Claim Missing Document
Check
Articles

Found 37 Documents
Search

Augmentasi Citra Pohon Kelapa Sawit untuk Deteksi Objek Berbasis Deep Learning Dedy Mirwansyah; Achmad Solichin; Fahrullah; Hardi, Richki; Wulan Sari, Nariza Wanti; Arista Rizki, Nanda; Aldo, Dasril
METIK JURNAL (AKREDITASI SINTA 3) Vol. 9 No. 1 (2025): METIK Jurnal
Publisher : LPPM Universitas Mulia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47002/metik.v9i1.1001

Abstract

Penelitian ini menitikberatkan pada Augmentasi citra pohon kelapa sawit untuk deteksi objek menggunakan pendekatan Deep Learning. Pohon kelapa sawit memiliki peran penting dalam industri perkebunan dan pertanian, sehingga pengembangan metode deteksi pohon kelapa sawit yang efisien menjadi krusial dalam pemantauan perkebunan dan pengelolaan sumber daya alam. Metode penelitian melibatkan augmentasi citra, seperti flip, crop, hue, saturation, brightness, exposure dan pra-pemrosesan auto orient dan resize untuk meningkatkan kualitas data pelatihan. Model Deep Learning yang digunakan adalah Convolutional Neural Network (CNN) yang terintegrasi dengan teknik object detection, memungkinkan identifikasi pohon kelapa sawit dari latar belakang dengan akurasi tinggi. Penelitian ini menggunakan 101 citra kepala sawit dan setelah dilakukan augmentasi berjumlah 253 citra pohon kelapa sawit yang bervariasi dalam kondisi pencahayaan, sudut pandang, dan penutupan daun. Hasil eksperimen menunjukkan bahwa metode ini mampu mengidentifikasi pohon kelapa sawit dengan akurasi yang baik, bahkan dalam kondisi yang kompleks. Hasil penelitian ini memiliki potensi aplikasi dalam pemantauan perkebunan kelapa sawit, perencanaan lahan, dan pemantauan lingkungan. Dengan peningkatan akurasi deteksi dan ekstraksi, manajemen perkebunan dan pemantauan lingkungan dapat menjadi lebih efisien dan berkelanjutan.
PELATIHAN ANALISIS DATA DENGAN SOFTWARE R BAGI SISWA SMA NEGERI 8 SAMARINDA Sari, Nariza Wanti Wulan; Sifriyani, Sifriyani; Suyitno, Suyitno; Wahyuningsih, Sri; Yuniarti, Desi; Purnamasari, Ika; Mahmudah, Siti; Nurmayanti, Wiwit Pura; Widyaningrum, Erlyne Nadhilah; Nugraha, Pratama Yuly; Pangruruk, Thesya Atarezcha; Hidayanty, Nurul Ilma; Kosasih, Raditya Arya; Bahriah, Ayu
Jurnal Abdi Insani Vol 12 No 7 (2025): Jurnal Abdi Insani
Publisher : Universitas Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29303/abdiinsani.v12i7.2136

Abstract

Students of SMA Negeri 8 Samarinda have received material on statistics since grade X. In the learning process, teachers use Microsoft Office Excel software which is closed source. So through this community service activity, a solution is provided by disseminating data analysis and alternative open source software 'R'. Community service activities are packaged in the form of training. Evaluation of activities in the form of pretest and posttest questionnaires and activity feedback surveys. This activity was carried out on September 11, 2024 in the Computer Laboratory Room of SMA Negeri 8 Samarinda. The number of students who participated in this activity consisted of 36 students. Based on the analysis of the pre-test and post-test data, it was concluded that there was an increase in student understanding after the training. The results of the feedback stated that the training material was easy, the explanations given were considered interesting, and the training activities were considered useful by the participants. Furthermore, participants hope that there will be follow-up activities to hold similar activities again.
IMPLEMENTATION OF NEURAL NETWORK IN PREDICTING STOCK PRICE OF PT BANK RAKYAT INDONESIA (PERSERO) TBK Nurmayanti, Wiwit Pura; Ni Luh Desvita Pratiwi; Nariza Wanti Wulan Sari; Desi Yuniarti; Erlyne Nadhilah Widyaningrum; Thesya Atarezcha Pangruruk
Multica Science and Technology (ACCREDITED-SINTA 5) Vol. 5 No. 1 (2025): Multica Science and Technology
Publisher : Universitas Mulia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47002/dwkza342

Abstract

Forecasting involves estimating future outcomes by examining patterns in both historical and present data. A commonly used data type in forecasting is time series data, characterized by observations collected at consistent time intervals. One forecasting technique that has gained significant attention is the Neural Network, particularly through the Backpropagation method utilized in this study. In the context of the stock market, price fluctuations are influenced by a variety of factors, including shareholder rights, company performance, and the balance between supply and demand. Typically, a rise in stock prices leads to decreased demand, while a decline tends to stimulate it. Predicting stock prices, such as those of Bank Rakyat Indonesia (BRI), can support investors in making well-informed decisions. This research seeks to identify the optimal number of neurons in the hidden layer for forecasting BRI stock prices by minimizing error metrics such as MAPE, MSE, and MAE. The analysis revealed that forecasting the stock price of PT Bank Rakyat Indonesia (Persero) Tbk. using a neural network with one hidden neuron resulted in a MAPE of 1.22248 and an MAE of 61.30548.
TRAFFIC ACCIDENT VICTIM CLASSIFICATION IN BONTANG USING NW-KNN AND BACKWARD ELIMINATION Mangalik, Gerald; Nariza Wanti Wulan Sari; Surya Prangga; Wiwit Pura Nurmayanti; Ika Purnamasari
Multica Science and Technology (ACCREDITED-SINTA 5) Vol. 5 No. 1 (2025): Multica Science and Technology
Publisher : Universitas Mulia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47002/yfbspb33

Abstract

Traffic accidents have been a serious problem caused by various factors such as road conditions, driver behavior, and weather. To understand the pattern of victim severity, a classification approach capable of handling imbalanced data and irrelevant features was needed. This study aimed to classify the status of accident victims using the Neighbor Weighted K-Nearest Neighbor (NW-KNN) method, equipped with backward elimination for feature selection. Backward elimination was employed to reduce insignificant features and improve accuracy.The case study for this research involved the status of accident victims in Bontang City, with a sample size of 93 cases. There were nine features in this study: accident victim status, accident time, road density, road function, road surface condition, speed limit at the location, road slope, and road status.The research results showed that the best parameter combination for classification using the NW-KNN method with backward elimination was K = 7 and E = 3. The "type of accident" feature was eliminated, leaving 8 features. Classification results using the NW-KNN method with backward elimination yielded an accuracy of 88.89%, demonstrating an improvement in classification performance for identifying the status of traffic accident victims. Thus, this method proved to be an effective approach for traffic accident analysis in Bontang City.
Klasifikasi Data Pasien Penyakit Tuberkulosis Paru Menggunakan Metode Probabilistic Neural Network  (Studi Kasus: Puskesmas Telaga Sari Kota Balikpapan) Ramadhini, Laila Thalia; Fathurahman, M.; Wulan Sari, Nariza Wanti
EKSPONENSIAL Vol. 16 No. 2 (2025): Jurnal Eksponensial
Publisher : Program Studi Statistika FMIPA Universitas Mulawarman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30872/eksponensial.v16i2.1514

Abstract

Pulmonary tuberculosis is an infectious disease that remains a major health problem in Indonesia. Early detection of this disease is very important to improve the effectiveness of treatment and prevention of its spread. The purpose of this study is to classify laboratory test data of pulmonary tuberculosis patients using the Probabilistic Neural Network method. The data used are medical records of patients with pulmonary tuberculosis disease at Puskesmas Telaga Sari, Balikpapan City in 2023-2024. The variables used are age, weight, systolic blood pressure, diastolic blood pressure, cough duration, fever duration, shortness of breath, and loss of appetite. The classification process involves the stages of encoding, data normalization, division of training data and testing data using a proportion of 80:20, and calculation of accuracy using confusion matrix. The results showed that classification using the Probabilistic Neural Network method was appropriate in classifying pulmonary tuberculosis disease and obtained the best smoothing parameter ( ) value of 0.1 with an accuracy value of 82.95% for training data and 95.45% for testing data.
Pengaruh Harga Pelayanan Dan Keselamatan Terhadap Tingkat Kepuasan Mahasiswa Dalam Menggunakan Ojek Online Aulia, Nabila; Afif Nurdiansyah, Mochamad; Shalihatunnisa, Shalihatunnisa; Christian, Diego; Angeline Seru, Indra; Sifriyani, Sifriyani; Wanti Wulan Sari, Nariza; Yuniarti, Desi; Atarezcha Pangruruk, Thesya; Nadhilah Widyaningrum, Erlyne
EKSPONENSIAL Vol. 16 No. 2 (2025): Jurnal Eksponensial
Publisher : Program Studi Statistika FMIPA Universitas Mulawarman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30872/fp39ng21

Abstract

This study aims to analyze the influence of price, service, and safety on the level of satisfaction of FMIPA students at Mulawarman University in using online motorcycle taxi services (Gojek). This study uses a quantitative approach with the Structural Equation Modeling (SEM) method based on Partial Least Square (PLS). A sample of 100 students was obtained through accidental sampling. The variables studied include price, service, safety, and customer satisfaction, each measured by several indicators. The analysis results indicate that the three independent variables (price, service, and safety) have a positive and significant effect on student satisfaction, with safety being the most dominant factor. The R-square value of 0.669 indicates that the model explains 66.9% of the variability in student satisfaction. Validity and reliability tests show that all constructs meet the model's validity criteria. This study suggests that online ride-hailing service providers should prioritize safety aspects, accompanied by improvements in service quality and reasonable price adjustments to enhance user satisfaction.
Penerapan Metode SEM-PLS pada Kepuasan Pengguna Aplikasi Instagram Tamba, Felicia Joy Rotua; Nasywa, Syarifah; Salsabila, Adellia; Khoiruddin, Ahmad Zulfikar; Tandi Kala, Ezra Alfrianto; Sifriyani, Sifriyani; Sari, Nariza Wanti Wulan; Yuniarti, Desi; Nadhilah Widyaningrum, Erlyne; Atarezcha Pangruruk, Thesya
EKSPONENSIAL Vol. 16 No. 2 (2025): Jurnal Eksponensial
Publisher : Program Studi Statistika FMIPA Universitas Mulawarman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30872/a8agna87

Abstract

Social media platforms, particularly Instagram, have emerged as widely utilized channels among diverse user groups, including university students, for information sharing, social interaction, and entertainment purposes. The study seeks to analyze how Instagram quality, perceived benefits, and social interaction contribute to user satisfaction and loyalty within the FMIPA community at Mulawarman University.  The SmartPLS 3.0 software facilitates the use of the Structural Equation Modelling technique based on Partial Least Squares (SEM-PLS) in this investigation.  The results show that each of the three independent factors significantly and favourably affects user pleasure, which in turn significantly boosts customer loyalty. The R-square values of 0.685 for satisfaction and 0.655 for loyalty suggest that the proposed model adequately explains the relationships among the variables. Furthermore, all measurement indicators were confirmed to be both valid and reliable. In conclusion, the study demonstrates that users’ positive perceptions of Instagram’s quality, benefits, and social interaction contribute to enhanced satisfaction and foster greater loyalty toward the platform.
Co-Authors Abdul Rahim Abdurahman Achmad Asdori Achmad Solichin Afif Nurdiansyah, Mochamad Agung Ranggono Aisyiyah Maulisa Nuur Anam, M Khairul Angeline Seru, Indra Arief Hidayat Atarezcha Pangruruk, Thesya Aulia, Nabila Bahriah, Ayu Budi, Ennesya Estya Christian, Diego Dasril Aldo Dedy Mirwansyah Dedy Mirwansyah Desi Yuniarti Dody Novandi Dody Prasetia Purnama Erlyne Nadhilah Widyaningrum Fahrullah Fahrullah Fahrullah, Fahrullah Faldi Fanny Pratiwi Fardiansyah Ibrahim Faza Alameka Gubtha Mahendra Putra Hairah, Ummul Hambali, Nidaa Rifdah Rahima Heri Yansah Hidayanty, Nurul Ilma Ika Purnamasari Ika Purnamasari Indah Ayu Maharani Indra Dwi Pangestu Ivan Leonard Tandi Khoiruddin, Ahmad Zulfikar Kosasih, Raditya Arya M. Fathurahman Mangalik, Gerald Marcelino Irawan, Kenny Maulidin Akbari Muhammad Muhammad Adryan Pratama Muhammad Bambang Firdaus Muhammad Ferdiansyah Muhammad Rayda Bazhrullah Muhammad Wisdan Pratama Putra Muhammad Yani Muhyiddin Muhyiddin Mutmainnah, Dalfa Diandra Nanda Arista Rizki Nasywa, Syarifah Natanael Dewanto Dewanto Ni Luh Desvita Pratiwi Nugraha, Pratama Yuly Nurmayanti, Wiwit Pura Palilu, Dryan Putra Pangruruk , Thesya Atarezcha Pangruruk Putriani Putriani Ramadhini, Laila Thalia Riawan, Tommy Andi Richki Hardi Rika Ismayanti Riyayatsyah Riyayatsyah Riyayatsyah Rizal Putra Aditya Salsabila, Adellia Shalihatunnisa, Shalihatunnisa Sifriyani, Sifriyani Sigit Pangestu SITI MAHMUDAH Sri Wahyuningsih Sry Tualeka Sulfikar Rakita Dewa Surya Prangga Suyitno Suyitno Tamba, Felicia Joy Rotua Tandi Kala, Ezra Alfrianto Tejawati, Andi Thami Rusdi Agus Tina Tri Wulansari Tri Wulansari, Tina Wahyu Yanuartha Wiji Prima Fitriyanto Wiwit Pura Nurmayanti Wulansari, Tina Tri Yumami, Eva Yuniarti, Desi ZIDAN, Muhamad Nur Zidan