Abstract:Abstract: Children's nutritional issues are an important concern for parents to pay attention to growth and development, especially health and well-being. According to the results of the Ministry of Health's Indonesian Nutrition…
utrition Status Survey (SSGI), there are 4 nutritional problems for children in Indonesia, namely stunting, wasting, underweight and everweight. In this research, how to predict signs of symptoms of a decline in a child's nutritional status using a machine learning algorithm, a prediction model was designed using logistic regression in Python IDE to predict whether a child is indicated by a decline in nutrition or not. Dataset from Bengkayang Community Health Center data consisting of 657 pediatric patient data. The dataset is divided into 7 features (independent variables) and 1 predictor (dependent variable). Test results show perfect performance with precision, recall, F1-score, accuracy values of 100%. Then the visualization results on the ROC (Receiver Operating Characteristic) curve to depict the TP (True Positive) value on the Y axis against the FP (false Positive) value on the become overfit. It is recommended that in preparing the training dataset, measure the training data and reduce the features, after carrying out feature selection to increase the accuracy of the model.
Keywords: child nutritional status; growth and development logistic regression; machine learning
Abstract: Masalah Gizi anak menjadi perhatian penting bagi orangtua untuk memperhatikan tumbuh kembang, terutama kesehatan dan kejahteraan. Menurut hasil survei status Gizi Indonesia (SSGI) Kemenkes memperlihatkan 4 permasalahan gizi anak di Indonesia yaitu stunting, wasting, underweight, dan everweight. Dalam penelitian ini, bagaimana memprediksi tanda gejala penurunan status gizi anak menggunakan algoritma machine learning dirancang model prediksi menggunakan logistic regression pada Python IDE dengan memprediksi anak terindikasi penurunan gizi atau tidak. Dataset dari data Puskesmas Bengkayang yang terdiri 657 data pasien anak. Dataset dibagi menjadi 7 feature (variabel independen) dan 1 predictor (variabel dependen). Hasil Pengujian memperlihatkan kinerja yang sempurna dengan nilai presisi, recall, F1-score, akurasi, sebesar 100%. Kemudian hasil Visualisasi pada kurva ROC (Receiver Operating Characteristic) untuk menggambarkan nilai TP (True Positif) di sumbu Y terhadap nilai FP (false Positif) di sumbu X juga menunjukkan nilai yang sangat tinggi dan sudah mendekati angka 1 ini pertanda bahwa model ini menjadi overfit. Sebaiknya dalam persiapan training dataset diukur dengan data training dan mengurangi feature, setelah melakukan feature Selection untuk meningkatkan akurasi model.
Keywords: logistic regression; machine learning; status gizi anak; tumbuh kembang
Abstract:Abstract: that the number of catches obtained by fishermen is more optimal. With secondary data based on the type of cultivation developed by fishing communities, the authors intend to explore this data so that they can…
examine more deeply the most effective types of cultivation using analysis of variance to find out the differences between each type of cultivation and cluster analysis using the complete linkage method. to find out the grouping of marine culture production based on the types developed by fishing communities in Indonesia. The correlation between the observed variables is 0.008, so it can be said that there is no relationship between the observed variables. In addition, the sig. and t-test. sig value is obtained. > α (5% = 0.05). This means that there is a significant average difference in fish production results based on the type of cultivation developed by fishing communities. With the grouping of types of marine cultivation developed by the Wesleyan community using the complete-linkage method, they are divided into 3 groups based on the degree of similarity in the production results obtained. Cluster 1 consists of Floating Nets, and Pools; Cluster 2 consists of other seas, seaweed, cages, and fishing nets; and Cluster 3 consists of Fresh Floating Nets, Minapadi, and Ponds.
Keywords: Complete-Linkage; Fish Production; Mariculture; Multivariate Analysis; T-test;
Abstrak: Berdasarkan penelitian sebelumnya pada analisis variansi untuk menguji perbedaan rata-rata pada masing-masing perlauan peletakan sudut jarring agar jumlah tangkapan yang diperoleh nelayan lebih optimal. Dengan adanya data sekunder berdasarkan jenis budidaya yang dikembangkan masyarakat nelayan, penulis bermasksud untuk melakukan eksplorasi pada data tersebut agar dapat mengkaji lebih dalam terhadap jenis budidaya yang paling efektif dengan analisis variansi untuk mengetahu perbedaan dari masing-masing jenis budidaya serta analisis cluster dengan metode complate linkage untuk mengetahui adanya pengelompokan hasil produksi bududaya laut berdasarkan jenis yang dikembangkan oleh masyarakat nelayan di Indonesia. Korelasi antar variabel yang diamati sebesar 0.008, maka dapat dikatakan bahwa tidak ada hubungan antara variabel yang diamati. Selain itu, hasil uji sig. dan uji t. diperoleh nilai sig. > α (5% = 0.05). Artinya, terdapat perbedaan rata-rata secara signifikan hasil produksi ikan berdasarkan jenis budidaya yang dikembangkan oleh masyarakat nelayan. Dengan adanya pengelompokan jenis budidaya laut yang dikembangkan oleh masyarakat neleyan dengan metode complete-linkage terbagi atas 3 kelompok berdasarkan tingkat kemiripan hasil produksi yang diperoleh. Cluster 1 terdiri dari Jaring Apung, Kolam; Cluster 2 terdiri dari Laut lainnya, Rumput laut, Keramba, Jaring Tancap; dan Cluster 3 terdiri dari Jaring Apung Tawar, Minapadi, Tambak.
Kata kunci: Analisis Multivariate; Budidaya Laut; Complate-Linkage; Produksi Ikan; Uji-t;
Abstract:Abstract: The technique of multiclass classification based on SVMs has been widely used. SVM optimization will be accomplished by examining the extraction features of Principal Component Analysis (PCA), Box-Cox Transformation,…
ation, and Recursive Feature Elimination (RFE). The dataset contains 13,611 rows and 17 variables, generated from the UCI repository's multiclass dry bean data. Barbunya, Bombay, Cal, Dermas, Horoz, Seker, and Sira are just a few of the dry bean kinds available. The dataset was tested using SVM Linear kernel and SVM Radial Basis.According to the results, the combination of scale-center-BoxCox-SVM Radial extraction achieves the maximum accuracy of 93.16 percent and the shortest processing time of 6.10 minutes. 96.00 percent, 100 percent, 96.71 percent, 95.16 percent, 97.60 percent, 97.74 percent, and 91.95 percent, according to bean class.RFE-SVM Radial has a 91.18 percent accuracy and a processing time of 6.55 minutes. BoxCox outperforms conventional techniques in terms of prediction accuracy while requiring less training time.
Keywords: Bean, PCA, BoxCox, SVM, RFE
Abstrak: Klasifikasi Multikelas menggunakan SVM telah banyak digunakan. Pada penelitian ini akan diuji fitur ekstraksi Principal Component Analysis, Box Cox Transformation dan fitur eliminisi Recursive Feature Elimination untuk mendapatkan optimasi SVM. Dataset berasal dari data multikelas kacang kering UCI repository dengan jumlah 13.611 baris dan 17 variabel. Kelas kacang kering yakni : Barbunya, Bombay, Cal, Dermas, Horoz, Seker dan Sira. Dataset diuji menggunakan kernel SVM Linier dan SVM Radial Basis. Didapatkan hasil, bahwa kombinasi fitur ekstraksi : scale-center-BoxCox-SVM Radial memiliki akurasi terbaik yakni 93,16% dan waktu proses 6,10 menit. Klasifikasi berdasarkan kelas kacang berturut-turut 96,00%,100%, 96,71%, 95,16%, 97,60%, 97,74% dan 91,95%. RFE- SVM Radial hanya memberikan akurasi sebesar 91,18 % dengan waktu proses sebesar 6.55 menit. Penggunaan BoxCox dibandingkan dengan lainnya, memberikan hasil prediksi lebih baik dan namun tidak mempercepat waktu pelatihan.
Kata kunci: BoxCox; Kacang; PCA; RFE; SVM
Abstract:Abstract : Corona virus is a very dangerous virus and can kill human life. This virus causes minor illnesses and serious illnesses such as colds or colds, since the emergence of the Corona Virus or Covid 19 paralyzing all…
l human activities carried out outside the home. The problem of this research is in the form of the impact of the corona virus on the economy, especially in the city of Batam so that the residents of Batam can overcome this corona virus outbreak to improve the weakening economy. The main objective of this research is to examine the impact of Covid 19 on the economy of the Batam population so that the Batam population can improve the already weakened economy. This study uses Fuzzy Inference Sistym the Mamdani Method for Decision Making, using Operators or through the process of Fuzification of Input Variables, Inference Machines to process rules and produce Defuzification to get the final value
Keywords: corona prediction fuzzy inference system; mamdani method
Abstrak:Virus Corona merupakan sebuah virus yang sangat berbahaya dan bisa menghilangkan nyawa manusia. Virus ini mengakibatkan penyakit ringan dan penyakit berat seperti common cold atau pilek, Sejak munculnya Virus Corona atau Covid 19 melumpuhkan semua kegiatan aktivitas manusia yang dilakukan diluar rumah. Permasalahan Penelitian ini berupa dampak akibat virus corona terhadap perekonomian khususnya pada Kota Batam sehingga penduduk Batam bisa mengatasi Wabah Virus corona ini untuk meningkatkan perekonomian yang semakin melemah. Tujuan Utama Penelitian ini mengkaji Dampak akibat Covid 19 terhadap perekonomian penduduk batam sehingga penduduk Batam bisa meningkatkan perekonomian yang sudah melemah. Penelitian ini menggunakan Fuzzy Inference Sistem Metode Mamdani untuk Pengambilan sistem Keputusan, menggunakan Operator Or dan melalui proses Fuzifikasi penentuan Variabel Input, Mesin Inferensi untuk melakukan proses aturan dan menghasilkan Defuzifikasi untuk mendapatkan nilai akhir.
Kata Kunci : fuzzy inference sistem; metode mamdani; prediksi corona
Abstract:Abstract: Student objectivity in filling out E-EDOM is very necessary, the results of data analysis become the basis for the leadership in making decisions for learning strategies. Previous research has proven that the E-EDOM…
-EDOM filling done by students is not objective. Efforts should be made so that students can fill it in seriously. This study aims to determine strategies that can be applied so that students can fill out the E-EDOM very objectively. Starting with analyzing and collecting data through a questionnaire. The Delon and Mclean model is used as a basis for creating questions in the questionnaire and processing the questionnaire data. The data collection technique used a simple random sampling method, with a population of 121 students from Amik Riau STMIK who were active in the 2019-2020 school year. Before processing, the data is tested for validity and reliability. After testing the validity and reliability, then testing the hypothesis to determine the relationship between variables in the Delon and Mc Lean success model. The results showed that each variable showed the effect of a positive relationship that was fully accepted with a value of 0.000. This means that all the variables used in this study are related to one another. Even so, it is necessary to implement several strategies that must be done in an effort to fill out E-EDOM which is very objective by students.
Keywords: e-edom, delon and mclean models, objectivity, students.
Abstrak: Objektifitas mahasiswa dalam mengisi E-EDOM sangat diperlukan, karena hasilnya akan dijadikan dasar oleh pimpinan dalam mengambil keputusan untuk masalah pembelajaran. Berdasarkan penelitian sebelumnya pengisian E-EDOM yang dilakukan mahasiswa masih banyak yang belum mengisinya dengan sangat objektif. Perlu dilakukan upaya agar mahasiswa dapat mengisinya dengan sunggun-sungguh. Penelitian ini bertujuan untuk menentukan strategi yang dapat diterapkan supaya mahasiswa dapat mengisi E-EDOM dengan sangat objektif. Diawali dengan melakukan analisa dan pengumpulan data melalui kuisioner. Model Delon and Mclean digunakan sebagai dasar untuk membuat pertanyaan dalam kuisioner dan melakukan pengolahan data kuesioner tersebut. Teknik pengumpulan data menggunakan metoda sampling simple random, dengan populasi mahasiswa STMIK Amik Riau yang aktif pada tahun ajaran 2019-2020 sejumlah 121 orang mahasiswa. Sebelum dilakukan pengolahan, terlebih dahulu data-data tersebut dilakukan uji validitas dan reability. Setelah dilakukan uji validitas dan reability, selanjutnya melakukan uji hipotesis untuk mengetahui hubungan antar variable yang ada pada model Delon and Mc Lean success. Hasil penelitian ini menunjukkan bahwa setiap variable menunjukkan pengaruh hubungan positif dapat diterima seluruhnya dengan nilai 0.000. Artinya semua variable yang digunakan pada penelitian ini memiliki keterkaitan antara satu dengan lainnya. Walaupun demikian perlu diterapkan beberapa strategi yang harus dilakukan dalam upaya pengisian E-EDOM yang sangat objektif oleh mahasiswa.
Kata kunci: e-edom, delon and mclean model, mahasiswa, objektifitas.
Abstract:Abstract: One of the ways to improve the quality of high school students is to form a favorite class in which the class will be a flagship class compared to other classes. Students will be selected based on 3 variables,…
that is the attendance index, semester average score and also the ethics of the students themselves. Data mining is the mining or discovery of new information by searching for a particular pattern or rule of large amounts of data that is expected to overcome the condition, utilizing data obtained from SMA for grouping students using clustering method using single linkage technique. By using clustering method is expected to make it easier for grouping students - students who go to class XI. So the results of this study will also be used by in determining the students-students who will enter the majors class. Keywords: Data Mining, Clustering, Single Lingkage, Selection of Departments.
Abstrak: Salah satu cara untuk meningkatkan kualitas siswa sekolah menengah adalah dengan membentuk kelas favorit di mana kelas akan menjadi kelas unggulan dibandingkan dengan kelas lain. Siswa akan dipilih berdasarkan 3 variabel, yaitu indeks kehadiran, nilai rata-rata semester dan juga etika siswa itu sendiri. Data mining adalah penambangan atau penemuan informasi baru dengan mencari pola tertentu atau aturan sejumlah besar data yang diharapkan untuk mengatasi kondisi tersebut, memanfaatkan data yang diperoleh dari SMA untuk mengelompokkan siswa menggunakan metode pengelompokan menggunakan teknik hubungan tunggal. Dengan menggunakan metode clustering diharapkan akan mempermudah pengelompokan siswa - siswa yang masuk ke kelas XI. Jadi hasil penelitian ini juga akan digunakan dalam menentukan siswa - siswa yang akan masuk kelas jurusan. Kata kunci: Data Mining, clustering, single lingkage, pemilihan departemen
Abstract:Tourism is one of the most important factors for the revenue of an area. To attract the interest of tourists takes some supporting factors, one of which is the hotel or the guesthouse. In the process of prediction of tourists…
rists visit, required data the number of tourists staying in order to predict for the next time. The prediction method used in this system is a method of Backpropagation Neural Network based on time series data forecasting component variansi random or random process beginning with autocorrelation for determination of input variables. Method of Backpropagation itself is known quite well used in the forecasting of time series data. The result of the method of Backpropagation is a number of predictions that tourists visit can be a reference for related officials in taking decisions for the period ahead.
Abstract:This study examines the development of fiscal decentralization and its relationship to regional financial independence in Indonesia through a systematic literature review. The objective is to synthesize empirical and conceptual…
ceptual findings published between 2017 and 2026 concerning the determinants, measurement, and consequences of regional financial independence, particularly the role of local own-source revenue (PAD), intergovernmental transfers, and capital expenditure. Using a systematic search of Scopus, Google Scholar, and Garuda databases, 30 relevant articles were screened, selected, and analyzed following defined inclusion and exclusion criteria. The review finds that fiscal decentralization consistently strengthens local revenue mobilization and administrative accountability when accompanied by adequate institutional capacity, transparent governance, and effective management of natural and economic resources. However, the effectiveness of decentralization varies considerably across regions due to disparities in economic potential, human resources, and political commitment. The synthesis further shows that financial independence positively affects the quality of public services and regional economic growth, although the relationship is moderated by expenditure efficiency and governance quality. The novelty of this review lies in its integrative framework linking revenue-side determinants, expenditure behavior, and governance mechanisms within a single analytical narrative, an integration rarely addressed jointly in prior single-country studies. The findings offer practical implications for policymakers designing fiscal transfer formulas and for future researchers seeking to test moderating variables such as digitalization and institutional quality in the fiscal decentralization–financial independence nexus.
Abstract:This study aims to analyze the influence of timeliness, transparency, and the effectiveness of recommendations on audit quality at the Audit Board(BPK) of Southeast Sulawesi Province. The research focuses on an economic-financial…
financial perspective, namely how these three variables play a role in improving the efficiency of fiscal governance, public spending accountability, and the effectiveness of state financial oversight. Research data were obtained through questionnaire distribution and audit document analysis. The results show that timeliness has a significant effect on audit quality because it is able to maintain the relevance of findings and accelerate follow-up. Transparency has a significant effect on increasing public trust and auditor credibility. The effectiveness of recommendations has the strongest influence on audit quality because it determines the implementation of financial governance improvements in audited entities. This study emphasizes the importance of promoting a fast, open, and responsive audit system to improve the quality of state financial management
Abstract:This study aims to construct an integrated constellation model and determine optimal strategies for reinforcing lecturers’ professional commitment at leading private universities in Bogor. Utilizing the POP-SDM (Modeling…
ng and Optimization of Management Resources) framework, the research integrates elements of local wisdom and organizational support within a systemic approach to human resource development. The exploratory qualitative phase involved in-depth interviews and focus group discussions to uncover major determinants influencing professional commitment. From the thematic analysis, four principal variables emerged—teamwork, organizational climate, religiosity, and work motivation—which were validated through expert judgment. Quantitative verification was subsequently performed using the Partial Least Squares–Structural Equation Modeling (PLS-SEM) technique to examine both direct and indirect relationships among constructs. The analysis confirmed that all variables exert positive and significant effects on lecturers’ professional commitment, with work motivation being the most dominant factor. To refine improvement priorities, the SITOREM (Scientific Identification Theory for Conducting Operational Research in Educational Management) method was applied, identifying indicators that should be improved, maintained, or further developed. The findings offer empirical and practical insights, including: (1) a validated POP-SDM–based commitment model combining cultural and organizational dimensions; (2) evidence-based strategies to enhance lecturer professionalism; and (3) an optimization framework to guide sustainable lecturer development in higher education institutions.