Abstract:The development of information technology provides solutions for increasing efficiency and accuracy in decision-making, such as in determining students eligible for BLT at SD Swasta IT ABI Husni. This study aims to implement…
ment the Naive Bayes algorithm to support a more objective BLT recipient selection process. The method used is CRISP-DM, starting from understanding the problem, data preparation, to model implementation. The data analyzed included type of residence, KPS recipients, parents' income, KIP recipients, number of siblings, distance from home and reasons for eligibility for BLT used were data from students of SD Swasta IT ABI Husni in the odd semester of 2024/2025, with a total of 137 data. The results of the study showed that the Naive Bayes algorithm was able to achieve an accuracy level of 98% with precision and recall of up to 100%, proving the effectiveness of the model in minimizing classification errors. In conclusion, the use of the Naive Bayes algorithm can help make decisions that are more targeted, transparent, and fair in the distribution of BLT.
Abstract:The Self-Help Housing Stimulant Assistance (BSPS) is a government house renovation program aimed at low-income communities. This program aims to enhance self-sufficiency in construction and improve the quality of houses,…
facilities, infrastructure, and public utilities through the principle of mutual cooperation. BSPS recipients must meet several criteria, such as income, house ownership status, house size, floor type, wall type, roof type, and water source. To address issues based on these criteria, Data Mining techniques using the Naive Bayes method were employed. This study utilized a dataset of BSPS recipients in Air Genting Village, Air Batu Sub-district, comprising 88 samples. The classification results from applying Naive Bayes yielded a precision value of 84%, a recall value of 81%, an F1-score of 82%, and an accuracy of 81%. The objective of this research is to facilitate the classification of eligible and rightful recipients of government assistance in the form of BSPS. The results of this study are expected to provide an alternative solution in determining BSPS recipients in Air Genting Village, Air Batu Sub-district
Abstract:Early childhood is frequently understood as a golden period of development; therefore, the formulation of learning goals becomes a crucial component that influences the direction of children’s behavior, motivation, and engagement…
engagement in the learning process. Problems arise when learning goals are predominantly formulated from an adult perspective, while the characteristics of children’s cognitive development are not fully taken into account, causing learning objectives to be difficult for children to understand and internalize. This study aims to examine the formation of learning goals for early childhood through the perspective of Jean Piaget’s cognitive development theory in order to obtain a conceptual understanding that is more aligned with children’s developmental stages. The research method employs a qualitative approach through a literature review of textbooks and national and international journal articles relevant to learning goals, cognitive development, and early childhood education, which are then analyzed descriptively through processes of identification, classification, and synthesis of theoretical concepts. The findings indicate that learning goals for early childhood tend to be concrete, short-term, contextual, and activity-oriented, and are not yet supported by mature self-regulation abilities. Based on Piaget’s framework, early childhood falls within the preoperational stage; therefore, understanding learning goals is highly dependent on direct experiences, play-based activities, simple symbols, and teacher guidance. The conclusion emphasizes that the design of learning goals must be consciously adjusted to children’s cognitive developmental stages so that learning objectives can be understood, meaningful, and optimally achieved. The novelty of this study lies in the conceptual integration of Piaget’s cognitive development theory with the practical formulation of learning goals in early childhood education as a theoretical–practical foundation for teachers.
Abstract:Abstract: This study aims to classify the nutritional status of toddlers based on anthropometric data using the K-Nearest Neighbor (KNN) algorithm. Data were obtained from 20 Integrated Health Posts (Posyandu) in Rumbai…
Timur District, including Lembah Sari Village and Limbungan Village with a total of 1,000 toddler data. After cleaning and preprocessing, 782 data were obtained ready for use. The preprocessing stages include data cleaning and transformation, outlier removal, minority class handling, and data normalization. Next, data balancing was carried out using the Synthetic Minority Oversampling Technique (SMOTE) to address class imbalance. The data was divided into 80% training data and 20% test data, then the K parameter was tested from 1 to 15 using 5-fold cross-validation. The results showed that the value of K = 1 provided the best performance with a macro recall of 0.8827 and an accuracy of 86.26%. These results indicate that the combination of the KNN algorithm with the SMOTE method and Min-Max normalization is effective in improving classification performance on imbalanced data and producing accurate and balanced predictions of toddler nutritional status between classes.
Keywords: k-nearest neighbor; toddler nutritional status; SMOTE; min-max scaling; classification; anthropometric data
Abstrak: Penelitian ini bertujuan untuk mengklasifikasikan status gizi balita berdasarkan data antropometri menggunakan algoritma K-Nearest Neighbor (KNN). Data diperoleh dari 20 Posyandu di Kecamatan Rumbai Timur, meliputi Kelurahan Lembah Sari dan Kelurahan Limbungan dengan total 1.000 data balita. Setelah melalui proses cleaning dan preprocessing, diperoleh 782 data yang siap digunakan. Tahapan pra-pemrosesan meliputi pembersihan dan transformasi data, penghapusan outlier, penanganan kelas minoritas, serta normalisasi data. Selanjutnya dilakukan penyeimbangan data menggunakan Synthetic Minority Oversampling Technique (SMOTE) untuk mengatasi ketidakseimbangan kelas. Data dibagi menjadi 80% data latih dan 20% data uji, kemudian dilakukan pengujian parameter K dari 1 hingga 15 menggunakan 5-fold cross-validation. Hasil penelitian menunjukkan bahwa nilai K = 1 memberikan performa terbaik dengan recall macro sebesar 0,8827 dan akurasi 86,26%. Hasil ini menunjukkan bahwa kombinasi algoritma KNN dengan metode SMOTE dan normalisasi Min-Max efektif dalam meningkatkan kinerja klasifikasi pada data tidak seimbang serta menghasilkan prediksi status gizi balita yang akurat dan seimbang antar kelas.
Kata kunci: k-nearest neighbor; status gizi balita; SMOTE; min-max scaling; klasifikasi; data antropometri
Abstract:Abstract: Information Technology (IT) has played a crucial role in various sectors, including the transportation sector, as seen in the Department of Transportation of Asahan Regency, North Sumatra. One of the challenges…
in this area is the performance of parking attendants, which affects the effectiveness of parking management and traffic safety. Poor performance of parking attendants can cause various issues, including traffic congestion, rule violations, and user discomfort. Therefore, evaluating the performance of parking attendants is essential to improve service quality and parking safety. In this context, the implementation of a technology-based information system is an appropriate solution to enhance the effectiveness of the performance evaluation process for parking attendants. Classification methods, such as k-nearest neighbor (KNN), are used to evaluate the performance of parking attendants more accurately and efficiently. This method allows early detection of poor performance, such as fraud or traffic rule violations, and provides feedback for improvements. The primary goal is to measure effectiveness, identify areas for improvement, and recognize parking attendants with good performance.
Keywords: Information Technology, Parking Attendants, Performance Evaluation, KNN, Asahan Regency.
Abstrak: Teknologi Informasi (TI) telah memainkan peran penting dalam berbagai sektor, termasuk sektor transportasi, seperti yang terlihat pada Dinas Perhubungan Kabupaten Asahan, Sumatera Utara. Salah satu tantangan di wilayah ini adalah kinerja juru parkir yang mempengaruhi efektivitas pengelolaan parkir dan keselamatan lalu lintas. Kinerja juru parkir yang kurang optimal dapat menimbulkan berbagai masalah, termasuk kemacetan, pelanggaran aturan, dan ketidaknyamanan pengguna parkir. Oleh karena itu, penilaian kinerja juru parkir menjadi sangat penting untuk meningkatkan kualitas layanan dan keamanan parkir. Dalam konteks ini, penerapan sistem informasi berbasis teknologi menjadi solusi yang tepat untuk meningkatkan efektivitas proses penilaian kinerja juru parkir. Metode klasifikasi, seperti k-nearest neighbor (KNN), digunakan untuk mengevaluasi kinerja juru parkir dengan lebih akurat dan efisien. Metode ini memungkinkan deteksi dini terhadap kinerja buruk, seperti penipuan atau pelanggaran aturan lalu lintas, serta memberikan umpan balik untuk perbaikan. Tujuan utamanya adalah mengukur efektivitas, mengidentifikasi area perbaikan, dan memberikan apresiasi bagi juru parkir yang memiliki kinerja baik.
Kata Kunci: Teknologi Informasi, Juru Parkir, Penilaian Kinerja, KNN, Kabupaten Asahan.
Abstract:Abstract: In this study, an analysis of the use of the Naive Bayes algorithm for sentiment analysis of reviews from Shopee app users on the Google Play Store was conducted, with classification divided into three categories:…
es: positive, negative, and neutral. To improve data quality, a preprocessing process was carried out with stages of cleaning, case folding, normalization, stop word removal, stemming, and tokenizing. Next, the text is formatted using the TF-IDF method to facilitate classification. For this data, the Naive Bayes model is used, which has an accuracy rate of 87% in detecting sentiment. Positive and negative categories can be easily identified compared to neutral sentiments due to the smaller amount of neutral data. Overall, the Naive Bayes algorithm successfully analyzed user sentiments well. The research can be developed with other algorithm methods, such as SVM, K-NN, or Decision Tree, in order to compare the performance of various algorithms.
Keywords: sentiment analysis; naive bayes; user reviews; e-commerce; shopee
Abstrak: Dalam penelitian ini dilakukan analisis penggunaan algoritma Naive Bayes untuk analisis sentimen review dari pengguna aplikasi Shopee di Google Play Store, klasifikasi dibagai menjadi 3 kategori yaitu positif, negatif, dan netral. Untuk meningkatkan kualitas data, dilakukam proses preprocessing dengan tahap cleanimg, case folding, normalisasi, stopword removal, stemming, dan tekonezing. Selanjutnya, teks diformat menggunakan metode TF-IDF untuk memudahkan klasifikasi. Untuk data ini, model Naive Bayes digunakan, yang memiliki tingkat akurasi 87% dalam mendeteksi sentimen. Kategori positif dan negatif dapat dengan mudah diidentifikasi dibadingkan sentiemen netral karena jumlah data netral yang lebih sedikit. Secara keseluruhan, algoritma Naive Bayes berhasil menganalisis perasaan pengguna dengan baik. Penelitian dapat dikembangkan dengan algoritma metode lain, seperti SVM, K-NN, atau Decision Tree, guna membandingkan kinerja berbagai algoritma.
Kata kunci: analisis sentiment; naive bayes; ulasan pengguna; e-commerce; shopee
Abstract:Abstract: PT. Padasa Enam Utama, a palm oil plantation company, currently assesses the quality of Fresh Fruit Bunches (FFB) based solely on physical aspects. They use Microsoft Excel without a specialized application system,…
tem, which can lead to subjective assessments and the risk of fraud. This research aims to develop a predictive system for the quality of Fresh Fruit Bunches. Data collection was conducted using quantitative methods through direct observation and interviews with relevant parties. The study shows that the use of the K-Nearest Neighbor method provides the best accuracy with a more efficient calculation process. With this system, the company’s performance in making decisions regarding FFB quality is expected to improve. The system helps reduce human errors in quality assessments and offers visualizations that make it easier for users to understand the classification of production quality. Although the results are reliable, there is still room for further development, such as improving accuracy through more advanced data preprocessing techniques or using more complex machine learning models.
Keywords: Data Mining; K-Nearest Neighbor algorithm; Fresh Fruit Bunches (FFB); Python; Streamlit.
Abstrak: PT. Padasa Enam Utama, sebuah perusahaan perkebunan kelapa sawit, saat ini menilai kualitas produksi Tandan Buah Segar (TBS) berdasarkan aspek fisik saja. Mereka menggunakan Microsoft Excel tanpa sistem aplikasi khusus, yang dapat menyebabkan penilaian tidak objektif dan risiko kecurangan. Penelitian ini bertujuan untuk mengembangkan sistem prediksi mutu kualitas Tandan Buah Segar. Dalam pengumpulan data, digunakan metode kuantitatif melalui observasi langsung dan wawancara dengan pihak terkait. Penelitian menunjukkan bahwa penggunaan metode K-Nearest Neighbor memberikan akurasi terbaik dengan proses perhitungan yang lebih efisien. Dengan adanya sistem ini, diharapkan kinerja perusahaan dalam membuat keputusan terkait mutu produksi TBS dapat meningkat. Sistem ini membantu mengurangi kesalahan manusia dalam penilaian mutu TBS dan memberikan visualisasi yang memudahkan pengguna memahami klasifikasi mutu produksi. Meskipun telah memberikan hasil yang dapat diandalkan, masih ada ruang untuk pengembangan lebih lanjut, seperti peningkatan akurasi melalui teknik preprocessing data yang lebih canggih atau penggunaan model-machine learning yang lebih kompleks.
Kata kunci: Data Mining; Algoritma K-Nearest Neighbor; Tandan Buah Segar (TBS); Python; Streamlit
Abstract:Abstract : The Central Bureau of Statistics (BPS) is a non-departmental government agency established as a provider of data or information based on Law No. 6/1960 on Census and Law No. 7/1997 on Statistics. The Central Statistics…
tatistics Agency (BPS) recorded the number of motorized vehicles such as cars, buses, trucks, and motorcycles in the provinces of North Sumatra and West Sumatra in 2020-2021 reaching 3,043,892 million units. The purpose of this study is to classify the number of motorized vehicles in the form of cars, motorcycles, buses and trucks. This research uses quantitative research with Naive Bayes Algorithm analysis model. The data used in this study is data from several regions in North Sumatra Province and West Sumatra Province in 2020-2021. Evaluation of model performance is based on accuracy parameters, precision and total recall of the confusion-matrix. The results of testing the dataset and calculating the model performance parameters have obtained an accuracy value of 100%. With the percentage value of the description of each dataset class, namely a little 70.6%, moderate 21.6%, and a lot 7.8%.
Keywords :classification;confusion-matrix; data; motor vehicles; naive bayes
Abstrak : Badan Pusat Statistik (BPS) adalah lembaga pemerintahan non-departemen yang dibentuk sebagai penyedia data atau informasi berdasarkan UU Nomor 6 Tahun 1960 tentang Sensus dan UU Nomor 7 Tahun 1997 tentang Statistik. Badan Pusat Statistik (BPS) mencatat jumlah kendaraan bermotor seperti mobil, bus, truk, dan sepeda motor di Provinsi Sumatera Utara dan Sumatera Barat pada tahun 2020-2021 mencapai 3.043.892 juta unit. Tujuan dari penelitian ini yaitu untuk mengklasifikasikan jumlah kendaraan bermotor berupa mobil, sepeda motor, bus dan, truk. Adapun penelitian ini menggunakan jenis penelitian kuantitatif dengan model analisis Algoritma Naive Bayes. Data yang digunakan pada penelitian ini adalah data dari beberapa daerah di Provinsi Sumatera Utara dan Provinsi Sumatera Barat tahun 2020-2021. Evaluasi kinerja model didasarkan pada parameter akurasi, presisi dan recall total dari Confusion-Matrix. Hasil pengujian dataset dan perhitungan parameter performa model telah didapat nilai akurasi 100%. Dengan presentase nilai keterangan setiap kelas dataset yaitu Sedikit 70,6%, Sedang 21,6%, dan Banyak 7,8%.
Kata kunci :confusion-matrix; data; kendaraan bermotorklasifikasi; naive bayes
Abstract:Abstract: The Family Hope Program (PKH) is a government program in the form of cash for Very Poor Households (RTSM) whose qualifications are met related to efforts to improve human quality, not in the field of education…
but also health. In the short term, the PKH program is calculated to reduce the expenditure of poor families and reduce poverty in the long term. To receive the PKH Program) the government has set several criteria, including income, house ownership status, house size, floor type, roof, wall, and type of water source. As for the way to do the settlement of the criteria that have been set, namely by utilizing the Data Mining technique through the Naïve Bayes method. The dataset in this study is the data of recipients of the 2020 Family Hope Program as many as 82 samples. The results of the classification modeling with the Naïve Bayes Algorithm produce precision values for the positive class 100%, for the negative class 77%, the recall value for the positive class 80%, for the negative class 100%, the f1-score value for the positive class 89%, for the negative class 87%, and 88% accuracy value. The purpose of this research is to help the Social Service in classifying the recipients of the Family Hope Program (PKH).
Keywords: The Family Hope Program; Data Mining; Naïve Bayes
Abstrak: Program Keluarga Harapan (PKH) merupakan program pemerintah dalam bentuk tunai untuk Rumah Tangga Sangat Miskin (RTSM) yang kualifikasinya terpenuhi terkait dengan upaya peningkatan kualitas manusia tersebut bukan dalam bidang pendidikan tetapi juga kesehatan. dalam jangka pendek Program PKH diperhitungkan bisa mengurangi biaya pengeluaran keluarga miskin serta mengurangi kemiskinan dalam jangka panjang. Untuk menerima Program PKH) pemerintah sudah menetapkan beberapa kriteria, diantaranya Penghasilan, Status Kepemilikan Rumah, Ukuran Rumah, tipe Lantai, Atap, Dinding, serta jenis sumber air. Adapun cara untuk melakukan penyelesaian terhadap kriteria yang sudah ditetapkan yaitu dengan memanfaatkan teknik Data Mining melalui Metode Naïve Bayes. Dataset dalam penelitian ini adalah data penerima Program Keluarga Harapan tahun 2020 sebanyak 82 sampel. Hasil pemodelan klasifikasi dengan Algoritma Naïve Bayes menghasilkan besaran nilai precision untuk kelas positif 100%, untuk kelas negatif 77%, nilai recall untuk kelas positif 80%, untuk kelas negatif 100%, nilai f1-score untuk kelas positif 89%, untuk kelas negatif 87%, dan nilai akurasi 88%. Tujuan dilaksanakannya penelitian ini adalah untuk membantu Dinas Sosial mengklasifikasikan penerima Program Keluarga Harapan (PKH).
Kata kunci: Program Keluarga Harapan; Data Mining; Naïve Bayes
Abstract:Optimizing the library space at OPPM Pondok Modern Darussalam Gontor aims to improve the book layout, classification system, and space design initiatives to increase the efficiency of borrowing books for students. The problems…
oblems faced include sloppy book layout, an ineffective classification system, and a lack of design initiative from library administrators. The implementation method uses a Participatory Action Research (PAR) approach, which involves several stages of socializing the layout design to administrators, implementing a new classification system, writing books according to classification, and creating Standard Operating Procedures (SOP) for daily, weekly and monthly activities. Familiarization provides an understanding of ergonomic design principles, while a new classification system and book fireplace make it easier to find and return books. Creating SOPs ensures consistent and efficient implementation. The results of this method show significant improvements in library management and user experience, with students finding it easier to access and borrow books and library administrators carrying out their duties in a more structured manner.
Keywords: optimization; libraries; layout design
Abstrak: Optimalisasi ruang perpustakaan di OPPM Pondok Modern Darussalam Gontor bertujuan untuk memperbaiki tata letak buku, sistem klasifikasi, dan inisiatif desain ruang untuk meningkatkan efisiensi peminjaman buku bagi siswa. Permasalahan yang dihadapi antara lain tata letak buku yang tidak rapi, sistem klasifikasi yang tidak efektif, dan kurangnya inisiatif desain dari pengelola perpustakaan. Metode pelaksanaannya menggunakan pendekatan Participatory Action Research (PAR) yang meliputi beberapa tahapan yaitu sosialisasi desain tata ruang kepada pengelola, penerapan sistem klasifikasi baru, penulisan buku sesuai klasifikasi, dan pembuatan Standard Operating Procedure (SOP) harian, mingguan dan kegiatan bulanan. Pembiasaan memberikan pemahaman tentang prinsip-prinsip desain ergonomis, sementara sistem klasifikasi baru dan perapian buku memudahkan pencarian dan pengembalian buku. Membuat SOP memastikan implementasi yang konsisten dan efisien. Hasil dari metode ini menunjukkan peningkatan yang signifikan dalam pengelolaan perpustakaan dan pengalaman pengguna, siswa menjadi lebih mudah mengakses dan meminjam buku serta pengelola perpustakaan menjalankan tugasnya secara lebih terstruktur.
Kata kunci: optimalisasi; perpustakaan, desain tata letak