Diabetes dalam kehamilan dapat meningkatkan berbagai risiko, baik pada maternal maupun neonatus. Adanya gangguan homeostasis glukosa dalam kehamilan dapat meningkatkan terjadinya malformasi ...kongenital, keguguran, risiko preeklampsia, Cepalo Pelvik Dispropotion (CPD), kelahiran prematur, kelainan letak, plasenta previa dan hipoglikemia neonatus. Oleh karena itu, diperlukan perhatian dan penanganan menyeluruh bagi ibu hamil yang menderita diabetes. Teknologi machine learning dapat dimanfaatkan dalam berbagai hal di bidang kesehatan. Salah satu dari pemanfaatan machine learning di bidang kesehatan adalah kemampuannya untuk mendeteksi risiko tinggi diabetus mellitus pada ibu hamil melalui berbagai data dan informasi seperti nama, usia, umur kehamilan, gravida, para, riwayat kehamilan, riwayat penyakit yang pernah diderita, faktor risiko, dan riwayat persalinan yang lalu. Proses persalinan ibu hamil dipengaruhi oleh faktor fisiologis dan faktor-faktor risiko lain yang dapat mempengaruhinya. Penelitian ini menggunakan dataset yang diperoleh dari data pemeriksaan ibu hamil di Puskesmas Lawang dari bulan Januari 2021 sampai dengan Agustus 2021 dan menggunakan16 atribut penting, yaitu: tanggal pengkajian, nama, tanggal HPHT, tanggal HPL, umur, GPA, usia kehamilan, KSPR, keterangan KSPR, IMT, kategori IMT, reduksi, albumin, hepatitis, HIV, dan IMS. Penelitian ini telah melakukan tahapan pengumpulan data, perancangan, implementasi, pengujian dan analisis data yang mengimplementasikan teknik machine learning K-Nearest Neighbor (KNN). Nilai akurasi tertinggi pada skenario pengujian pertama dengan atribut k=2 adalah 70.27%. Nilai akurasi tertinggi pada skenario pengujian kedua dengan k=3 adalah 75.68%. Nilai akurasi tertinggi pada skenario pengujian ketiga dengan k=4 adalah 78.38%. Sedangkan Nilai akurasi tertinggi pada skenario pengujian keempat dengan k=5 adalah 77.03%. Nilai akurasi tertinggi dicapai pada rasio sebesar 7:3 antara data latih dengan data testing. AbstractDiabetes in pregnancy can increase various risks, both maternal and neonatal. Disorders of glucose homeostasis in pregnancy can increase the occurrence of congenital malformations, miscarriage, risk of preeclampsia, Cepalo Pelvic Dispropotion (CPD), premature birth, malformations, placenta previa and neonatal hypoglycemia. Thorough attention and treatment is needed for pregnancy with diabetes. Machine learning technology can be used to detect the risk of diabetes mellitus in pregnancy. Several data such as name, age, gestational age, gravida, para, past pregnancy history, past medical history, risk factors, and past birth history were used in the risk detection. Delivery process in pregnancy is affected by the physiologic of prospective mother and several other risk factors.The dataset used in this study was 248 examination data of pregnancy check up at the Lawang Health Center from January 2021 to August 2021. The study used 16 attributes in determining the risk, i.e., date of assessment, name of mother, date of HPHT, date of HPL, age, GPA, gestational age, KSPR, KSPR information, BMI, BMI category, reduction, albumin, hepatitis, HIV, and STIs. This study has follow the implementation stages of data collection, design, implementation, testing and data analysis. The highest accuracy for the first test scenario with k=2 is 70.27%. The highest accuracy for the second test scenario with k=3 is 75.68%. The highest accuracy for the third test scenario with k=4 is 78.38%. While the highest accuracy for the fourth test scenario with k=5 is 77.03%. Highest accuracies were achieved with the distribution ratio of 7:3 between training and testing data.
Diabetes pada ibu hamil dapat meningkatkan berbagai risiko, baik maternal maupun neonatus. Terdapat gangguan homeostasis glukosa pada ibu hamil. Terjadinya malformasi kongenital, keguguran, risiko ...preeklampsia, CPD (Cepalo Pelvik Dispropotion), kelahiran prematur, kelainan letak, plasenta previa dan hipoglikemia neonatus. Oleh karena itu, Perhatian dan penanganan menyeluruh bagi ibu hamil yang mengalami diabetes. Data mining dapat digunakan untuk deteksi resiko tinggi diabetus mellitus pada ibu hamil. Data yang digunakan seperti nama, usia, umur kehamilan, gravida, para, riwayat kehamilan yang lalu, riwayat penyakit yang pernah diderita, faktor risiko, riwayat persalinan yang lalu untuk deteksi resiko tinggi diabetus mellitus pada ibu hamil. Tidak semua kehamilan dapat berjalan dengan normal atau fisiologis pada saat proses persalinannya ada faktor risiko yang dapat mempengaruhinya. Pada penelitian ini dapat mendeteksi resiko yang akan terjadi kepada ibu hamil dan bayi dalam kandungannya. Nilai akurasi tertinggi terdapat pada pengujian ke 4 sebesar 82.4324% dan terendah nilai akurasi pada pengujian ke 2 sebesar 75%. Nilai presisi tertinggi terdapat di uji coba ke 3 sebesar 79.2% dan nilai presisi terendah di uji coba ke 2 sebesar 76.3%. Nilai recall tertinggi terdapat di uji coba ke 4 sebesar 82.4% dan nilai recall terendah di uji coba ke 2 sebesar 75%. Nilai F-Measure tertinggi terdapat di uji coba ke 3 sebesar 79.2% dan nilai F-Measure terendah di uji coba ke 2 sebesar 74.8%. AbstractDiabetes in pregnant women can increase various risks, both maternal and neonatal. There is a disturbance of glucose homeostasis in pregnant women. Occurrence of congenital malformations, miscarriage, risk of preeclampsia, CPD (Cepalo Pelvic Disproportion), premature birth, position abnormalities, placenta previa and neonatal hypoglycemia. Therefore, attention and comprehensive treatment for pregnant women with diabetes. Data mining can be used to detect high risk of diabetes mellitus in pregnant women. The data used are name, age, gestational age, gravida, para, past pregnancy history, history of previous illness, risk factors, past delivery history to detect high risk of diabetes mellitus in pregnant women. Not all pregnancies can run normally or physiologically at the time of delivery there are risk factors that can affect it. In this study, it can detect the risks that will occur to pregnant women and their babies in the womb. In addition, recommendations from the system can support a midwife's decision making in taking action to pregnant women. The highest accuracy value is found in the 4th test of 82,4324% and the lowest accuracy value in the 2nd test is 75%. The highest precision value was found in the 3rd trial of 79.2% and the lowest precision value in the 2nd trial of 76.3%. The highest recall value was found in the 4th trial of 82.4% and the lowest recall value in the 2nd trial of 75%. The highest F-Measure value was found in the 3rd trial of 79.2% and the lowest F-Measure value in the 2nd trial of 74.8%.
Data mining dapat diterapkan pada bidang lembaga atau institusi Pendidikan dan sering disebut juga dengan Educational Data Mining (EDM) yaitu sebuah pengembangan metode dalam mengeksplorasi jenis ...tipe data pendidikan yang bersifat unik yang bertujuan untuk mempelajari dalam memahami kinerja siswa dan pengaturan lingkungan di tempat siswa belajar. Data mining juga dapat dimanfaatkan untuk analisa seleksi atribut untuk prediksi kegagalan belajar mahasiswa pada perkuliahan. Salah satunya kegagalan dalam menyelesaikan skripsi dengan menggunakan algoritme naïve bayes. Tahapan penelitian ini dimulai dari pengumpulan data, preproses data, implementasi algoritme naïve bayes, pengujian, dan analisa hasil. Data yang digunakan sebanyak 500 data untuk mahasiswa angkatan 2012-2015 dengan 24 atribut. Akurasi tertinggi yaitu algoritme naive bayes dengan menggunakan data latih yang menunjukkan hasil 412 prediksi benar dengan akurasi sebesar 82.4% dan 88 prediksi salah dengan presentasi sebesar 17.6%. Sedangkan hasil seleksi atribut yang telah dilakukan terdapat Lama P2 merupakan atribut dengan rankinging teratas yang mempengaruhi hasil klasifikasi. Abstract Data mining can be applied to the field of educational institutions or institutions and is often referred to as Educational Data Mining (EDM), which is a method development in exploring unique types of educational data types that aim to study in understanding student performance and environmental settings in which students learn. Data mining can also be used to analyze attribute selection for predicting student learning failure in lectures. One of them is the failure in completing the thesis using the naïve Bayes algorithm. The stages of this research started from data collection, data preprocessing, implementation of the Naïve Bayes algorithm, testing, and analysis of the results. The data used is as much as 500 data for students class 2012-2015 with 24 attributes. The highest accuracy is the Naive Bayes algorithm using data training which shows the results of 412 correct predictions with an accuracy of 82.4% and 88 false predictions with a presentation of 17.6%. Meanwhile, the result of attribute selection that has been carried out is that the Old P2 is the attribute with the top ranking that affects the classification results.
Magang merupakan proses yang penting dalam proses belajar mengajar di SMK. Secara spesifik magang di SMK disebut Prakerin (Praktek Kerja Industri). Penempatan magang harus memerhatikan kompetensi ...siswa, kuota dari perusahaan, kesesuaian jurusan dengan lowongan, dan penghasilan orang tua. Penempatan magang secara manual selama ini memakan waktu, sehingga kurang efisien. Oleh karena itu, penelitian ini fokus mengembangkan aplikasi dengan menerapkan pendekatan Algoritme Genetika untuk mempermudah dalam menentukan penempatan magang dengan menerapkan aturan yang berlaku. Algoritme Genetika dinilai sebagai algoritma yang relevan dan solutif untuk diterapkan dalam penyelesaian masalah optimasi kompleks. Masalah yang dimaksud umumnya adalah masalah yang sulit dilakukan dengan menerapkan metode konvensional. Algoritme Genetika memberikan hasil yang lebih baik untuk setiap iterasi pencarian solusi. Hasil fitness terbaik dengan nilai 0.0014286 diperoleh pada jumlah individu 200, jumlah generasi 200, persentase crossover 50% dan mutasi 10%. Hasil validasi dengan pihak SMK menyatakan bahwa sistem ini mudah untuk digunakan dan bermanfaat bagi pihak SMK, dengan rata-rata persentase kualitas sistem 82,5%. Algoritme Genetika efektif untuk diterapkan pada studi kasus penjadwalan atau penempatan magang yang memiliki karakteristik data yang kompleks. AbstractInternships are an important component of teaching and learning activities in vocational high schools (SMK). Specifically the internship in SMK is called Prakerin (Industrial Work Practice). The internship placement should considering student competence, number of vacancies, the suitability of majors with vacancy, and the income of the parent. During this time, manual internship placement takes more time, so less efficient. Therefore, this research tries to approach using Genetic Algorithm to make it easier in determining the internship placement by applying the applicable rules. The Genetic Algorithm is judged as the right algorithm used in solving complex optimization problems, which is difficult to do by conventional methods. The Genetic Algorithm provides better results for each iteration of the solution search. Best fitness results with value 0.0014286 obtained on the number of individuals 200, the number of generation 200, the percentage of crossover 50% and the mutation 10%. Validation results with the SMK stated that the system is easy to use and beneficial to the SMK, with an average percentage of system quality about 82.5%. Genetic Algorithms are effective to apply to scheduling case studies or internship placements that have complex data characteristics.
ETL scheduling is a challenging and exciting issue to solve. The ETL scheduling problem has many facets, one of which is the cost of time. If it is not handled correctly, it may take a very long time ...to execute and inconsistent data in very large data. In this study using Round-robin algorithm method that proved able to produce efficient results and in accordance with conventional methods. After doing the research, the difference between these two methods is about execution time. Through this experiment, the Round-robin scheduling method gives a more efficient execution time of up to 61% depending on the amount of data and the number of partitions used.
Introduction: Suicide is a significant mental health problem in adolescents around the world that requires comprehensive treatment. This study aimed to examine the relationship between stress, ...anxiety, and depression with suicidal ideation in adolescents. Method: This research used quantitative methods with a cross-sectional approach. The number of respondents was 869 adolescents, with a total sampling technique. The instrument used to measure stress, anxiety, and depression is the Depression Anxiety Stress Scale (DASS-21), while the idea of suicide is measured using the Scale for Suicide Ideation (SSI) instrument. Results: The result of this study showed that teenagers who had suicidal ideation were 206 (23.7%) respondents, while 663 (76.3%) of other respondents did not have the idea of suicide. There was a significant relationship between suicidal ideation with stress levels (p-value 0.000), anxiety (p-value 0.000), and level of depression (p-value 0.000) in adolescents. Conclusion: Mental and psychological health support measures must be given to adolescents to prevent an increase in suicide ideas.
Stres merupakan keadaan dimana seseorang merasakan adanya tekanan yang berlebih pada dirinya. Pemantauan tingkat stres menjadi hal yang penting bagi manusia. Tingkat stres yang tinggi dapat ...menimbulkan dampak negatif terhadap kesehatan manusia. Deteksi dini stres menjadi sesuatu yang sangat penting untuk dilakukan. Salah satu cara mengetahui tingkat stres seseorang adalah melalui analisis teks. Penelitian ini dilakukan untuk melakukan klasifikasi tingkat stres berdasarkan data berupa teks menggunakan algoritma Support Vector Machine (SVM) dan Random Forest. Pada penelitian ini melakukan perbandingan beberapa metode transformasi. Transformasi yang dilakukan pada penelitian ini menggunakan TF-IDF, CountVectorizer, NRCLex, dan Word Affect Intensities. Data yang digunakan dalam penelitian ini berupa sebuat teks berbahasa Inggris yang diambil dari media sosial Twitter. Total data yang digunakan yaitu 8439 data. Pelatihan model baik untuk Support Vector Machine dan Random Forest menggunakan 6751 data. Sedangkan untuk pengujian menggunakan 1688 data. Hasil penelitian menunjukkan bahwa algoritma SVM dengan pembobotan menggunakan TF-IDF memiliki performa yang paling baik dibandingkan dengan algoritma Random Forest dan metode transformasi lainnya yang digunakan dalam penelitian. Model algoritma SVM dengan transformasi TF-IDF yang dibangun berhasil mendapatkan akurasi sebesar 84%. Model ini mendapatkan akurasi yang lebih tinggi dibanding model Random Forest yang memperoleh akurasi tinggi sebesar 80% dengan menggunakan transformasi CountVectorizer.
Abstract
Stress is a condition where a person feels excessive pressure on himself. Monitoring stress levels is important for humans. High levels of stress can have a negative impact on human health. Early detection of stress is something that is very important to do. One way to find out someone's stress level is through text analysis.This research was conducted to classify stress levels based on text data using the Support Vector Machine (SVM) and Random Forest algorithms. This research compares several transformation methods. The transformation performed in this study uses TF-IDF, CountVectorizer, NRCLex, and Word Affect Intensities. The data used in this research is an English text taken from Twitter social media. The total data used is 8439 data. Model training for both Support Vector Machine and Random Forest uses 6751 data. While for testing using 1688 data. The results showed that the SVM algorithm with weighting using TF-IDF had the best performance compared to the Random Forest algorithm and other transformation methods used in the study. The SVM algorithm model with TF-IDF transformation that was built managed to get an accuracy of 84%. This model obtained a higher accuracy than the Random Forest model which obtained a high accuracy of 80% using the CountVectorizer transformation.
Decline in quality caused by daily use of facilities and infrastructure owned by an organization will certainly disrupt its function in supporting the performance of the organization. The solution ...that came from the research that has been conducted before is to develop android applications called Infiremis (Infrastructure and Facility Reporting Management Information System), that can be used to report damage to facilities and infrastructure and to track the status reporting. This android application was developed to be used by students, lecturers and staffs of Faculty of Computer Science Brawijaya University which those users has different background persona. Therefore, the usability of this android application need be tested to find out the value of effectiveness, efficiency and satisfaction of the application to fulfill its purpose. This research was conducted mainly to discover the result of usability testing towards the android application of infrastructure and facility reporting management information system. Based on Usability Testing that has been done show that the level of effectiveness and satisfaction of Infiremis respectively is 97,14% and 89,7%, whereas for the efficiency score is 89,9%.
Education becomes an important thing to advance a nation. Therefore, everyone must follow the education level. One of education level is early childhood education. KB & TK Permata Iman which was ...established in 2005 is a private educational institution and focus on early childhood education. In learning evaluation, KB & TK Permata Iman still use conventional method. The conventional method takes much time because teachers need to collect daily grade until the end of a semester for final grade calculation and prepare the results in grade book. The semester learning evaluation process can be shortened and simplified using a web-based academic assessment management information system. The system can store, directly perform calculations when teachers add students’ grade and make grade book from saved grade. From the testing result, the time efficiency increased to 94.94% when evaluating semester learning using the system and it can help the teacher to save time and do another task.
Students’ learning process analysis normally involves massive amount of data. This study explores the pattern and relationship of students’ learning process data in an interactive learning media ...to identify their learning process patterns to ease the needs of sophisticated data analysis for class instructors and educational researchers. This study focuses on the development of a web-based software application that creates a visual representation of students’ learning process in a learning media. The result of this software is a visualization of students’ activity sequence. This result is then used to infer students’ learning patterns as well as identifying their learning behavior and to create a better feedback via the learning instructors. As a case study, this research uses the data log of Monsakun, a digital learning environment that focuses on the subject of mathematic for grade school students on the topic of arithmetic using story-based question and problem-posing approach. Investigation result shows four distinct learning activity patterns which are: smart pattern, adventure pattern, peer pattern and cyclic pattern. Each pattern requires different feedback to optimize learning progression, by using this web-based application, appropriate feedback to specific learning pattern is then applied to each student based on its learning activity pattern.
PDF
