Bangsal Village is in the South Sumatra region within the district of Pampangan Ogan Komering Ilir. The village has potential including buffalo milk, sugar puan, sagon, penjem (a kind of yoghurt), curd (a kind of butter for cooking oil), smoked-fish, fish-crackers and swamp-rice with high iron mineral (Fe). Majority of Bangsal villagers are buffalo breeders. The potential possessed by Bangsal Village can be expected to make the villages has food sovereignty, economic independence and local wisdom in culture. The Computer and Information Technology (ICT) is one of the tools to develop Website. The Website can be a media for promotion of potentials and products owned by Bangsal Village. Everyone can easily search for information and knowledge about the village without having to go directly to the village. The development of the village Website requires an active role from the Bangsal Village community and community itself. Website management training has given to several village community participants with good results. These can be seen from the ability of participants to complete more than 70% of the tasks given by the trainer.Abstrak Desa Bangsal merupakan wilayah Sumatera Selatan yang berada dalam kabupaten Ogan Komering Ilir Kecamatan Pampangan. Desa Bangsal Memiliki Potensi yang sangat baik diantaranya susu kerbau, gula puannya, sagon, penjem (semacam yoghurt), dadih (semacam mentega untuk minyak goreng), ikan asap, kerupuk ikan dan padi rawa yang termasuk beras yang kaya zat besi (Fe). Selain itu hampir mayoritas masyarakat desa adalah peternak kerbau. Potensi yang dimiliki oleh Desa Bangsal bila dikembangkan, maka diharapkan dapat menjadikan desa sebagai salah satu desa yang memiliki kedaulatan pangan, kemandirian ekonomi dan kearifan lokal sebagai kepribadian dalam budaya. Pengembangan potensi desa yang dapat dilakukan adalah memanfaatkan Teknologi Komputer dan Informasi melalui pengembangan website desa. Website desa dapat menjadi media promosi potensi dan produk yang dimiliki Desa Bangsal. Semua orang dapat dengan mudah mencari informasi dan mengenal desa tanpa harus langsung ke desa melalui website. Pengembangan website Desa Bangsal memerlukan peranan aktif dari perangkat dan masyarakat desa. Pelatihan pengembangan dan pengelolaan website yang diberikan ke masyarakat desa menunjukkan hasil yang baik, terlihat dari tugas yang diberikan 70% dari dapat diselesaikan dengan baik.
<span id="docs-internal-guid-cd6caed5-7fff-5f99-0341-cb32fa5ad787"><span>The imbalanced data affect the accuracy of models, especially for precision and sensitivity, it makes difficult to find information on minority class. The problem is identified in the tracer study dataset Universitas Sriwijaya that has 2934 data. The label attribute is divided into several label classes, namely not tight, somewhat-tight, tight, very tight, and tightest. The number of the tightest and very tight is 27% and 38.6% of the number majority classes. In the study, the SMOTE is combined with eliminating the missing value of data to handle the imbalanced data. The method was evaluated by the classification methods KNN, ANN, and C4.5. The results of these methods show a significant increase in accuracy as a whole and a significant increase in the precision and sensitivity of minority classes. The precision and sensitivity of both the majority and minority are not too different, although the number of the minority is very less compared to the majority class. the information on minority classes can be obtained with quite high precision and sensitivity. As a conclusion, the proposed method is passably to improve accuracy and greatly affects the increase in sensitivity and precision.</span></span>
<p align="justify"><em>Educational data mining</em> (EDM) adalah suatu bidang aplikasi antara pendidikan dan komputer. Salah satu yang dapat dilakukan pada EDM adalah memprediksi tingkat prestasi mahasiswa. Tingkat indeks prestasi kumulatif (IPK) akademik mahasiswa sangat penting karena menentukan tingkat kelulusan dan kualiatas institusi pendidikan. Penelitian ini bertujuan untuk menganalisa atribut-atribut yang mempengaruhi tingkat indeks prestasi kumulatif (IPK) mahasiswa yang berasal dari faktor eksternal pada mahasiswa. Adapun atribut yang digunakan adalah 10 variabel atribut yaitu nilai TOEFL, pendidikan ayah, pendidikan ibu, pekerjaan ayah, pekerjaan ibu, asal daerah, tempat tinggal selama kuliah dan tingkat prestasi akademik yang dicapai. Hasil akurasi pengolahan dengan menggunakan Algoritma C4.5 adalah 75,18% dan <em>Naive Bayes</em> 74,47% menunjukkan bahwa model dan atribut yang digunakan baik untuk memprediksi tingkat IPK mahasiswa. Algoritma C4.5 mampu menunjukkan atribut apa yang berpengaruh langsung pada tingkat IPK mahasiswa yaitu Nilai TOEFL, jam belajar, pendidikan ayah, pekerjaan ayah, dan tempat tinggal mahasiswa. Algoritma C4.5 tidak mampu memperhitungkan peluang suatu klasifikasi jika jumlah instan pada klasifikasi tersebut sangat sedikit pada kejadian data. Sebaliknya <em>Naive Bayes</em> tetap mampu memperhitungkan peluang kemunculan dan ketepatannya informasi yang dihasilkan meski jumlah instan yang sedikit. Dalam penelitian ini data mahasiswa yang memiliki tingkat IPK <em>cumlaude</em> sangat sedikit, namun <em>Naive Bayes</em> tetap mampu mengukur <em>Recall</em> pada kelas ini sebesar 28,6% dan <em>Precision</em> sebesar 40%. </p>
The study period pattern of student can facilitate the stakeholders to improve education services in their institutions. This study investigated the study period pattern of the graduated students from January 2014 until February 2018 with the C4.5 algorithm. The obtained data from three academic years 2011, 20112, and 2013 is 140 students with 18 frequently repeated subjects. The total attributes that used in the study are 19 attributes. These attributes contain 18 frequently repeated subject and one attribute for the label is from the study period of a student (punctual or not punctual). This study used the method of K-fold cross-validation with K = 10 and the percentage split with the percentage is 66% to measure the performance of the algorithm C4.5. The results of both methods showed that the subjects that affect sequentially in the study period of the student are a complex function, numerical methods, introduction to computer science, computer programs and basic physics. The accuracy of the results obtained from both the training process K-fold cross-validation amounted to 84.29% and 72.92% for percentage split. It shows that algorithm C4.5 is quite well in predicting the pattern of the study period of a student majoring in mathematics, Department of Universitas Sriwijaya.
The Traveling Salesman Problem (TSP) is very well known as one of the optimization problems of circuit of Hamiltonian , which will seek for the shortest route that must be passed by a number of city salesmen exactly once and will return to the initial city. Genetic Algorithm (GA) and Simulated Annealing (SA) are one method that can be used in TSP case. Fertilizer distribution at PT. Sahabat Mewah dan Makmur (SMM) in Belitung which is one of the branches of PT. Austindo Nusantara Jaya Group does not yet have an optimal fertilizer distribution schedule, where when fertilizer will be distributed from the starting point of distribution to the location of storage warehouses, it is not determined which location points will receive delivery, shipments are made to warehouse locations that still have enough storage space or stacked in the nearest warehouse. PT.SMM distributes fertilizer from Port of Tanjung Pandan to warehouses in Jangkang, Balok, Ladang Jaya, Sari Bunga, and Aik Ruak. The results show that in the GA of 120 routes, there are 8 routes with a distance of 175 km; In SA, the shortest distance is equal to GA, which is 175 km.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.