Garuda - Garba Rujukan Digital

Pengembangan Chatbot Menggunakan Deep Feed-Forward Neural Network sebagai Pusat Layanan Informasi Akademik Faurina, Ruvita; Revanza, Dede; Sopran, Ahmad
Jurnal Eksplora Informatika Vol 11 No 2 (2022): Jurnal Eksplora Informatika
Publisher : Institut Teknologi dan Bisnis STIKOM Bali

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30864/eksplora.v11i2.833

Program studi informatika merupakan salah satu program studi unggulan di Universitas Bengkulu. Sebagai program studi unggulan, tentunya pelayanan terbaik untuk setiap elemen civitas akademika yang ada di Program Studi Informatika Universitas Bengkulu harus diperhatikan. Dalam hal pelayanan ini, adanya pusat layanan informasi akademik bagi civitas akademika di informatika sangat dibutuhkan. Namun, belum adanya pusat layanan informasi akademik yang bisa diakses dari mana dan kapan saja menjadi salah satu hambatan terlaksananya layanan informasi akademik. Pembatasan aktivitas yang memungkinkan terjadinya interaksi akibat pandemi covid-19 juga menjadi kendala. Sebagai upaya menindaklanjuti keterbatasan tersebut dikembangkanlah chatbot layanan informasi akademik program studi informatika untuk mengatasi kendala yang dihadapi. Dengan chatbot layanan informasi akademik ini pengguna dapat bertanya mengenai informasi layanan akademik kepada bot yang akan menjawab informasi yang dibutuhkan. Algoritma yang digunakan dalam penelitian ini adalah deep feed-forward neural network. Adapun knowledge dari chatbot ini berupa informasi mata kuliah, informasi dosen, dan informasi administrasi di Program Studi Informatika Universitas Bengkulu. Pada proses train model, data sebanyak 2059 dibagi menjadi 80% sebagai data train, 10% data validation, dan 10% data test pada epoch 450 dan batch size 100 didapat akurasi 94%, evaluasi Precision 0.88, recall 0,89, dan f1-score 0,88.

Implementasi Deep Feed-Forward Neural Network pada Perancangan Chatbot Berbasis Web di UPPIK RSUD M. YUNUS Faurina, Ruvita; Gazali, M. Jumli; Herani, Icha Dwi Aprilia
Komputika : Jurnal Sistem Komputer Vol. 12 No. 2 (2023): Komputika: Jurnal Sistem Komputer
Publisher : Computer Engineering Departement, Universitas Komputer Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34010/komputika.v12i2.8914

ABSTRACT – The UPPIK (Customer Information and Counseling Complaint Unit) at the M. Yunus Hospital has an important role in serving visitors who come to the hospital. However, visitors often complain about the UPPIK service due to limited working hours, so there is not always staff available to provide the information needed by visitors. In addition, the ongoing Covid-19 pandemic requires people to maintain distance and reduce interaction with others. To solve this problem, an automatic chatbot has been developed to provide service as if the visitor is speaking directly to the staff without any time constraints. This research uses a Deep Feed-Forward Neural Network algorithm. The dataset used is a collection of question-answer data collected through direct observation at the UPPIK, consisting of 1464 pairs of data. The best accuracy was obtained by spliting the dataset into 80% training data (1,185 data), 10% testing data (147 data), and 10% validation data (132 data) with 300 epochs, which resulted in an accuracy of 91.98%. Evaluation of these results showed a precision value of 0.99, a recall value of 0.98, and an f1-score of 0.99. Keywords - UPPIK RSUD M. Yunus Bengkulu; Artificial Intelligence; Chatbot; Deep Feed-Forward Neural Network; Deep Learning

Implementasi Deep Feed-Forward Neural Network pada Perancangan Chatbot Berbasis Web Di UPPIK RSUD M. YUNUS Faurina, Ruvita; Gazali, M Jumli; Herani, Icha Dwi Aprilia
Jurnal Linguistik Komputasional Vol 6 No 2 (2023): Vol. 6, No. 2
Publisher : Indonesia Association of Computational Linguistics (INACL)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26418/jlk.v6i2.123

UPPIK (Unit Pengaduan Pelanggan Informasi dan Konseling) pada RSUD M. Yunus memiliki peran penting dalam melayani pengunjung yang datang. Akan tetapi, tidak jarang dari pengunjung mengeluh dengan pelayanan dari UPPIK karena terbatasnya jam operasional kerja menyebabkan tidak ditemukannya staf/petugas yang berjaga sehingga membuat para pengunjung kebingungan dalam mencari informasi terkait RSUD M. Yunus. Selain itu, pandemi Covid-19 yang belum mereda mengharuskan masyarakat untuk menjaga jarak dan mengurangi interaksi antar individu. Sebagai tindaklanjut dari permasalahan ini dikembangkanlah sebuah automatic chatbot yang dapat melayani pengunjung seolah-olah berbicara langsung dengan staf/petugas tanpa adanya batasan waktu. Pada penelitian ini menggunakan algoritma Deep Feed-Forward Neural Network sebagai intent classifier untuk mengklasifikasi maksud dari pertanyaan yang diajukan oleh user. Deep Feed-Forward Neural Network adalah salah satu jenis Neural Network yang koneksi antar node tidak membentuk looping. Dataset yang digunakan adalah kumpulan data pasangan antara pertanyaan dan jawaban yang dikumpulkan melalui observasi langsung ke UPPIK RSUD M. Yunus dengan jumlah sebanyak 1464 pasangan data. Pengujian dilakukan memakai parameter pembagian dataset, jumlah epoch, dan batch size yang digunakan. Akurasi terbaik didapatkan dengan membagi dataset menjadi 80% data training sebanyak 1057 data, 10% data testing sebanyak 147 data, dan 10% validation sebanyak 132 data menggunakan epoch 300 dan mendapatkan hasil performa akurasi sebesar 91.98%. Sedangkan hasil evaluasi precision sebesar 0.99, recall sebesar 0.98 dan f1-score sebesar 0.99.

Ventilator Non-Invasive berbasis Kontrol Volume dengan Orifice Plate Flow Meter PRIYADI, IRNANDA; HADI, FAISAL; FAURINA, RUVITA; AGUSTIAN, INDRA
ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika Vol 10, No 2: Published April 2022
Publisher : Institut Teknologi Nasional, Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26760/elkomika.v10i2.259

ABSTRAKPada penelitian ini diusulkan ventilator noninvasif dengan sistem kendali volume. Ventilator pada umumnya berbiaya mahal, tidak mudah dibawa dan desain yang rumit. Pada penelitian ini dirancang ventilator noninvasif dengan desain cukup sederhana, mudah dibawa, dan ekonomis. Mekanisme kendali volume didapatkan melalui pengukuran aliran dengan prinsip orifice flow meter. Pengukuran aliran ini dilakukan dengan menurunkan persamaan Bernoulli dan persamaan kontinuitas, sehingga didapat persamaan debit aliran. Koefisien discharge optimal pada persamaan debit aliran yang digunakan pada penelitian ini adalah 0,9. Melalui pengujian RR (Respiratory Rate) 12, 16 dan 20 BPM (Breath Per Minute), minute ventilation terbaik diperoleh pada RR 12, yaitu 498,5541Â±3,3255, dengan simpangan terbesar 4,7714 mL atau sebesar 0,95%. Sedangkan performa terendah pada RR 16 dengan minute ventilation 503,7034Â±4,1626, simpangan terbesar 8,21 mL atau sebesar 1,64%. Ini mengindikasikan bahwa sistem kendali volume pada ventilator noninvasif berkerja dengan cukup baik. Saat ini ventilatorÂ hanya mampu mensuplai tekanan hingga 1,5 kPa atau sekitar 15,296 cmH2O.Kata kunci: ventilator noninvasif, kontrol volume, orifice flow meter, sensor tekanan, koefisien dischargeÂ ABSTRACTIn this research, a ventilator with a volume control system is proposed. Ventilators are generally expensive, not portable, and have a complex design. In this research, a non-invasive ventilator was designed with a fairly simple design, easy to carry, and of economic value. The volume control mechanism is obtained through-flow measurement with the orifice flow meter principle. This flow measurement is done by deriving the Bernoulli equation and the continuity equation, in order to get the flow rate equation. The optimal discharge coefficient in the flow discharge equation used in this study is 0.9. By RR (Respiratory Rate) testing 12, 16, and 20 BPM (Breath Per Minute), the best minute ventilation is obtained at RR 12, which is 498.5541Â±3.3255, with the largest deviation of 4.7714 mL or 0.95%. While the lowest performance is on RR 16 with minute ventilation 503.7034Â±4.1626, the largest deviation is 8.21 mL or 1.64%. A fairly small error indicates that the volume control system on a noninvasive ventilator is designed to work quite well. Currently, the ventilator is only capable of supplying pressure of up to 1.5 kPa or about 15.296 cmH2O.Keywords: non invasive ventilator, volume control, orifice flow meter, pressure sensor, discharge coefficient

Comparison of Convolutional Neural Networks Transfer Learning Models for Disease Classification of Food Crop Faurina, Ruvita; Rahma, Silvia; Vatresia, Arie; Susanto, Agus
JOIV : International Journal on Informatics Visualization Vol 8, No 4 (2024)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/joiv.8.4.1936

Indonesia is an agricultural country with 29% of the workforce working in the agricultural sector, however, farmers' knowledge and practices depend on informal local wisdom based on inherited past practices. Moreover, identifying diseases in plants is difficult to do with human vision so that intelligent technology is needed.Â In this paper, an architecture of CNN models such as MobileNetV2, ResNetV50, InceptionV3 and DenseNet121 will be built to detect diseases based on leaf images of several crops obtained from the agroai dataset containing multiple crops namely bean, chili, corn, potato, tomato and tea. The model is used through transfer learning for feature extraction of the trained model with imagenet weights, with 4 fully connected layers. Each model for each crop will be compared to get the best model based on the accuracy of training, evaluation and testing. ResNet50 has the best performance for four type of plants, including bean plants with training accuracy of 99.49%, validation of 99.52%, testing of 98.96%, chili plants with training accuracy of 98.03%, evaluation of 98.75%, testing of 100%, tea plants with training accuracy of 99.62%, evaluation of 99.6%, testing of 99.74% and tomato plants with training accuracy of 99.62%, validation of 99.7%, testing of 99.37%. Moreover, MobileNetV3 has the best performance for 2 types of crops that is corn with training accuracy of 99.22%, validation of 99.69%, testing of 99.55%, and potato with training accuracy of 99.62%, evaluation of 99.60%, testing of 99.74%.

Sistem Kendali Suhu Mesin Tetas Telur Ayam Buras Menggunakan Kontroler PID dengan Metode Tuning Ziegler Nichols Open Loop Step Response Agustian, Indra; Prakoso, Dian S; Faurina, Ruvita; Daratha, Novalio
JURNAL AMPLIFIER : JURNAL ILMIAH BIDANG TEKNIK ELEKTRO DAN KOMPUTER Vol. 12 No. 1 (2022): Amplifier Mei Vol. 12, No 1 2022
Publisher : UNIB Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33369/jamplifier.v12i1.21535

An egg incubator is a tool that helps the process of hatching eggs using an electric heater and is equipped with an egg rack that functions to evenly distribute the heat in the incubator. Good temperature control in the hatching process is something that greatly affects the hatching results. In this study, an egg incubator temperature control system was designed using the PID method with the Ziegler Nichols Open Loop Step Response tuning method. The control system is specifically for free-range chicken eggs which require a normal temperature of 37 °C-39 °C. The main control components are the microcontroller, the incandescent lamp heater, and the DHT22 temperature sensor. The open loop test shows a time delay of 20 seconds and a time constant of 385 seconds, so with the Ziegler Nichols open loop tuning method, the values of Kp = 23.1, Ki = 40, and Kd = 10. The test results show that the PID controller can control the temperature properly. In testing the hatching process within 21 days, the temperature control worked well, and the effect of changes in day and night temperature did not significantly affect the performance of the PID controller.

Implementasi Algoritma AES 256 CBC, BASE 64, Dan SHA 256 dalam Pengamanan dan Validasi Data Ujian Online Utama, Ferzha Putra; Wijaya, Gusman; Faurina, Ruvita; Vatresia, Arie
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 10 No 5: Oktober 2023
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jtiik.2023106558

Terdapat berbagai macam cara untuk melaksanakan ujian di tingkat perguruan tinggi, selama masa pandemi Covid-19 metode ujian online menjadi banyak digunakan. Meskipun ujian online dapat dilaksanakan di mana saja dan kapan saja, sayangnya masih banyak terjadi kecurangan seperti bocornya soal ujian, tersebarnya kunci jawaban secara ilegal, dan pengubahan pada data hasil ujian. Salah satu solusi dalam menjaga integritas hasil ujian berbasis online adalah mengenkripsi data ujian dengan metode kriptografi. Penelitian ini mengusulkan menerapkan beberapa metode kriptografi sebagai upaya dalam mengamankan dan memastikan keaslian data ujian online menggunakan algoritma AES 256 CBC, Base 64, dan SHA 256. Penelitian ini menghasilkan aplikasi ujian online berbasis website yang dibangun menggunakan teknologi MERN Stack. Hasil pengujian dalam memvalidasi data ujian online yang telah dienkripsi menggunakan sistem dan OpenSSL menunjukkan nilai hash yang sama. Hal ini menunjukkan sistem telah mampu mengenkripsi, mendekripsi, dan memvalidasi data ujian online dengan efektif. Abstract There are various ways to organize exams at the higher education level. During the Covid-19 pandemic, the online examination method has become widely used. Although online exams can be held anywhere and anytime, unfortunately, many violations and fraud exist, such as leaking exam questions, spreading answer keys illegally, and changing exam result data. One solution for maintaining the integrity of online-based exam results is to encrypt exam data with cryptographic methods. This study proposes applying several cryptographic methods to secure and ensure the authenticity of online exam data using AES 256 CBC, Base 64, and SHA 256 algorithms. This research resulted in a website-based online exam application built using MERN Stack technology. The test results in validating online exam data that has been encrypted using the system and OpenSSL show the same hash value. This shows that the system has been able to encrypt, decrypt, and validate online exam data effectively.

Regression Analysis for Crop Production Using CLARANS Algorithm Vatresia, Arie; Faurina, Ruvita; Simanjuntak, Yanti
JOIN (Jurnal Online Informatika) Vol 8 No 1 (2023)
Publisher : Department of Informatics, UIN Sunan Gunung Djati Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15575/join.v8i1.1031

Crop production rate relies on rainfall over Rejang Lebong district. Data showed a discrepancy between increased crop production and rainfall in Rejang Lebong District. However, the spatiotemporal distribution of the crop variable's dependencies remains unclear. This study analyses the relationship between rainfall and crop production rate in the Rejang Lebong district based on the performance of the machine learning method. In addition, this research also performed regression analysis to carry out rainfall clusters and crop production. This order provides information in the form of cluster results to determine how much the rainfall variable influences the crop production rate in each cluster. Harnessing the Elbow, CLARANS, Simple Linear Regression, and Silhouette Coefficient methods, this study used 231 rainfall data sourced from the Bengkulu BMKG and 110 data for plant production obtained from BPS Bengkulu Province from 2000-2022. This research found that the optimal clusters were 3 clusters. C1 contains 106 data with the largest regression value for chili = 0.127, C2 contains 15 data with the largest regression value for mustard greens = 0.135, and C3 contains 110 data with the largest regression value for cabbage = 0.408, eggplant = 0.197, and carrots = 0.201. Furthermore, this research also found that the biggest correlation of crops with highly significant improvement would be cabbage commodity (Y=0.4114X+0.2013) and chili plantation with high RSME (0.9897).

Pengembangan Chatbot Menggunakan Deep Feed-Forward Neural Network sebagai Pusat Layanan Informasi Akademik Faurina, Ruvita; Revanza, Dede; Sopran, Ahmad
Eksplora Informatika Vol 11 No 2 (2022): Jurnal Eksplora Informatika
Publisher : Institut Teknologi dan Bisnis STIKOM Bali

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30864/eksplora.v11i2.833

Program studi informatika merupakan salah satu program studi unggulan di Universitas Bengkulu. Sebagai program studi unggulan, tentunya pelayanan terbaik untuk setiap elemen civitas akademika yang ada di Program Studi Informatika Universitas Bengkulu harus diperhatikan. Dalam hal pelayanan ini, adanya pusat layanan informasi akademik bagi civitas akademika di informatika sangat dibutuhkan. Namun, belum adanya pusat layanan informasi akademik yang bisa diakses dari mana dan kapan saja menjadi salah satu hambatan terlaksananya layanan informasi akademik. Pembatasan aktivitas yang memungkinkan terjadinya interaksi akibat pandemi covid-19 juga menjadi kendala. Sebagai upaya menindaklanjuti keterbatasan tersebut dikembangkanlah chatbot layanan informasi akademik program studi informatika untuk mengatasi kendala yang dihadapi. Dengan chatbot layanan informasi akademik ini pengguna dapat bertanya mengenai informasi layanan akademik kepada bot yang akan menjawab informasi yang dibutuhkan. Algoritma yang digunakan dalam penelitian ini adalah deep feed-forward neural network. Adapun knowledge dari chatbot ini berupa informasi mata kuliah, informasi dosen, dan informasi administrasi di Program Studi Informatika Universitas Bengkulu. Pada proses train model, data sebanyak 2059 dibagi menjadi 80% sebagai data train, 10% data validation, dan 10% data test pada epoch 450 dan batch size 100 didapat akurasi 94%, evaluasi Precision 0.88, recall 0,89, dan f1-score 0,88.

OPTIMIZATION OF DISEASE PREDICTION ACCURACY THROUGH ARTIFICIAL NEURAL NETWORK (ANN) ALGORITHMS IN DIAGNESE APPLICATION Faurina, Ruvita; Gazali, M. Jumli; Herani, Icha Dwi Aprilia
Jurnal Teknik Informatika (Jutif) Vol. 5 No. 2 (2024): JUTIF Volume 5, Number 2, April 2024
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2024.5.2.1182

This research aims to enhance the accuracy and speed of diagnoses in the Diagnese application by implementing the ANN algorithm for disease prediction. The dataset used for experimentation was featuring binary data types, containing 131 symptoms used to predict 41 types of diseases. The Diagnese application assists patients in identifying diseases and finding suitable specialist doctors based on reported symptoms. To achieve this goal, researchers explored various machine learning algorithms, such as decision trees, SVM, Random Forest, Logistic Regression, and ANN. Through comprehensive analysis, the ANN algorithm outperforms other algorithms and showcases the best performance. The research results demonstrate that integrating this application can significantly improve diagnostic accuracy and speed, thereby potentially reducing treatment delays and enhancing patient health outcomes. The neural network model displayed exceptional accuracy across training, validation, and testing datasets, scoring 97%, 99%, and 95%, respectively. Overall, this study showcases the potential of implementing the ANN algorithm within Diagnese applications to elevate the accuracy and efficiency of disease diagnosis. The application of this model is expected to augment the efficiency and precision of the medical diagnosis process, enabling doctors to make more accurate decisions and provide more effective patient care.

Title

Found 11 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 11 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 11 Documents
Search