Article Per Year (5 Year)
p-Index From 2021 - 2026
7.016
P-Index
This Author published in this journals
All Journal Jurnal Ilmiah Ekonomi dan Bisnis AL ISHLAH Jurnal Pendidikan Jurnal Obsesi: Jurnal Pendidikan Anak Usia Dini IT JOURNAL RESEARCH AND DEVELOPMENT INOVTEK Polbeng - Seri Informatika Dinamisia: Jurnal Pengabdian Kepada Masyarakat MATRIK : Jurnal Manajemen, Teknik Informatika, dan Rekayasa Komputer JURNAL TEKNOLOGI DAN OPEN SOURCE Digital Zone: Jurnal Teknologi Informasi dan Komunikasi JURTEKSI Jurdimas (Jurnal Pengabdian Kepada Masyarakat) Royal JOURNAL OF SCIENCE AND SOCIAL RESEARCH Zonasi: Jurnal Sistem Informasi Jurnal Pengabdian Masyarakat Multidisiplin Jutsi: Jurnal Teknologi dan Sistem Informasi J-Com (Journal of Computer) Jurnal Ekonomika Dan Bisnis J-COSCIS : Journal of Computer Science Community Service CONSEN: Indonesian Journal of Community Services and Engagement Jurnal Pemberdayaan Sosial dan Teknologi Masyarakat Indonesian Research Journal on Education JURNAL KOMUNITAS SAINS MANAJEMEN SATIN - Sains dan Teknologi Informasi INOVTEK Polbeng - Seri Informatika SAICGC
Nurliana Nasution, Nurliana
Universitas Lancang Kuning
Religion Aerospace Engineering Arts Humanities Astronomy Automotive Engineering Biochemistry, Genetics & Molecular Biology Chemistry Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Earth & Planetary Sciences Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Environmental Science Immunology & microbiology Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Library & Information Science Materials Science & Nanotechnology Mathematics Medicine & Pharmacology Nursing Physics Public Health Social Sciences Other

Published : 63 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 63 Documents
Search

 3   4   5   6   7 
The Mitigating Overfitting in Sentiment Analysis Insights from CNN-LSTM Hybrid Models Susandri, Susandri; Zamsuri, Ahmad; Nasution, Nurliana; Efendi, Yoyon; Alwan, Hiba Basim
MATRIK : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer Vol 24 No 2 (2025)
Publisher : LPPM Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/matrik.v24i2.4742

Abstract

This study aims to improve sentiment analysis accuracy and address overfitting challenges in deep learning models by developing a hybrid model based on Convolutional Neural Networks and Long Short-Term Memory Networks. The research methodology involved multiple stages, starting with preprocessing a dataset of 5,456 rows. This process included removing duplicate data, empty entries, and neutral sentiments, resulting in 2,685 usable rows. To overcome data quantity limitations, data augmentation expanded the training dataset from 2,148 to 10,740 samples. Data transformation was carried out using tokenization, padding, and embedding techniques, leveraging Word2Vec and GloVe to produce numerical representations of textual data. The hybrid model demonstrated strong performance, achieving a training accuracy of 99.51%, validation accuracy of 99.25%, and testing accuracy of 87.34%, with a loss value of 0.56. Evaluation metrics showed precision, recall, and F1-Score values of 86%, 87%, and 86%, respectively. The hybrid model outperformed individual models, including Convolutional Neural Networks (70% accuracy) and Long Short-Term Memory Networks (81% accuracy). It also surpassed other hybrid models, such as the multiscale Convolutional Neural Network-Long Short-Term Memory Network, which achieved a maximum accuracy of 89.25%. The implications of this study demonstrate that the hybrid model based on Convolutional Neural Networks and Long Short-Term Memory Networks effectively improves sentiment analysis accuracy while reducing the risk of overfitting, particularly in small or imbalanced datasets. Future research is recommended to enhance data quality, adopt more advanced embedding techniques, and optimize model configurations to achieve better performance.
Application of Sales Forecasting Using The Least Square Method in Web-Based Information Systems Nurliana Nasution; Dadang Rukmana Sitompul; Walhidayat Walhidayat
JURNAL TEKNOLOGI DAN OPEN SOURCE Vol. 6 No. 1 (2023): Jurnal Teknologi dan Open Source, June 2023
Publisher : Universitas Islam Kuantan Singingi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36378/jtos.v6i1.2580

Abstract

Technology has become an important role in life, causing the role of computers to be indispensable in various aspects. The presence of technology today is not only in the field of technology but computational methods are also developing. The use of the internet in the aspect of E-commerce (electronic commerce) also plays an important role in the business process cycle. Sale is a major aspect of supporting survival in an industry. Because the high level of sales in an industry/service can compensate let alone provide benefits for the industry. The LEAST Square method is used as an analytical tool for forecasting / predicting sales at the ABDS Store Pekanbaru store. The level of accuracy of the calculation will have an impact on the availability of stock in the store. This method is often used in finding the best parameters of a mathematical model that describes observational data. By using the least squares method, it is expected that the resulting mathematical model can provide a better description of the observation data.
Synthetic Minority Oversampling Technique for Efforts to Improve Imbalanced Data in Classification of Lettuce Plant Diseases Nurliana Nasution; Feldiansyah Feldiansyah; Ahmad Zamsuri; Mhd Arief Hasan
JURNAL TEKNOLOGI DAN OPEN SOURCE Vol. 6 No. 1 (2023): Jurnal Teknologi dan Open Source, June 2023
Publisher : Universitas Islam Kuantan Singingi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36378/jtos.v6i1.2883

Abstract

In this study we classified lettuce plant diseases. These plant diseases are available in the form of images that have been converted in .csv format to be classified. These plant diseases are available in the form of images that have been converted in .csv format to be classified. Image These plant diseases have been divided into several classes or categories. Then we determine the features of each row and column of the dataset. Each line in the CSV file represents one image, and each column represents one feature Each line in the CSV file represents one image, and each column represents one feature. Then a label is made for each line in the CSV file, namely the class or category where the images are grouped. Thus, so that we get datasets that are ready to be processed with machine learning. However, in processing the dataset, we get imbalanced data. So we added the Synthetic Minority Over-sampling Technique (SMOTE) method to overcome the imbalance that occurs. So that the data can be classified using several algorithms to find the best accuracy.
MEMBANGUN KETERAMPILAN DIGITAL: PELATIHAN PENGGUNAAN SCRATCH DI SMK NEGERI 8 PEKANBARU Nurliana Nasution; Feldiansyah Bakri Nasution; Mhd Arief Hasan; Muhammad Al Fajar
Jurnal Pemberdayaan Sosial dan Teknologi Masyarakat Vol 4, No 1 (2024): April 2024
Publisher : Smart Education

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54314/jpstm.v4i1.1932

Abstract

Abstract: This community service aims to enhance the programming skills of students at SMK Negeri 8 Pekanbaru through Scratch training. The problems addressed include limited access to and knowledge of programming among students, as well as low participation rates in technology learning. With a practical and interactive approach, the training involved 7 students and one accompanying teacher. The methods used included introducing basic programming concepts, case studies, and practical projects. Evaluation results showed a significant improvement in understanding basic programming concepts, ability to create simple projects, and interest in programming. The level of student participation in the training sessions reached 100%, indicating high enthusiasm and engagement. This activity proves to be an effective step in preparing students to face the challenges in an increasingly digitally connected workforce. Keywords: pelatihan; pemrograman; scratch; siswa; SMK.  Abstrak: Pengabdian ini bertujuan untuk meningkatkan keterampilan pemrograman siswa SMK Negeri 8 Pekanbaru melalui pelatihan penggunaan Scratch. Masalah yang dihadapi adalah keterbatasan akses dan pengetahuan siswa terkait pemrograman serta rendahnya tingkat partisipasi dalam pembelajaran teknologi. Dengan pendekatan praktis dan interaktif, pelatihan dilaksanakan dengan melibatkan 7 siswa dan satu guru pendamping. Metode yang digunakan mencakup pengenalan konsep dasar pemrograman, studi kasus, dan proyek praktikum. Hasil evaluasi menunjukkan peningkatan signifikan dalam pemahaman konsep dasar pemrograman, kemampuan membuat proyek sederhana, dan minat terhadap pemrograman. Tingkat partisipasi siswa dalam sesi pelatihan mencapai 100%, menandakan antusiasme dan keterlibatan yang tinggi. Kegiatan ini membuktikan dirinya sebagai langkah efektif dalam mempersiapkan siswa untuk menghadapi tantangan di dunia kerja yang semakin terhubung secara digital. Kata kunci: training; programming; scratch; students; vocational school.
Dampak Gaya Hidup Terhadap Kepuasan Konsumen Dan Niat Membeli Kembali Fadhlillah, Il; Handayani, Ririn; Nasution, Nurliana
Jurnal Ekonomika Dan Bisnis (JEBS) Vol. 4 No. 6 (2024): November - Desember
Publisher : CV. ITTC INDONESIA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47233/jebs.v4i6.2205

Abstract

This study uses a quantitative method with a descriptive and explanatory survey approach. The study was conducted at Arifin Ahmad Pekanbaru Hospital, with the aim of testing the role of consumer satisfaction in mediating the influence of lifestyle on repurchase intentions. The population of this study were all directors, general managers, medical support managers, PPI (infection control center), purchasing, pharmacy, and users (doctors, nurses and midwives) totaling 120 people. Because the population members numbered 120 people, this study used a saturated sample method, meaning that all populations were sampled. All respondents will be used to obtain primary data related to the variables,. All respondents will be used to obtain primary data related to the variables, which will be collected through a questionnaire with a Likert scale of 1-5 points. All data obtained were analyzed using Structural Equation Modeling (SEM) with the Smart PLS 3.0 analysis tool. The results showed that lifestyle had a significant positive effect on repurchase intentions, lifestyle had a significant positive effect on consumer satisfaction, consumer satisfaction had a significant positive effect on repurchase intentions, and consumer satisfaction mediated the influence of lifestyle on repurchase intentions
PERANCANGAN DAN IMPLEMENTASI SISTEM PEMBUATAN DAN PEMINDAIAN QR CODE UNTUK PENDATAAN TANAMAN DIPTEROCARPACEAE Prastyaningsih, Sri Rahayu; Siswanto, Didik; Nasution, Nurliana; Alfanandi, Ridho
JOURNAL OF SCIENCE AND SOCIAL RESEARCH Vol 8, No 2 (2025): May 2025
Publisher : Smart Education

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54314/jssr.v8i2.3309

Abstract

Abstract: QR Code-based information systems are increasingly being used to facilitate access to information. In this study, a system consisting of the dipterocarpaceae.my.id website and the Diptero Check application was designed and implemented for plant data collection from the Dipterocarpaceae family. The website allows users to enter plant descriptions and generate downloadable QR Codes. The Diptero Check application is used to scan the QR Code to obtain plant information instantly. The system model was developed using UML (Unified Modeling Language) which includes Use Case Diagrams, Sequence Diagrams, and Activity Diagrams. The system implementation was tested by displaying the website and application interfaces and observing the workflow of creating and scanning QR Codes. The results of the study indicate that this system can improve efficiency in managing Dipterocarpaceae plant information. Keywords: QR Code, Information System, Dipterocarpaceae Abstrak: Sistem informasi berbasis QR Code semakin banyak digunakan untuk mempermudah akses informasi. Penelitian ini merancang dan mengimplementasikan sistem yang terdiri dari Website Dipterocarpaceae.my.id dan aplikasi Diptero Check untuk pendataan tanaman dari famili Dipterocarpaceae. Website memungkinkan pengguna untuk memasukkan deskripsi tanaman dan menghasilkan QR Code yang dapat diunduh. Aplikasi Diptero Check digunakan untuk memindai QR Code tersebut guna memperoleh informasi tanaman secara instan. Model sistem dikembangkan menggunakan UML (Unified Modeling Language) yang mencakup Use Case Diagram, Sequence Diagram, dan Activity Diagram. Implementasi sistem diuji dengan menampilkan tampilan antarmuka website dan aplikasi serta mengamati alur kerja dari pembuatan dan pemindaian QR Code. Hasil penelitian menunjukkan bahwa sistem ini dapat meningkatkan efisiensi dalam pengelolaan informasi tanaman Dipterocarpaceae. Kata kunci: QR Code, Sistem Informasi, Dipterocarpaceae 
Evaluation of the Effect Of Regularization on Neural Networks for Regression Prediction: A Case Study of MLLP, CNN, and FNN Models Susandri; Zamsuri, Ahmad; Nasution, Nurliana; Ramadhani, Maya
INOVTEK Polbeng - Seri Informatika Vol. 10 No. 3 (2025): November
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/m2rcsf96

Abstract

Regularization is an important technique for developing deep learning models to improve generalization and reduce overfitting. This study evaluated the effect of regularization on the performance of neural network models in regression prediction tasks using earthquake data. We compare Multilayer Perceptron (MLP), Convolutional Neural Network (CNN), and Feedforward Neural Network (FNN) architectures with L2 and Dropout regularization. The experimental results show that MLP without regularization achieved the best performance (RMSE: 0.500, MAE: 0.380, R²: 0.625), although prone to overfitting. CNN performed poorly on tabular data, while FNN showed marginal improvement with deeper layers. The novelty of this study lies in a comparative evaluation of regularization strategies across multiple architectures for earthquake regression prediction, highlighting practical implications for early warning systems.
Penerapan Model Lesson Study dalam Meningkatkan Kualitas Pembelajaran Matematika Melalui Permainan Tradisional di Sekolah Dasar Negeri 08 Kampung Rempak Roliah, Roliah; Nasution, Nurliana; Marwa, Marwa
Indonesian Research Journal on Education Vol. 5 No. 5 (2025): Irje 2025
Publisher : Fakultas Keguruan dan Ilmu Pendidikan, Universitas Pahlawan Tuanku Tambusai

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31004/irje.v5i5.3136

Abstract

Penelitian ini bertujuan untuk meningkatkan hasil belajar matematika siswa dan profesionalisme guru melalui penerapan model lesson study berbasis permainan tradisional di SDN 08 Kampung Rempak. Penelitian menggunakan pendekatan mixed method dengan desain Penelitian Tindakan Kelas (PTK) dalam dua siklus. Subjek penelitian terdiri dari siswa kelas IV dan V serta guru kelas tinggi yang tergabung dalam komunitas belajar “SeRempak Delapan”. Data dikumpulkan melalui observasi, wawancara, dokumentasi, dan tes hasil belajar. Hasil penelitian menunjukkan bahwa model lesson study yang dilaksanakan secara kolaboratif mampu meningkatkan efektivitas pembelajaran matematika secara signifikan. Hal ini ditunjukkan melalui peningkatan rata-rata nilai siswa dari siklus I ke siklus II, yang terbukti secara statistik melalui uji Paired Samples t-Test. Permainan tradisional seperti galah panjang, batu berimbang, dan statak digunakan sebagai media pembelajaran yang membantu siswa memahami konsep matematika secara konkret dan menyenangkan. Selain itu, keterlibatan guru dalam merancang, mengimplementasikan, dan merefleksikan pembelajaran menunjukkan peningkatan kompetensi pedagogik dan sikap profesional. Komunitas belajar guru yang terbentuk selama proses lesson study juga berkontribusi terhadap penguatan kolaborasi, komunikasi horizontal, serta pengembangan kurikulum berbasis budaya lokal. Dengan demikian, model lesson study berbasis permainan tradisional tidak hanya meningkatkan hasil belajar siswa tetapi juga menjadi strategi pengembangan profesional guru yang berkelanjutan dan relevan dengan konteks sekolah dasar.
Penerapan Problem Based Learning Berdasarkan Gaya Belajar terhadap Hasil Belajar Peserta Didik pada Pembelajaran IPAS Materi Ciri-Ciri Khusus Hewan di SD Negeri 03 Kampung Rempak Safrini, Safrini; Herlinawati, Herlinawati; Nasution, Nurliana
Indonesian Research Journal on Education Vol. 5 No. 6 (2025): Irje 2025
Publisher : Fakultas Keguruan dan Ilmu Pendidikan, Universitas Pahlawan Tuanku Tambusai

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31004/irje.v5i6.3152

Abstract

Penelitian ini bertujuan untuk mengetahui pengaruh penerapan Problem Based Learning (PBL) berdasarkan gaya belajar terhadap hasil belajar peserta didik pada pembelajaran IPAS materi ciri-ciri khusus hewan. Penelitian ini menggunakan pendekatan kuantitatif dengan desain quasi eksperimen jenis one-group pretest-posttest. Subjek penelitian adalah peserta didik kelas VI A dan VI B SD Negeri 03 Kampung Rempak, yang diklasifikasikan berdasarkan gaya belajar visual, auditori, dan kinestetik. Data dikumpulkan melalui angket gaya belajar, pretest, dan posttest. Analisis data dilakukan menggunakan uji normalitas, homogenitas, dan uji ANOVA satu arah. Hasil penelitian menunjukkan bahwa penerapan PBL memberikan peningkatan signifikan pada hasil belajar peserta didik. Selain itu, terdapat perbedaan hasil belajar yang signifikan antara peserta didik dengan gaya belajar berbeda. Peserta didik dengan gaya belajar kinestetik menunjukkan peningkatan hasil belajar tertinggi, diikuti oleh auditori dan visual. Temuan ini menunjukkan bahwa PBL merupakan model pembelajaran yang efektif dalam mengakomodasi perbedaan gaya belajar peserta didik dan mendorong peningkatan hasil belajar secara menyeluruh.
The Mitigating Overfitting in Sentiment Analysis Insights from CNN-LSTM Hybrid Models Susandri, Susandri; Zamsuri, Ahmad; Nasution, Nurliana; Efendi, Yoyon; Alwan, Hiba Basim
MATRIK : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer Vol. 24 No. 2 (2025)
Publisher : Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/matrik.v24i2.4742

Abstract

This study aims to improve sentiment analysis accuracy and address overfitting challenges in deep learning models by developing a hybrid model based on Convolutional Neural Networks and Long Short-Term Memory Networks. The research methodology involved multiple stages, starting with preprocessing a dataset of 5,456 rows. This process included removing duplicate data, empty entries, and neutral sentiments, resulting in 2,685 usable rows. To overcome data quantity limitations, data augmentation expanded the training dataset from 2,148 to 10,740 samples. Data transformation was carried out using tokenization, padding, and embedding techniques, leveraging Word2Vec and GloVe to produce numerical representations of textual data. The hybrid model demonstrated strong performance, achieving a training accuracy of 99.51%, validation accuracy of 99.25%, and testing accuracy of 87.34%, with a loss value of 0.56. Evaluation metrics showed precision, recall, and F1-Score values of 86%, 87%, and 86%, respectively. The hybrid model outperformed individual models, including Convolutional Neural Networks (70% accuracy) and Long Short-Term Memory Networks (81% accuracy). It also surpassed other hybrid models, such as the multiscale Convolutional Neural Network-Long Short-Term Memory Network, which achieved a maximum accuracy of 89.25%. The implications of this study demonstrate that the hybrid model based on Convolutional Neural Networks and Long Short-Term Memory Networks effectively improves sentiment analysis accuracy while reducing the risk of overfitting, particularly in small or imbalanced datasets. Future research is recommended to enhance data quality, adopt more advanced embedding techniques, and optimize model configurations to achieve better performance.
Co-Authors Agung Pratama Ahmad Zamsuri, Ahmad Ahmad, Rafik Alfajar, Muhammad Alfanandi, Ridho Alkindi, Aditia Fikri Alwan, Hiba Basim Anto Ariyanto arizal N, arizal Bayu Febriadi, Bayu Bimby, Novia Putri Dadang Rukmana Sitompul darmayunata, yuvi David Setiawan David Setiawan Deni Iskandar Desnelita, Yenny Erlin Fachreza Akbar Fadhlillah, Il Fajar, Muhammad Al Fajrizal Fajrizal, Fajrizal Feldiansyah Bakri Nasution Feldiansyah Feldiansyah Feldiansyah Feldiansyah Feldiansyah Nasution Feldiansyah, Feldiansyah Fransiskus Zoromi Herlinawati Herlinawati Ilfan Setiawan Jeni Wardi Khairani Djahara, Khairani Laili Suryati Mariza Devega Martahan, Sutan Marwa, Marwa Mhd. Arief Hasan, Mhd. Arief Muhammad Al Fajar MUHAMMAD RIZAL Nasution, Feldiansyah nurhayani lubis Nurul Aien Binti Abd Aziz Putra, Rudi Julian Eka Ramadhani, Maya Ria Saputri Ria Saputri, Ria Ririn Handayani Roki Hardianto Roliah, Roliah Safrini, Safrini Siswanto, Didik Sitompul, Dadang Rukmana Sri Rahayu Prastyaningsih Sri Utami Lestari Sri Wahyuni Susandri, Susandri Sutan Martahan Syofyan Syofyan Tumilah, Tumilah Walhidayat Walhidayat Walhidayat, Walhidayat Yayi Suryo Prabandari Yoyon Efendi Yummastian Yummastian, Yummastian Yuvi Darmayunta Zamzami, Zamzami Zamzuri, Ahmad