Garuda - Garba Rujukan Digital

p-Index From 2021 - 2026

6.189

P-Index

This Author published in this journals

NISKY IMANSYAH YAHYA

Universitas Negeri Gorontalo

Author-ID : 1764220

Astronomy Biochemistry, Genetics & Molecular Biology Chemical Engineering, Chemistry & Bioengineering Chemistry Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Mathematics Mechanical Engineering Physics Social Sciences Transportation Other

Published : 48 Documents Claim Missing Document

Claim Missing Document

Articles

1 2 3 4 5

Pengelompokan Data Stunting di Indonesia Menggunakan Metode X-Means dan Agglomerative Hierarchical Clustering Wahab, Nur Dhea; Nasib, Salmun K.; Nurwan; Wungguli, Djihad; Yahya, Nisky Imansyah
Research in the Mathematical and Natural Sciences Vol. 4 No. 1 (2025): November 2024-April 2025
Publisher : Scimadly Publishing

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55657/rmns.v4i1.201

Stunting is one of the serious problems that threaten the quality of human resources in Indonesia. This study aims to analyze the patterns and characteristics of stunting in Indonesia by applying the X-Means clustering method and Agglomerative Hierarchical Clustering (AHC). The X-Means method is used to determine the optimal number of clusters automatically by utilizing the Bayesian Information Criterion (BIC), while AHC forms a dendrogram to understand the multilevel structure of the clusters formed. Based on the analysis, the X-Means method produces three optimal clusters with the smallest BIC value of 651.9475, where cluster 1 consists of 17 provinces, cluster 2 includes 12 provinces, and cluster 3 includes 5 provinces. The AHC method with the Single Linkage approach also produced three optimal clusters, with cluster 1 covering 32 provinces, cluster 2 consisting of 1 province (West Nusa Tenggara), and cluster 3 covering 1 province (East Nusa Tenggara), as well as the highest Silhouette Index value of 0.28. The results show that both methods provide a comprehensive picture of stunting patterns in Indonesia, which can be used as a basis for designing more targeted intervention programs according to the characteristics of each cluster. This data-driven strategy is expected to increase policy effectiveness in reducing stunting in Indonesia.

Bilangan Terhubung Pelangi pada Graf Tengah (M(G)) dari Graf Ulat (C_(m,2)) Kiayi, Fuji Fauzia; Ismail, Sumarno; Yahya, Nisky Imansyah; Yahya, Lailany; Nasib, Salmun K.
Research in the Mathematical and Natural Sciences Vol. 4 No. 1 (2025): November 2024-April 2025
Publisher : Scimadly Publishing

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55657/rmns.v4i1.204

Edge coloring of a graph is considered rainbow connected if the graph is connected and a rainbow path exists for every pair of points. The rainbow connection number of a graph, denoted as , represents the smallest number of colors required to make the graph is rainbow connected. This study examines the rainbow connection number of the middle graph of a caterpillar graph. The middle graph is a modified result of a graph , denoted as . It is described as a graph constructed from the intersection of a set of points and edges. The set of points in the middle graph consists of the combination of points and edges of the graph . Two points are considered adjacent if only they are connected in , or if one point corresponds to a point and the other corresponds to an edge adjacent to it. A caterpillar graph denoted by is a tree that will be a path if all the leaf points are deleted. The results of this research show the rainbow-connected number theorem for the middle graph of the caterpillar graph for .

Pewarnaan Pelangi pada Graf Garis dari Graf Ilalang (S_(3,r)) Rauf, Dewi Nur Angriani; Achmad, Novianita; Yahya, Nisky Imansyah
Griya Journal of Mathematics Education and Application Vol. 5 No. 1 (2025): Maret 2025
Publisher : Pendidikan Matematika FKIP Universitas Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29303/griya.v5i1.529

The rainbow connection number, denoted by rc(G), is the minimum number of colors required to color the edges of a graph G such that the graph is rainbow connected. A graph G is said to be rainbow connected if every pair of vertices in the graph has at least one rainbow path, a path in which each edge has a different color. Rainbow coloring has been extensively studied on various types of graphs and their modifications, including line graphs. The line graph L(G) of a graph is a graph whose vertex set is V(L(G)) = E(G), meaning each vertex in represents an edge of . Two vertices in L(G) are adjacent if and only if their corresponding edges in G share a common vertex. This study examines the rainbow coloring of the line graph of the ilalang graph (Sn,r) for n = 3 and r>= 3. Based on the research findings, the rainbow connection number of the line graph of the ilalang graph is given by the theorem rc(L(S3,r)) = r for r>= 3.

Optimization of LightGBM Model with Bayesian Optimization for Malware Detection Kasim, Afrianto Pratama; Nasib, Salmun K.; Hasan, Isran K.; Wungguli, Djihad; Yahya, Nisky Imansyah
ILKOMNIKA Vol 7 No 1 (2025): Volume 7, Number 1, April 2025
Publisher : Lembaga Penelitian dan Pengabdian Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28926/ilkomnika.v7i1.722

Cyberattacks through malware on Android devices continue to rise, making accurate detection crucial. This research optimizes the LightGBM model using Bayesian Optimization to enhance accuracy and efficiency in detecting Android malware. A feature selection mechanism based on Attention Mechanism is applied to select the most relevant features for classification. The dataset used comes from the Canadian Institute for Cybersecurity (CIC) and consists of 17,804 Android applications, with a balanced distribution between malware and normal applications. The dataset is split into ratios of 80%:20%, 75%:25%, and 70%:30%. Feature selection reduces the number of features from 9503 to 300, 500, and 1000. The LightGBM model is then optimized with Bayesian Optimization to fine-tune parameters such as learning rate, number of iterations, and maximum number of leaves. The model's performance is evaluated using accuracy, precision, and recall metrics. Experimental results show that the model achieves 96,99% accuracy, 97,30% precision, and 96,70% recall with an 80%:20% dataset split and 1000 features. The combination of Attention Mechanism and Bayesian Optimization effectively improves processing efficiency without compromising performance.

ANALISIS SENTIMEN TWITTER TERHADAP NYAMUK WOLBACHIA MENGGUNAKAN METODE LSTM DENGAN PENDEKATAN NLTK Lakoro, Tiara; K. Nasib, Salmun; Imansyah Yahya, Nisky; S. Panigoro, Hasan; Nurmardia Abdussamad, Siti
Trigonometri: Jurnal Matematika dan Ilmu Pengetahuan Alam Vol. 6 No. 2 (2025): Trigonometri: Jurnal Matematika dan Ilmu Pengetahuan Alam
Publisher : Cahaya Ilmu Bangsa Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.3483/trigonometri.v6i2.12266

Dengue Hemorrhagic Fever (DHF) is one of the major health issues in Indonesia. One of the preventive measures is the Wolbachia mosquito program. However, the implementation of this program has sparked various reactions from the public, which can be observed through social media, particularly Twitter. This study aims to analyze public sentiment towards Wolbachia mosquitoes using the Long Short-Term Memory (LSTM) method and the Natural Language Toolkit (NLTK) approach. Data was collected through a crawling process from Twitter using keywords related to "Wolbachia mosquitoes." Preprocessing was then carried out using NLTK, including tokenization, stopword removal, and stemming. The data was manually labeled into positive, negative, and neutral sentiment categories. The LSTM model was used for sentiment classification with the best parameters, including 100 neurons, a learning rate of 0.001, a sigmoid activation function, a batch size of 32, and 7 epochs. The results indicate that the LSTM model used was able to classify sentiment with an accuracy of 95%, precision of 94%, recall of 97%, and an F1-score of 95%. This demonstrates that the LSTM method with the NLTK approach is effective in analyzing public sentiment towards

Bilangan Terhubung Titik Pelangi pada Graf Garis, Graf Tengah, dan Graf Total dari Graf Panci Jusuf, Anryan; Nurwan, Nurwan; Yahya, Nisky Imansyah; Yahya, Lailany; Nasib, Salmun K.; Asriadi, Asriadi
Hexagon: Jurnal Ilmu dan Pendidikan Matematika Vol. 2 No. 2 (2024): October
Publisher : LPPM Universitas Terbuka

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33830/hexagon.v2i2.10000.

Salah satu konsep dalam bidang teori graf yang berkaitan erat dengan pewarnaan titik pelangi adalah bilangan terhubung titik pelangi. Sebuah graf G dikatakan terhubung titik pelangi jika terdapat setidaknya satu jalur yang menghubungkan titik-titik dengan warna yang berbeda. Konsep ini mengacu pada jumlah minimum warna yang dibutuhkan untuk mewarnai sebuah graf G sehingga graf tersebut terhubung dengan titik pelangi dan dilambangkan dengan rvc(G). Topik pewarnaan titik pelangi dapat dieksplorasi dalam berbagai bentuk pengembangan graf dengan memanfaatkan graf garis, graf tengah dan graf total. Graf garis L(G) adalah graf yang titik-titiknya merupakan sisi-sisi dari G, dan jika u, v ≥ E(G) maka uv ≥ E(L(G)) sedemikian sehingga u dan v saling berbagi titik di G. Graf tengah M(G), merupakan sebuah graf dengan himpunan titiknya merupakan gabungan antara kumpulan titik dan kumpulan sisi dari graf G. Sedangkan graf total T(G), yaitu graf yang titiknya didapatkan dari himpunan titim dan himpunan sisi dari graf G, dimana setiap titik V(G)saling terhubung. Pada penelitian ini, saya membahas bilangan terhubung titik pelangi yang terhubung pada graf garis, graf tengah dan graf total dari graf panci (Pnm) dengan m ≥ 6. Berdasarkan hasil yang diperoleh, didapatkan teorema bilangan terhubung titik pelangi pada graf garis dari graf panci rvc(L(Pn_m)), graf tengah dari graf panci rvc(M(Pn_m)), dan graf total dari graf panci rvc(T(Pn_m)).

Bilangan Terhubung Pelangi pada Graf Tengah dari Graf Ilalang Rauf, Dewi Nur Angriani; Achmad, Novianita; Yahya, Nisky Imansyah; Nurwan, Nurwan; Nasib, Salmun K.; Asriadi, Asriadi
Jurnal Riset Mahasiswa Matematika Vol 4, No 4 (2025): Jurnal Riset Mahasiswa Matematika
Publisher : Mathematics Department, Maulana Malik Ibrahim State Islamic University of Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18860/jrmm.v4i4.31475

Bilangan terhubung pelangi yang dinotasikan dengan adalah jumlah warna terkecil yang diperlukan untuk mewarnai sisi-sisi dari sebuah graf sehingga graf tersebut menjadi terhubung pelangi. Bilangan terhubung pelangi dapat dipelajari dalam berbagai bentuk pengembangan graf yang dimodifikasi, termasuk graf tengah. Semua jenis graf, baik yang sederhana maupun yang kompleks, dapat direpresentasikan sebagai graf tengah. Sebuah graf tengah yang dinotasikan dengan dibentuk dari sebuah graf dan didefinisikan sebagai . Dua buah simpul pada bersisian jika dan hanya jika keduanya bersisian dengan sebuah sisi pada , atau salah satu simpul pada bersisian dengan sebuah sisi pada . Penelitian ini membahas tentang pewarnaan pelangi pada graf tengah dari graf ilalang dengan dan Berdasarkan penelitian diperoleh teorema pelangi bilangan terhubung pada graf tengah graf ilalang untuk

Implementasi Metode Bidirectional LSTM Dengan Word Embedding FastText Dalam Analisis Sentimen Ulasan Pengguna Aplikasi Maxim Wewengkang, Hanz Franklyn Bachruddin; Wungguli, Djihad; Yahya, Nisky Imansyah; Hasan, Isran K.; Abdussamad, Siti Nurmardia
Jurnal Riset Mahasiswa Matematika Vol 4, No 5 (2025): Jurnal Riset Mahasiswa Matematika
Publisher : Universitas Islam Negeri Maulana Malik Ibrahim Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18860/jrmm.v4i5.33358

Aplikasi transportasi online kini menjadi bagian penting dalam kehidupan masyarakat Indonesia. Maxim, sebagai salah satu penyedia layanan, perlu memahami persepsi pengguna untuk meningkatkan kualitas layanannya. Penelitian ini menerapkan metode Bidirectional Long Short-Term Memory (BiLSTM) untuk melakukan klasifikasi sentimen terhadap ulasan pengguna aplikasi Maxim di Google Play Store. Untuk memperkuat representasi kata, digunakan word embedding FastText yang mampu menangkap informasi sub-kata secara lebih baik. Data penelitian diperoleh melalui scraping menggunakan package google-play-scraper pada Python. Model BiLSTM yang dilatih dengan konfigurasi hyperparameter optimal berhasil mengklasifikasikan sentimen ulasan secara efektif, dengan hasil accuracy 94%, precision 96%, recall 95%, dan f1-score 95%. Hasil ini menunjukkan bahwa kombinasi BiLSTM dan FastText mampu mendeteksi sentimen positif dan negatif secara akurat dan seimbang, serta relevan untuk mendukung evaluasi kualitas layanan berbasis opini pengguna.

Penerapan Model ARFIMA-LSTM Menggunakan Variasi Estimasi Parameter Pembeda Dalam Meramalkan data IHPBI Harun, Trieke Nurfadilah; Djakaria, Ismail; Yahya, Nisky Imansyah; Nasib, Salmun K; Hasan, Isran K
Jurnal Riset Mahasiswa Matematika Vol 4, No 5 (2025): Jurnal Riset Mahasiswa Matematika
Publisher : Universitas Islam Negeri Maulana Malik Ibrahim Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18860/jrmm.v4i5.33303

Indeks Harga Perdagangan Besar Indonesia (IHPBI) merupakan indikator penting dalam mengukur perkembangan ekonomi, khususnya pada sektor pertanian yang memiliki pengaruh besar terhadap daya beli masyarakat. Fluktuasi harga di sektor ini berdampak langsung pada kesejahteraan konsumen dan produsen, sehingga diperlukan metode peramalan yang akurat. Penelitian ini bertujuan untuk meramalkan IHPBI sektor pertanian menggunakan pendekatan hybrid Autoregressive Fractionally Integrated Moving Average (ARFIMA) dan Long Short-Term Memory (LSTM), serta membandingkan performa metode estimasi parameter pembeda terbaik. Model ARFIMA digunakan untuk menangani komponen stasioner dan pola jangka panjang melalui diferensiasi pecahan, sedangkan LSTM digunakan untuk menangkap pola nonlinier dalam data. Keterbaruan dalam penelitian ini adalah membandingkan parameter pembeda terbaik yaitu Local Whittle dan Rescaled Range Statistics dalam hybrid ARFIMA-LSTM. Hasil dari penelitian yaitu peramalan menunjukkan tren naik IHPBI sektor pertanian selama 12 bulan ke depan. Metode estimasi parameter pembeda terbaik dalam model ARFIMA adalah Rescaled Range Statistics dengan nilai sebesar 0,322. Model hybrid ini menghasilkan nilai MAPE sebesar 0,6337853%, yang menunjukkan tingkat akurasi sangat tinggi.

Perbandingan Seleksi Fitur Forward Selection dan Backward Elimination pada Algoritma Support Vector Machine Suharmin, Wandayana Nur'Amanah; Hasan, Isran K.; Yahya, Nisky Imansyah
The Indonesian Journal of Computer Science Vol. 14 No. 2 (2025): The Indonesian Journal of Computer Science
Publisher : AI Society & STMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33022/ijcs.v14i2.4755

Support Vector Machine (SVM) is an effective and robust classification method, particularly when applied to high-dimensional data. However, high-dimensional data often contain irrelevant features that can lead to suboptimal SVM performance. Therefore, a feature selection process is necessary to optimize classification performance by eliminating irrelevant and redundant features from the original dataset. This research aims to compare the Forward Selection and Backward Elimination feature selection methods within the Support Vector Machine Algorithm for classification using the Poverty Depth Index data in Papua Province. The results indicated that applying the Support Vector Machine with Forward Selection feature selection achieved a classification accuracy of 93%, whereas Backward Elimination feature selection achieved a classification accuracy of 97%. Based on these classification accuracy results, it can be concluded that applying Support Vector Machine with Backward Elimination feature selection results in better performance than Forward Selection.

Co-Authors Afifah Farhanah Akadji Afifah Farhanah Akadji Agusyarif Rezka Nuha Akadji, Afifah Farhanah Amelia T. R. Sidik Armayani Arsal Aruchamy, Pradeepa Asriadi Asriadi Asriadi Asriadi Ayyasy, Muhammad Yahya Bertu Rianto Takaendengan Cindy Aisa Putri Noor Dennynatalis Taha Dewi Rahmawaty Isa Dhandapani, Prasantha Bharathi Djihad Wungguli Fatmawati, Ainun Franky Alfrits Oroh Fuzi Sandra Talibo Ganesan, Gomathi Hamani, Mohamad Taufik Harmain, Ismail Saputra R. Harun, Trieke Nurfadilah Hasan S. Panigoro Husuna, Cabelita Imran, Nurain Indrawati Lihawa Ismail Djakaria Isran K Hasan Jusuf, Anryan K. Nasib, Salmun Kai, Ferawati Karim, Finansiya S. Abd. Karina Anselia Mamonto Kasim, Afrianto Pratama Khairun Nisa Humolungo Kiayi, Fuji Fauzia La Ode Nashar Lailany Yahya Lailany Yahya Lakisa, Narti Lakoro, Tiara Mahagaonkar, Pralahad Meilan Sigar Melisa Huntala Mita Sari Mohamad Rivaldi Moha Mokodompit, Marcela Muhammad Rezky F. Payu Muhammad Rifai Katili Nadiyyah, Ana Narti Lakisa Novianita Achmad Novria Fatmawati Lakutu Nurmardia Abdussamad, Siti Nursiya Bito Nurwan Nurwan Nurwan Nurwan, Nurwan Periyannan, Jayalakshmi Pomahiya, Saiful Pranata, Widya Eka Prasetyo, Deny Ardika Rahim, Delvira Masita Rahmi, Emli Randi Mooduto Rauf, Dewi Nur Angriani Resmawan Resmawan Salmun K. Nasib Salmun K. Nasib Saravanakumar, Anitha Sari, Septi Rahmita Sembiring, Rinawati Siti Nurmardia Abdussamad Sri Lestari Mahmud Suharmin, Wandayana Nur'Amanah Sumarno Ismail Taha, Dennynatalis Tahir, Fauzia D Tahir, Fauzia D. Taufik, Mohamad Alfiransyah Wahab, Nur Dhea Wahdania A.T. Ja’a Wewengkang, Hanz Franklyn Bachruddin Zulkifli Alamtaha

Title

Found 48 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 48 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 48 Documents
Search