to toddler nutrition levels. The knowledge stored in the knowledge base and production rules serves as the foundation for the inference engine
Pengukuran Akuisisi Pelanggan Insyira Oleh-Oleh Berdasarkan Analisis Sentimen Pengguna Instagram Wira Mulia, M. Roid; Inggih Permana; Febi Nur Salisah; Eki Saputra; Arif Marsal
Journal of Informatics, Electrical and Electronics Engineering Vol. 4 No. 4 (2025): June 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/jieee.v4i4.2472

Abstract

Social media, especially Instagram, has transformed how businesses interact with customers and market products. However, there remains a literature gap regarding customer acquisition measurement through sentiment analysis of Instagram comments. This research aims to measure customer acquisition at Insyira Oleh-Oleh Pekanbaru by analyzing 1,363 comments from May 2024 to May 2025 using Python-based Natural Language Processing (NLP). The results show neutral sentiment dominates (47.7%) with the highest acquisition rate (50.9%) - meaning every 2 neutral comments yield 1 acquisition - compared to positive (37.7%) and negative comments (41.8%). The Chi-square test confirms the significant relationship between sentiment and acquisition (?²=21.78; p<0.0001), while (OR=0.58; CI[0.46,0.73]) indicates positive comments have 42% lower acquisition probability than neutral ones, forming triangular consistency that eliminates doubts. Negative sentiment also yields higher acquisition than positive sentiment, challenging the assumption that positive comments are most effective for acquisition. This reveals neutral comments containing product inquiries have greater acquisition potential. The study provides new insights for digital marketing strategy, emphasizing the importance of quick responses to neutral comments to enhance new customer conversion.