Jurnal Fourier
Not a member yet
146 research outputs found
Sort by
Classification of Wood Types Based on Wood Fiber Texture Using GLCM - ANN
No full textIn Indonesia, various types of wood grow and develop with various characteristics and benefits. Each type of wood has differences in texture and fiber, to classify it must have sufficient knowledge about the texture and fiber of wood. A wood species identification system is needed to help the classification process. The purpose of this research is to classify Teak Wood, Sengon Wood, Mahogany Wood, and Gmelina Wood which are often sold in Indonesia. The classification method used in this research is Artificial Neural Network with Gray Level Co- occurrence Matrix (GLCM) extraction. Pre-processing stages include Histogram Equalization, filtering, converting images into grayscale form, and data augmentation. Feature extraction of pre-processing results using GLCM is taken, namely contrast, correlation, energy, homogeneity, and entropy. From the research results, classification using Artificial Neural Network was obtained with 46% accuracy, 43% precision, 42.5% recall, and 42% F1-Score with a GLCM inclination angle of 90°. So, this method can be used to classify the types of wood, but it is less accurate because there are still deficiencies in the model
Modular Version of The Total Vertex Irregularity Strength for The Generalized Petersen Graph
No full textLet be a graph. A labeling graph is a maps function of the set of vertices and/or edges of , to the set of positive integers. A total modular labeling is said to be a -modular total irregular labeling of the vertices of , if for every two distinct vertices and in , the modular weights are different, and belong to the set of integers . The minimum such that the graph has a - modular total irregular labeling is called the modular total vertex irregularity strength and denoted by . In this paper, we study about the modular total vertex irregularity strength for the generalized Petersen graph . The result show that the exact value is
Performa Naïve Bayes, SVM, dan IndoBERT pada Analisis Sentimen Twitter IndiHome dengan Strategi Penanganan Data Tidak Seimbang
No full textPenelitian ini bertujuan untuk membandingkan performa tiga pendekatan analisis sentimen, yaitu Naïve Bayes, Support Vector Machine (SVM), dan Indonesian Bidirectional Encoder Representations from Transformers (IndoBERT), pada layanan IndiHome menggunakan data Twitter. Keterbatasan model tradisional melatarbelakangi penelitian ini dalam mengenali opini positif dan tantangan ketidakseimbangan data yang sering muncul dalam analisis berbasis media sosial. Data penelitian berupa 7393 tweet (Januari 2019–Agustus 2024) yang dilabeli secara manual menjadi sentimen positif dan negatif. Model dievaluasi menggunakan stratified 10-fold cross validation dan data uji, dengan penerapan teknik penanganan ketidakseimbangan berupa Synthetic Minority Oversampling Technique (SMOTE) dan pembobotan kelas (class weighting). Hasil menunjukkan IndoBERT unggul dengan akurasi 0,96 dan F1-score makro 0,95 tanpa penanganan khusus, sedangkan SVM mencapai akurasi 0,95 dengan pembobotan kelas, dan Naïve Bayes meningkat dari akurasi 0,89 menjadi 0,92 setelah SMOTE. Analisis tren sentimen menunjukkan opini negatif mendominasi, terutama terkait kecepatan dan kestabilan layanan. Temuan ini menegaskan bahwa IndoBERT lebih efektif dalam memahami konteks bahasa Indonesia, sementara teknik penanganan data tetap relevan untuk meningkatkan performa model tradisional. Hasil penelitian ini penting karena memberikan dasar empiris dalam pemilihan model analisis sentimen yang lebih akurat, adaptif terhadap bahasa Indonesia, dan bermanfaat dalam meningkatkan kualitas layanan.
This study aims to compare the performance of three sentiment analysis approaches, namely Naïve Bayes, Support Vector Machine (SVM), and Indonesian Bidirectional Encoder Representations from Transformers (IndoBERT), on IndiHome services using Twitter data. The limitations of traditional models underlie this study in recognizing positive opinions and the challenge of data imbalance that often arises in social media based analysis. The research data consist of 7,393 tweets (January 2019–August 2024) manually labeled into positive and negative sentiments. Models were evaluated using stratified 10-fold cross validation and test data, with the application of imbalance handling techniques such as Synthetic Minority Oversampling Technique (SMOTE) and class weighting. Results show IndoBERT excels with 0.96 accuracy and 0.95 macro F1-score without special handling, while SVM reaches 0.95 accuracy with class weighting, and Naïve Bayes improves from 0.89 to 0.92 accuracy after SMOTE. Sentiment trend analysis indicates negative opinions dominate, mainly regarding speed and service stability. These findings confirm IndoBERT is more effective in understanding Indonesian context, while data handling remains relevant for improving traditional models. This study’s results are important because they offer an empirical foundation for choosing sentiment analysis models that are more accurate, adaptive to Indonesian language, and useful for improving service quality.
Peningkatan Kemampuan Kolaborasi dan Komunikasi Matematis Peserta Didik Kelas X SMA Melalui Penerapan Model Cooperative Learning Tipe TGT Terintegrasi CASEL
No full textAbstrak
Penelitian ini dilatarbelakangi oleh rendahnya kemampuan kolaborasi dan komunikasi matematis peserta didik kelas X-A SMA Muhammadiyah 1 Yogyakarta, yang tercermin dari hasil asesmen diagnostik dan pernyataan peserta didik tentang kesulitan dalam pengerjaan soal matematika. Penelitian ini bertujuan untuk meningkatkan kemampuan kolaborasi dan komunikasi matematis melalui penerapan model pembelajaran kooperatif tipe Teams Games Tournament (TGT) yang terintegrasi dengan pendekatan CASEL. Metode yang digunakan dalam penelitian ini adalah Penelitian Tindakan Kelas (PTK) dengan instrumen lembar observasi untuk mengukur kemampuan kolaborasi dan tes untuk menilai komunikasi matematis. Indikator kolaborasi meliputi produktivitas, partisipasi aktif, penghargaan terhadap pendapat kelompok, fleksibilitas, dan tanggung jawab, sementara indikator komunikasi matematis meliputi pengungkapan situasi dalam bahasa matematika, penyajian penyelesaian secara terstruktur, dan evaluasi ide matematis. Hasil penelitian menunjukkan peningkatan signifikan pada kemampuan kolaborasi dan komunikasi matematis peserta didik setelah penerapan model TGT. Rata-rata nilai tes komunikasi matematis meningkat dari 64% pada siklus I menjadi 90% pada siklus II, sedangkan kemampuan kolaborasi meningkat dari 62% menjadi 73%. Peserta didik menunjukkan keterlibatan yang lebih aktif dalam diskusi dan saling mendukung selama pembelajaran, yang berkontribusi pada peningkatan kemampuan penyelesaian soal matematika. Hasil ini menunjukkan bahwa penerapan model TGT efektif dalam meningkatkan kemampuan kolaborasi dan komunikasi matematis peserta didik.
Kata Kunci: CASEL, Kolaborasi, Komunikasi, Matematis, TGT
Abstract
This research is motivated by the low ability of mathematical collaboration and communication of class X-A students of SMA Muhammadiyah 1 Yogyakarta, which is reflected in the results of diagnostic assessments and student statements about difficulties in working on mathematics problems. This study aims to improve mathematical collaboration and communication skills through the application of the Teams Games Tournament (TGT) type cooperative learning model integrated with the CASEL approach. The method used in this study is Classroom Action Research (CAR) with observation sheet instruments to measure collaboration skills and tests to assess mathematical communication. Collaboration indicators include productivity, active participation, respect for group opinions, flexibility, and responsibility, while mathematical communication indicators include expressing situations in mathematical language, presenting solutions in a structured manner, and evaluating mathematical ideas. The results showed a significant increase in students' mathematical collaboration and communication skills after the application of the TGT model. The average mathematical communication test score increased from 64% in cycle I to 90% in cycle II, while collaboration skills increased from 62% to 73%. Students showed more active involvement in discussions and supported each other during learning, which contributed to improving their mathematical problem-solving abilities. These results indicate that the implementation of the TGT model is effective in improving students' mathematical collaboration and communication abilities.
Keywords: CASEL, Collaboration, Communication, Mathematical, TG
ANALISIS HIERARCHICAL CLUSTERING (SINGLE LINKAGE) DAN K-MEDOIDS PADA DATA PENGHASILAN DAN DEMOGRAFI AREA KOMUNITAS CHICAGO
No full textPenelitian ini menganalisis metode Hierarchical Clustering Single Linkage dan K-Medoids dalam mengelompokkan data pendapatan dan demografi di Chicago. Dengan menggunakan data sekunder dari situs Kaggle, penelitian ini mengelompokkan 77 komunitas area berdasarkan kesamaan karakteristik sosial dan ekonomi. Hasil analisis dengan metode Hierarchical Clustering Single Linkage menunjukkan bahwa terdapat satu komunitas area yang terpisah dalam klaster kedua, sementara sisanya tergabung dalam satu klaster utama. Sebaliknya, metode K-Medoids menghasilkan dua klaster yang lebih seimbang dalam distribusi datanya. Berdasarkan visualisasi clustering, metode K-Medoids dianggap lebih baik karena mampu membagi data secara lebih seimbang. Namun, jika ditinjau dari nilai Silhouette Score dan Dunn Index, metode Hierarchical Clustering Single Linkage lebih unggul karena memiliki nilai yang lebih tinggi, menunjukkan fragmentasi klaster yang lebih jelas. Dengan demikian, pemilihan metode terbaik bergantung pada tujuan analisis, di mana K-Medoids lebih sesuai untuk interpretasi distribusi data yang lebih merata, sedangkan Hierarchical Clustering Single Linkage lebih optimal dalam kriteria klaster yang jelas.
This study analyzes the Hierarchical Clustering Single Linkage and K-Medoids methods in clustering income and demographic data of communities in Chicago. Using secondary data from the Kaggle website, this study clusters 77 community areas based on similarities in social and economic characteristics. The analysis using the Hierarchical Clustering Single Linkage method reveals that one community area is isolated in the second cluster, while the rest are grouped into a single main cluster. In contrast, the K-Medoids method produces two clusters with a more balanced distribution. Based on clustering visualization, the K-Medoids method is considered superior as it provides a more evenly distributed classification. However, when evaluated using the Silhouette Score and Dunn Index, the Hierarchical Clustering Single Linkage method outperforms K-Medoids due to its higher values, indicating clearer cluster separation. Thus, the choice of the best method depends on the analytical objective, where K-Medoids is more suitable for interpreting a more balanced data distribution, while Hierarchical Clustering Single Linkage is optimal for achieving distinct cluster separation
Analysis of Inflation Rates During and After the COVID-19 Pandemic Using the K-Means Clustering Method and Kruskal-Wallis Test
No full textInflation occurs when excessive demand results in an overall increase in the prices of goods and services. During the COVID-19 pandemic, the inflation rate in Indonesia leveled off due to the weakening economy. However, in 2022, there was a spike in post-COVID-19 inflation due to increased public demand as pandemic conditions improved. Stable inflation is a requirement for sustainable economic growth and improving people's welfare. In handling inflation problems in various regions, variables and unique circumstances in each region are very important. This research aims to determine whether significant differences exist in the clustering of inflation rates in Indonesia during and after the COVID-19 pandemic. The research results using the Kruskal-Wallis test and the K-Means method obtained that the clustering of inflation rates with k=2 provides good results, as indicated by the Silhouette Coefficient value of 0.66. In addition, there is a significant difference between the current (2020-2021) and post (2022-2023) years of COVID-19 as evidenced by the Kruskal-Wallis test with a p-value < 0.05
Penerapan Model Regresi Data Panel Dinamis Menggunakan Generalized Method of Moment System Terhadap Faktor-Faktor Yang Mempengaruhi Pertumbuhan Ekonomi
No full textRegresi data panel dinamis merupakan salah satu pemodelan matematika yang baik untuk konsep kedinamisan, dimana suatu variabel tidak hanya dipengaruhi oleh variabel pada periode yang sama, melainkan juga pada variabel periode sebelumnya. Salah satu metode estimasi model regresi data panel dinamis adalah Generalized Method of Moment System. Metode ini memiliki kelebihan yaitu menghasilkan estimasi yang tidak bias, konsisten, dan lebih efisien. Pada penelitian ini mengambil studi kasus pertumbuhan ekonomi di provinsi Jawa Barat dari 2013-2023 dengan variabel independen Pendapatan Domestik Regional Bruto tahun sebelumnya dan Indeks Pembangunan Manusia. Hasil analisis memperlihatkan bahwa kedua variabel berpengaruh signifikan terhadap pertumbuhan ekonomi Jawa Barat dengan elastisitas efek jangka pendek variabel Pendapatan Domestik Regional Bruto tahun sebelumnya sebesar 0,2610 dan Indeks Pembangunan Manusia sebesar 0,2870. Sedangkan untuk efek jangka panjang nilai Indeks Pembangunan Manusia diperoleh sebesar 0,3885 artinya setiap kenaikan nilai Indeks Pembangunan Manusia sebesar 1 persen maka pertumbuhan ekonomi naik sebesar 38,85% dengan asumsi variabel lain bernilai konstan
Model Matematika Penjadwalan Obat Kemoterapi Kanker secara Optimal Menggunakan Non-dominated Sorting Genetic Algorithm-II (NSGA-II)
No full textIn this study, a mathematical model for cancer chemotherapy drug scheduling was developed, which is the problem of scheduling drugs given to patients. The mathematical model developed has an objective function of reducing cancer cells while reducing toxicity in the patient's body, with constraints in the form of limits for the number of healthy cells, cancer cells, drug concentration, and patient toxicity. The influential and interrelated variables are arranged in a system of differential equations consisting of the number of healthy cells, number of cancer cells, drug dose, drug concentration, patient toxicity and drug effect, which describes the chemotherapy of non-specific cancer cell cycles. Optimal solution was obtain numerically using Runge-Kutta Method and Non-dominated Sorting Genetic Algorithm-II (NSGA-II). The results showed that this algorithm was able to produce a solution with an optimal dosing schedule every 8 days for 106 days with 14 drug doses. Doses ranged from 20.00 to 29.55 mg/m² with an average of 24.28 mg/m² and a standard deviation of 3.64 mg/m² so as to minimize the number of cancer cells and damage to healthy cells
Generalized Gaussian Fibonacci Numbers and its Determinantal Identities
No full textIn this paper, we present the determinantal identities of generalized Gaussian Fibonacci numbers. The generalized Gaussian Fibonacci sequence is defined by the recurrence relation. This was introduced by S. Pethe and A. F. Horadam. Also, we present its determinantal identities with classical numbers like gaussian Fibonacci, Lucas, Pell, Pell-Lucas, Jacobsthal, jacobsthal-Lucas, Bronze, Nickel and Mersenne numbers
Sturuktur Graf Fuzzy dan Aplikasinya pada Pengambilan Keputusan dalam Identifikasi Layanan Perjalanan
No full textStruktur graf fuzzy adalah penggabungan dari struktur graf dan graf fuzzy. Penelitian ini membahas beberapa pengertian dan sifat dari struktur graf fuzzy diantaranya struktur graf fuzzy komplit dan kuat, struktur graf fuzzy terhubung, serta struktur graf fuzzy reguler. Lebih lanjut, dibentuk semi strong min-product dari dua struktur graf fuzzy dan beberapa teoremanya dari semi strong min-product yang dihasilkan. Selanjutnya disajikan aplikasi dari struktur graf fuzzy dalam pengambilan keputusan, yaitu pengambilan keputusan dalam identifikasi layanan perjalanan, yang didasarkan pada tarif harga dari masing-masing agen. Dengan menerapkan algoritma yang telah disusun disusun dapat ditentukan layanan perjalanan dari satu kota ke kota lain, berdasarkan harga tiket terendah.
[
A fuzzy graph structure is an extension of graph structure and fuzzy graph. This research discusses several definitions and properties of the fuzzy graph structure including complete and strong fuzzy graph structure, connected fuzzy graph structure, and regular fuzzy graph structure. Furthermore, the semi strong min-product of two fuzzy graph structures can be formed, then some theorems are discussed for semi strong min-product. Furthermore, the application of the fuzzy graph structure in decision making is presented, specially decision making for the identification of travel services, which is based on the price rates of each agent. Through the algorithm, it is possible to determine the travel service from one city to another, based on the lowest ticket price.