Abstract:Abstract: Heart disease is one of the leading causes of death worldwide, making early detection and accurate diagnosis crucial for reducing mortality rates and improving patient outcomes. This study aims to evaluate the…
effectiveness of four machine learning algorithms—Logistic Regression, Random Forest, Support Vector Machine (SVM), and K-Nearest Neighbors (KNN)—in predicting heart disease, with a focus on enhancing model performance using Linear Discriminant Analysis (LDA) for feature reduction. Among the models, SVM achieved the highest accuracy at 84.24%, followed by Logistic Regression at 83.70%. Although Random Forest and KNN showed lower accuracies, all models benefited from LDA's dimensionality reduction. This study suggests that SVM, combined with LDA, offers an optimal solution for early and accurate heart disease prediction in the healthcare industry.
Keywords: feature reduction; heart disease; linear discriminant analysis (LDA); machine learning; SVM
Abstrak: Penyakit jantung merupakan salah satu penyebab utama kematian di seluruh dunia, sehingga deteksi dini dan diagnosis yang akurat sangat penting untuk menurunkan angka kematian dan meningkatkan hasil pengobatan pasien. Penelitian ini bertujuan untuk mengevaluasi efektivitas empat algoritma pembelajaran mesin—Regresi Logistik, Random Forest, Support Vector Machine (SVM), dan K-Nearest Neighbors (KNN)—dalam memprediksi penyakit jantung, dengan fokus pada peningkatan kinerja model menggunakan Analisis Diskriminan Linear (LDA) untuk reduksi fitur. Di antara model yang diuji, SVM mencapai akurasi tertinggi sebesar 84,24%, diikuti oleh Regresi Logistik dengan 83,70%. Meskipun Random Forest dan KNN menunjukkan akurasi yang lebih rendah, semua model memperoleh manfaat dari reduksi dimensi yang diberikan oleh LDA. Studi ini menunjukkan bahwa SVM yang dikombinasikan dengan LDA merupakan solusi optimal untuk prediksi penyakit jantung secara dini dan akurat dalam industri kesehatan.
Kata kunci: linear discriminant analysis (LDA); machine learning; penyakit jantung; reduksi fitur; SVM.
Abstract:Abstract: The current development of technology has successfully met various societal needs, one of which is the buying and selling activities. This development has led people to engage in online transactions, where buyers…
rs do not necessarily have to meet sellers in person. Tokopedia is one of the most popular e-commerce platforms used in Indonesia. Security issues arose when in 2020 Tokopedia experienced a breach, with data from around 91 million accounts being compromised by hackers. Consequently, Tokopedia needed to establish a Data Protection and Privacy Office (DPPO) to protect and safeguard user data privacy.This research addresses how perceptions of security and privacy can influence users' trust in transacting on Tokopedia. Using multiple linear regression analysis, the study evaluates the relationship between perceptions of data security and privacy with trust in transacting on Tokopedia. Based on the calculations of the multiple linear regression model using previously collected respondent data, it was found that perceptions of data security do not directly affect trust in transactions. However, perceptions of privacy are considered to have a significant influence and can increase trust in transactions among students in Pekanbaru.
Keywords: data security; e-commerce; tokopedia; transaction trust; user perceptions
Abstrak: Perkembangan teknologi saat ini telah sukses mencapai berbagai kebutuhan masayarakat salah satunya kegiatan jual beli, perkembangan ini membawa manusia untuk dapat melakukan jual beli secara online dimana tidak mengharuskan pembeli bertemu penjual secara langsung. Tokopedia menjadi salah satu platform e-commerce yang sangat popular digunkanan diindonesia. Masalah keamaan terjadi dimana pada tahun 2020 tokopedia mengalami peretasan dengan sekitar 91 juta akun berhasil diperoleh datanya oleh peretas, sehingga Tokopedia perlu membentuk data protection and privacy office (DPPO) guna melindungi dan menjaga privasi data pengguna Tokopedia.terkait hal tersebut penelitian ini mengangkat bagaimana persepsi keamanan dan privasi dapat mempengaruhi kepercayaan pengguna dalam bertransaksi ditokopedia. Dengan menggunakan metode regresi linear berganda, evaluasi dilakukan untuk menjelaskan hubungan antara persepi keamanan data dan privasi terhadap kepercayaan bertransaksi ditokopedia. Berdasarkan perhitungan model regresi linear berganda menggunakan data responden yang telah dilakukan sebelumnya didapat persepsi keamanan data terhadap kepercayaan bertransaksi tidak berpengaruh secara langsung. Namun pada persepsi privasi terhadap kepercayaan bertransaksi dinilai sangat berpengaruh dan dapat meningkatkan kepercayaan bertransaksi di kalangan mahasiswa di pekanbaru.
Kata kunci: e-commerce; keamanan data; kepercayaan transaksi; persepsi pengguna; tokopedia
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: Population is a group of people who live or settle in an area for six months or more. Increasing the population in an area results in more problems being faced by the area such as high unemployment rates, poverty…
ty and food shortages which result in hunger. BPS Asahan Regency records that there is an increase in population every year. Asahan Regency BPS cannot predict population growth in the following year, so an application is needed to predict population growth. The purpose of this study is to predict population growth in Asahan Regency in the following year based on previous data using the concept of data mining. By applying data mining using multiple linear regression methods can be used to calculate population growth estimates based on previous data. This quantitative research used population data of Asahan Regency from 2016 to 2022. From the calculation of the multiple linear regression model using data from the previous five years, the estimated population growth of Asahan for 2023 was 824,617 people and the process of estimating the population became more systematic and calculated. well with this population estimation system and the process of storing data becomes easier and does not require a lot of paper to print and save.
Keywords: Application; Data Mining; Multiple Linear Regression
Abstrak: Penduduk merupakan sekumpulan orang yang tinggal atau menetap pada suatu wilayah selama enam bulan atau lebih. Bertambahnya jumlah penduduk pada suatu daerah mengakibatkan semakin banyak pula persoalan yang di hadapi oleh daerah tersebut seperti tingkat pengangguran yang tinggi, kemiskinan dan kekurangan pangan yang mengakibatkan kelaparan. BPS Kabupaten Asahan mencatat terjadi adanya pertambahan penduduk pada setiap tahunnya. BPS Kabupaten Asahan tidak dapat memprediksi pertumbuhan penduduk pada tahun berikutnya sehingga dibutuhkan suatu aplikasi untuk memprediksi pertambahan penduduk tersebut. Tujuan penelitian ini adalah untuk memprediksi pertumbuhan penduduk Kabupaten Asahan pada tahun berikutnya berdasarkan data sebelumnya menggunakan konsep data mining. Dengan menerapkan data mining menggunakan metode regresi linier berganda dapat digunakan untuk menghitung estimasi pertumbuhan penduduk berdasarkan data sebelumnya. Penelitian yang dilakukan secara kuantitatif ini menggunakan data penduduk Kabupaten Asahan dari tahun 2016 sampai tahun 2022. Dari perhitungan model regresi linier berganda menggunakan data lima tahun sebelumnya didapat estimasi pertumbuhan penduduk Asahan untuk tahun 2023 sebesar 824.617 jiwa dan proses estimasi jumlah penduduk menjadi lebih sistematis dan terkalkulasi dengan baik dengan adanya sistem estimasi jumlah penduduk ini dan proses penyimpanan data menjadi lebih mudah dan tidak memerlukan banyak kertas untuk di cetak dan di simpan.
Kata kunci: Aplikasi; Data Mining; Regresi Linier Berganda
Abstract:Abstract: A research institute explains that with 83.7 million people using the Internet, Indonesia is among the top 20 internet users globally. Various individual or group activities require an internet network, one of…
which is playing games, for developments in the gaming sector, especially the MOBA (Massive Online Battle Arena) genre game, is being hotly discussed. There are various kinds of MOBA genre games, one of which is the Mobile Legends game. Many E-Sport Mobile Legends teams, especially in Asia, make this phenomenon a business space to generate large profits. In this study, the researcher recommends a good machine learning algorithm to predict the outcome of Mobile Legends matches. Of the 600 match history data analyzed, this study recommends the Artificial Neural Network (ANN) and Random Forest (RF) algorithms as the right algorithms to predict the outcome of the match. Prediction results from each algorithm can reach 82% and 80% accuracy. These findings can help the E-sports analysis team build their match strategy.
Keywords: artificial neural networ; machine learning; mobile legend; prediction; random forest
Abstrak: Sebuah lembaga penelitian menjelaskan bahwa dengan 83,7 juta penduduk yang menggunakan Internet, Indonesia termasuk di dalam 20 besar pengguna internet secara global. Berbagai aktivitas individu atau kelompok membutuhkan jaringan internet, salah satunya adalah bermain game, untuk perkembangan pada sektor game khususnya game bergenre MOBA (Massive Online Battle Arena) sedang hangat diperbincangkan. Ada berbagai macam game bergenre MOBA, salah satunya game Mobile Legends. Banyak tim E-Sport Mobile Legends khususnya di asia menjadikan fenomena ini sebagai ruang bisnis untuk menghasilkan keuntungnya yang besar. Dalam penelitian ini, peneliti merekomendasikan algoritma pembelajaran mesin yang baik untuk memprediksi hasil pertandingan Mobile Legends. Dari 600 data riwayat pertandingan yang dianalisis, penelitian ini merekomendasikan algoritma Artificial Neural Network (ANN) dan Random Forest (RF) sebagai algoritma yang tepat untuk memprediksi hasil pertandingan. Hasil prediksi dari masing-masing algoritma dapat mencapai 82% dan akurasi 80%. Temuan ini dapat membantu tim analisis E-sports membangun strategi pertandingan mereka.
Kata kunci: artificial neural network; machine learning; mobile legend; prediksi; random forest
Abstract: Abstract – Price forecasting is a part of economic decision making. Forecasting the daily rise and fall of gold prices can help investors decide when to buy or sell the commodity. The price of gold depends on many factors…
many factors such as the price of other precious metals, the price of crude oil, the performance of the stock exchange, and the exchange rate of currencies. This study discusses gold price forecasting using the multiple linear regression method. The results of this study indicate that the best model is in the data distribution of 70%: 30% for training and testing, with a MAPE of 4.7% Based on these results, it can be concluded that the use of multiple linear regression method produces a fairly good model for gold prices forecasting. Besides, the correlation analysis show that the price of other precious metals greatly influences the price of gold where in this case the silver price whose correlation value is 0.87.
Keywords: forecasting, gold investment, multiple linear regression
Abstrak: Peramalan harga merupakan bagian dari pengambilan keputusan ekonomi. Melakukan peramalan terhadap kenaikan dan penurunan harga emas harian dapat membantu investor memutuskan kapan harus membeli atau menjual komoditas. Harga Emas bergantung pada banyak faktor seperti harga logam mulia lainnya, harga minyak mentah, kinerja bursa saham, dan nilai tukar mata uang. Penelitian ini membahas peramalan harga emas dengan menggunakan metode regresi linear ganda. Hasil dari penelitian ini menunjukkan bahwa model terbaik terdapat pada pembagian data pelatihan 70% dan pengujian 30%, dengan MAPE sebesar 4.7%. Berdasarkan hasil tersebut dapat diambil kesimpulan bahwa penggunaan metode regresi linear ganda menghasilkan model yang cukup baik untuk peramalan harga emas. Selain itu, analisis korelasi menunjukkan bahwa harga logam mulia lainnya sangat mempengaruhi harga emas dimana dalam hal ini variabel harga perak yang nilai korelasinya 0.87.
Kata kunci: peramalan; investasi emas, regresi linear ganda
Abstract:Abstract: Flood disasters often occur in areas with certain geographical conditions, such as proximity to rivers, high rainfall especially during the wetseason and soil types that contain clay so that they are not good enough…
nough to absorb water. One of the cities in Indonesia whichhas frequent floods. The planned mitigation strategy must be more targeted so that it is more effective in tackling flood disasters. Therefore, mapping with Geographic Information Systems can be used to map areas that are prone to flooding specifically by combining spatial data on each predetermined parameter. Not only that, the integration of Geographic Information Systems and forecasting with multiple linear regression methods can predict the level of flood vulnerability based on the parameters determined in the following year. Based on the analysis that has been done, the areas in Pontianak City that are prone to flood disasters are spread over several sub-districts, namely East Pontianak District, Pontianak City District and parts of North Pontianak District.
Keywords: Flood vulnerability; Geographic Information System; Multiple Linear Regression
Abstrak: Bencana banjir seringkali terjadi di wilayah dengan kondisi geografis tertentu sepertijaraknya yang dekat dengan sungai, curah hujan cukup tinggi khususnya pada musim hujan hingga mayoritas jenis tanah yang memiliki kandungan lempung sehingga tidak cukup baikdalam menyerap air. Kota Pontianak merupakan satu diantara kota di Indonesia yang sering dilanda bencana banjir. Oleh karena itu, pemetaan dengan Sistem Informasi Geografis dapat digunakan untuk memetakan wilayah-wilayah yang rawan bencana banjir secara spesifik dengan menggabungkan data spasial pada setiap parameter yang sudah ditentukan. Tidak hanya itu, integrasi sistem informasi geografis dan peramalan dengan metoderegresi linier berganda dapatmemprediksi tingkat kerawanan banjir berdasarkan parameter yang ditentukan pada tahun berikutnya. Berdasarkan analisis yang telah dilakukan, daerah di Kota Pontianak yang rawan bencanabanjir tersebar di beberapa kecamatan yaitu Kecamatan Pontianak Timur, Kecamatan Pontianak Kota dan sebagianKecamatan Pontianak Utara.
Kata kunci: Kerawanan Banjir; Regresi Linier Berganda; Sistem Informasi Geografis
Abstract:Abstract: DNS plays a vital role in the operation of services on the internet. Almost all services on the internet are under DNS control, such as email, FTP, web apps, etc. So, it is not surprising that various malicious…
activities involve DNS services such as financial fraud, phishing, malware, and malicious activity, etc. Fortunately, in DNS there is a record with the name time to live which can be used to detect a query or the address accessed from the user is a normal query or an abnormal query. Therefore, the purpose of this study is to determine the correlation value between time to live and abnormal queries on passive DNS data using the Binary Logistic Regression model. The results showed that the Binary Logistic Regression method could model the correlation between TTL, elapsed, and bytes which have an optimal model F1 Score of 0.9997 and also have a condition close to the ideal state by using the Precision-Recall Curve (PRC) graph plot.
Keywords: Binary Logistic Regression; DNS Passive; Precision-Recall Curve (PRC); Query Abnormal
Abstrak: DNS memegang peranan yang vital di dalam berjalanya service di internet. Hampir seluruh layanan di internet berada di bawah kendali DNS seperti email, ftp, app web dll. Jadi, tidak mengherankan bahwa berbagai kegiatan jahat melibatkan layanan DNS seperti financial fraud, phising, malware dan aktivitas malicious dll. Untungnya, di dalam DNS tersimpan sebuah record dengan nama time to live yang dapat digunakan untuk mendeteksi sebuah query atau alamat yang diakses dari user tersebut bersifat query normal atau query tidak normal. Oleh karena itu, tujuan penelitian ini adalah untuk mengetahui nilai korelasi antara time to live dengan query tidak normal pada data passive DNS dengan menggunakan model Binary Logistic Regression. Hasil penelitian menunjukkan bahwa metode Binary Logistic Regression dapat memodelkan korelasi antara TTL, elapsed dan bytes yang memiliki model optimal F1 Score sebesar 0.9997 dan juga memiliki kondisi hampir mendekati keadaan ideal dengan menggunakan plot grafik Precision Recall Curve (PRC).
Kata kunci: Binary Logistic Regression; DNS Passive; Precision-Recall Curve (PRC); Query Abnormal
Abstract:This study aims to develop a comprehensive constellation model and identify optimal strategies for strengthening lecturers’ professional commitment in the largest private universities in Bogor. Penelitian ini mengkaji secara…
secara mendalam bagaimana emosi dan belajar sosial memengaruhi proses pembelajaran di sekolah dasar melalui perspektif neuropedagogik dan brain‑based learning. A mixed methods approach was used by combining quantitative analysis (meta-analysis of 173 respondents and 47 indicators of NP, EC, OB, MS, BS) and descriptive qualitative analysis using thematic analysis techniques on semi-structured interviews with five elementary school teachers. The meta-analysis results showed a very strong average effect of the latent construct relationship (t(128) = 12.92; p < 0.001; r ≈ 1.00) with almost zero heterogeneity (Qₑ(128) = 1.67; τ² = 0; I² = 0%), and no significant moderating effects were found for all indicators; the partial meta-regression coefficients for all items were very close to zero and the R² value was 0.000. Qualitatively, three main themes emerged: (1) positive emotions as the foundation of learning readiness, (2) social interaction as a reinforcement of meaning formation, and (3) contextual learning that integrates cognitive, emotional, and social dimensions. Although most teachers have not yet mastered the concepts of neuropedagogy and brain-based learning theoretically, they have intuitively implemented its principles through motivation, praise, humor, group work, collaborative projects, and learning experiences relevant to students' real lives. These findings support the latest theory that places emotions and social interactions as the main drivers of brain function in learning (Immordino Yang, 2016; Tyng et al., 2017; Vygotsky, 1978; Jensen, 2008), and emphasizes the importance of strengthening teachers' competence in understanding and designing brain- and emotion-based learning to support the holistic development of elementary school students.
Abstract:Public service quality is one of the fundamental indicators in assessing the performance of government institutions, especially at the district level where direct interactions with citizens take place. This study aims to…
analyze the influence of employee motivation on the quality of administrative services at the Leihitu Sub-district Office, Central Maluku Regency. The research employs a quantitative approach with an explanatory design to identify causal relationships between variables. The population in this study consists of all employees involved in administrative services, and total sampling was used due to the manageable number of staff. Data were collected through a structured questionnaire using a Likert scale to measure motivation and service quality indicators. The data were analyzed using descriptive statistics and linear regression to determine the effect of motivation on service quality. The results show that employee motivation significantly and positively influences administrative service quality. Employees with higher intrinsic and extrinsic motivation tend to demonstrate better responsiveness, discipline, communication, and consistency in carrying out public service functions. The study concludes that strengthening motivation is essential to improve public service performance. Therefore, organizational leaders are encouraged to enhance work motivation through recognition, supportive leadership, fair reward systems, and professional development opportunities to ensure services meet community expectations.