Winda Aprianti
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Winda Aprianti has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Herfia Rhomadhona
Politeknik Negeri Tanah Laut
2 shared publications - Hendrik Setyo Utomo
Politeknik Negeri Tanah Laut
1 shared publication - Imam Mukhlash
Department of Mathematics, Institut Teknologi Sepuluh Nopember, Surabaya, Indonesia
1 shared publication - Jaka Permadi
Politeknik Negeri Tanah Laut
1 shared publication - Jaka Permadi
Politeknik Negeri Tanah Laut
1 shared publication Khairul Anwar Hafizd
Politeknik Negeri Tanah Lauti
1 shared publication
Latest Publications
- Open Access
- 22 January 2022
- Published by Universitas Muhammadiyah Mataram in JTAM (Jurnal Teori dan Aplikasi Matematika)
- Vol. 6 (1) , 10-21
Prediction Active Case of Covid-19 with ERNN
SARS-CoV-2 is known as Covid-19 has been spread in all world since end of 2019. Indonesia, including South Kalimantan has detected first Covid-19 in March 2020. This pandemic has affected in all entirely live in Indonesia. This makes Covid-19 be the main focus of the government. The government has provided aid and imposed restrictions on activities. These policies require planning that can be a solution. Careful planning requires an overview of the data on active cases that are positive for Covid-19. This overview can be obtained through prediction. In this research, Elman Recurrent Neural Network (ERNN) was used to predict active cases of Covid-19. Architecture of ERNN was used ERNN with 3 input nodes, 2 hidden nodes, and 2 context nodes. The data used is 277 data, which is then divided into training data and testing data, respectively 90%-10%, 80%-20%, and 70%-30%. ERNN with a learning rate of 0.1 until 0.9 is applied to data on active cases of Covid-19, then Mean Absolute Percentage Error (MAPE) is calculated to find out performance of model generated by ERNN. The results showed that all of MAPE were below 10% with the smallest MAPE as 3.21% for scenario 90:10 and learning rate 0.6. MAPE value which is less than 10% indicates that ERNN has very good predictive ability.
- 22 January 2022
- Published by Universitas Muhammadiyah Mataram in JTAM (Jurnal Teori dan Aplikasi Matematika)
- Vol. 6 (1) , 10-21
Open AccessPrediction Active Case of Covid-19 with ERNN
SARS-CoV-2 is known as Covid-19 has been spread in all world since end of 2019. Indonesia, including South Kalimantan has detected first Covid-19 in March 2020. This pandemic has affected in all entirely live in Indonesia. This makes Covid-19 be the main focus of the government. The government has provided aid and imposed restrictions on activities. These policies require planning that can be a solution. Careful planning requires an overview of the data on active cases that are positive for Covid-19. This overview can be obtained through prediction. In this research, Elman Recurrent Neural Network (ERNN) was used to predict active cases of Covid-19. Architecture of ERNN was used ERNN with 3 input nodes, 2 hidden nodes, and 2 context nodes. The data used is 277 data, which is then divided into training data and testing data, respectively 90%-10%, 80%-20%, and 70%-30%. ERNN with a learning rate of 0.1 until 0.9 is applied to data on active cases of Covid-19, then Mean Absolute Percentage Error (MAPE) is calculated to find out performance of model generated by ERNN. The results showed that all of MAPE were below 10% with the smallest MAPE as 3.21% for scenario 90:10 and learning rate 0.6. MAPE value which is less than 10% indicates that ERNN has very good predictive ability.
- Open Access
- 31 July 2021
- Published by Yayasan Lavandaia Dharma Bali in Jurnal Widya Laksmi: Jurnal Pengabdian Kepada Masyarakat
- Vol. 1 (2) , 55-61
PELATIHAN PENGGUNAAN GOOGLE CLASSROOM DAN GOOGLE MEET SEBAGAI MEDIA PEMBELAJARAN DARING DI MASA PANDEMI
SDS Waladun Sholeh merupakan salah satu sekolah swasta di Kabupaten Tanah Laut yang terdampak virus Covid-19, sehingga kegiatan belajar mengajar harus dilakukan secara online atau daring (dalam jaringan) dengan memanfaatkan teknologi komputer yang dilengkapi jaringan internet. Hal tersebut bertujuan agar materi pembelajaran tersampaikan dengan baik kepada peserta didik. Metode pelaksanaan pengabdian terdiri dari 3 (tiga) tahapan yaitu tahapan persiapan berupa koordinasi dengan panitia SDS, tahapan pelaksanaan berupa pelatihan penggunaan 2 (dua) aplikasi pembelajaran besutan google yaitu google meet dan google classroom dan yang terakhir tahapan evaluasi. Pada tahapan evaluasi peserta diminta untuk mengisi kuisioner sebelum dan sesudah pelatihan, hal ini dilakukan agar panitia pengabdian dapat mengetahui tingkat pemahaman dan keterampilan peserta dalam menggunakan google meet dan google classroom. Berdasarkan hasil evaluasi tersebut terlihat peningkatan pemahaman dan keterampilan peserta dimana rata-rata nilai peserta sebelum pelatihan adalah 59.8 sedangkan setelah pelatihan dilakukan rata-rata nilai peserta meningat menjadi 91.42.
- 31 July 2021
- Published by Yayasan Lavandaia Dharma Bali in Jurnal Widya Laksmi: Jurnal Pengabdian Kepada Masyarakat
- Vol. 1 (2) , 55-61
Open AccessPELATIHAN PENGGUNAAN GOOGLE CLASSROOM DAN GOOGLE MEET SEBAGAI MEDIA PEMBELAJARAN DARING DI MASA PANDEMI
SDS Waladun Sholeh merupakan salah satu sekolah swasta di Kabupaten Tanah Laut yang terdampak virus Covid-19, sehingga kegiatan belajar mengajar harus dilakukan secara online atau daring (dalam jaringan) dengan memanfaatkan teknologi komputer yang dilengkapi jaringan internet. Hal tersebut bertujuan agar materi pembelajaran tersampaikan dengan baik kepada peserta didik. Metode pelaksanaan pengabdian terdiri dari 3 (tiga) tahapan yaitu tahapan persiapan berupa koordinasi dengan panitia SDS, tahapan pelaksanaan berupa pelatihan penggunaan 2 (dua) aplikasi pembelajaran besutan google yaitu google meet dan google classroom dan yang terakhir tahapan evaluasi. Pada tahapan evaluasi peserta diminta untuk mengisi kuisioner sebelum dan sesudah pelatihan, hal ini dilakukan agar panitia pengabdian dapat mengetahui tingkat pemahaman dan keterampilan peserta dalam menggunakan google meet dan google classroom. Berdasarkan hasil evaluasi tersebut terlihat peningkatan pemahaman dan keterampilan peserta dimana rata-rata nilai peserta sebelum pelatihan adalah 59.8 sedangkan setelah pelatihan dilakukan rata-rata nilai peserta meningat menjadi 91.42.
- Open Access
- 30 October 2018
- Published by Fakultas Ilmu Komputer Universitas Brawijaya in Jurnal Teknologi Informasi dan Ilmu Komputer
- Vol. 5 (5) , 613-620
K-Means Clustering untuk Data Kecelakaan Lalu Lintas Jalan Raya di Kecamatan Pelaihari
Kecelakaan lalu lintas di jalan raya masih menjadi penyumbang tingginya angka kematian di Indonesia, sehingga menjadi perhatian khusus bagi kepolisian di negara ini. Termasuk Kepolisian Resor (Polres) Tanah Laut, yang telah membuktikan perhatian tersebut dengan membentuk komunitas korban kecelakaan lalu lintas dan Pelatihan Pertolongan Pertama Gawat Darurat (PPGD). Tahapan awal pencegahan kecelakaan lalu lintas adalah dengan mengetahui faktor-faktor penyebab kecelakaan lalu lintas yang diperoleh melalui analisa data kecelakaan. Analisa tersebut dapat dilakukan dengan data mining, yaitu K-Means Clustering. K-Means Clustering mengelompokkan data menjadi beberapa cluster sesuai karakteristik data tersebut. Data kecelakaan lalu lintas dibagi menjadi 2 dataset, yakni dataset 1 dan dataset 2. Hasil cluster penerapan K-means clustering terhadap dataset 1 dan dataset 2 kemudian dilakukan pengujian silhoutte coefficient untuk mencari hasil cluster dengan kualitas terbaik. Pengujian silhoutte coefficient secara berurutan menghasilkan distance measure paling optimal yakni clustering dengan 4 cluster untuk dataset 1 dan clustering dengan 2 cluster untuk dataset 2. Selain memperoleh cluster dengan kualitas terbaik, penganalisaan data juga menghasilkan beberapa informasi kecelakaan lalu lintas yang sering terjadi, yakni faktor penyebab dan korban kecelakaan adalah pengemudi, umur korban adalah 9 sampai 28 tahun, dan keadaan korban kecelakaan adalah luka ringan. AbstractTraffic accidents on the highway are still contribute to the high mortality rate in Indonesia, which are becoming a special concern for the police. Including the Police of Tanah Laut Resort where prove themselves by established The Community of Traffic Accident Victims and Emergency First Aid Training. The first prevention of traffic accidents is knowing the factors causing traffic accidents which is obtained through the analysis of traffic accident’s data. It can be done through data mining, i.e. K-Means Clustering, which is clustering data into clusters according to characteristics of the data. Traffic accident data is divided into two datasets, namely dataset 1 and dataset 2. After obtaining the cluster results, the next step is to calculate silhoutte coefficient which is used to find the best quality cluster result. The result of testing silhoutte coefficient are clustering with 4 clusters for dataset 1 and clustering with 2 clusters for dataset 2. Analyzing data in this research also produces some information on traffic accidents that often occur, namely the causes and victims of accidents are drivers, the age of the victims is between 9 and 28 years old, and the circumstance of the accidents victims are minor injuries.
- 30 October 2018
- Published by Fakultas Ilmu Komputer Universitas Brawijaya in Jurnal Teknologi Informasi dan Ilmu Komputer
- Vol. 5 (5) , 613-620
Open AccessK-Means Clustering untuk Data Kecelakaan Lalu Lintas Jalan Raya di Kecamatan Pelaihari
Kecelakaan lalu lintas di jalan raya masih menjadi penyumbang tingginya angka kematian di Indonesia, sehingga menjadi perhatian khusus bagi kepolisian di negara ini. Termasuk Kepolisian Resor (Polres) Tanah Laut, yang telah membuktikan perhatian tersebut dengan membentuk komunitas korban kecelakaan lalu lintas dan Pelatihan Pertolongan Pertama Gawat Darurat (PPGD). Tahapan awal pencegahan kecelakaan lalu lintas adalah dengan mengetahui faktor-faktor penyebab kecelakaan lalu lintas yang diperoleh melalui analisa data kecelakaan. Analisa tersebut dapat dilakukan dengan data mining, yaitu K-Means Clustering. K-Means Clustering mengelompokkan data menjadi beberapa cluster sesuai karakteristik data tersebut. Data kecelakaan lalu lintas dibagi menjadi 2 dataset, yakni dataset 1 dan dataset 2. Hasil cluster penerapan K-means clustering terhadap dataset 1 dan dataset 2 kemudian dilakukan pengujian silhoutte coefficient untuk mencari hasil cluster dengan kualitas terbaik. Pengujian silhoutte coefficient secara berurutan menghasilkan distance measure paling optimal yakni clustering dengan 4 cluster untuk dataset 1 dan clustering dengan 2 cluster untuk dataset 2. Selain memperoleh cluster dengan kualitas terbaik, penganalisaan data juga menghasilkan beberapa informasi kecelakaan lalu lintas yang sering terjadi, yakni faktor penyebab dan korban kecelakaan adalah pengemudi, umur korban adalah 9 sampai 28 tahun, dan keadaan korban kecelakaan adalah luka ringan. AbstractTraffic accidents on the highway are still contribute to the high mortality rate in Indonesia, which are becoming a special concern for the police. Including the Police of Tanah Laut Resort where prove themselves by established The Community of Traffic Accident Victims and Emergency First Aid Training. The first prevention of traffic accidents is knowing the factors causing traffic accidents which is obtained through the analysis of traffic accident’s data. It can be done through data mining, i.e. K-Means Clustering, which is clustering data into clusters according to characteristics of the data. Traffic accident data is divided into two datasets, namely dataset 1 and dataset 2. After obtaining the cluster results, the next step is to calculate silhoutte coefficient which is used to find the best quality cluster result. The result of testing silhoutte coefficient are clustering with 4 clusters for dataset 1 and clustering with 2 clusters for dataset 2. Analyzing data in this research also produces some information on traffic accidents that often occur, namely the causes and victims of accidents are drivers, the age of the victims is between 9 and 28 years old, and the circumstance of the accidents victims are minor injuries.
- Open Access
- 6 December 2017
- Published by Lembaga Penelitian dan Pengabdian kepada Masyarakat ITS in Limits: Journal of Mathematics and Its Applications
- Vol. 14 (2) , 57
Implementasi Association Rules dengan Algoritma Apriori pada Dataset Kemiskinan
Usaha pengentasan kemiskinan terus dilakukan di Kabupaten Tanah Laut. Untuk membantu pemerintah dalam perumusan kebijakan pengentasan kemiskinan maka diperlukan pengetahuan mengenai indikator yang berkaitan dengan kemiskinan dan bagaimana indikator-indikator tersebut saling mempengaruhi. Tujuan penelitian ini adalah menerapkan Association rules dengan algoritma Apriori pada dataset kemiskinan untuk mencari pola hubungan antar indikator. Dataset yang terdiri dari 46 atribut merupakan data sekunder BPS Kabupaten Tanah Laut dan BPS Provinsi Kalimantan Selatan tahun 2010-2014. Hasil penerapan association rules dengan algoritma apriori menggunakan minimum support 30% dan minimum confidence 80% menghasilkan 4614 rules hubungan antar indikator.
- 6 December 2017
- Published by Lembaga Penelitian dan Pengabdian kepada Masyarakat ITS in Limits: Journal of Mathematics and Its Applications
- Vol. 14 (2) , 57
Open AccessImplementasi Association Rules dengan Algoritma Apriori pada Dataset Kemiskinan
Usaha pengentasan kemiskinan terus dilakukan di Kabupaten Tanah Laut. Untuk membantu pemerintah dalam perumusan kebijakan pengentasan kemiskinan maka diperlukan pengetahuan mengenai indikator yang berkaitan dengan kemiskinan dan bagaimana indikator-indikator tersebut saling mempengaruhi. Tujuan penelitian ini adalah menerapkan Association rules dengan algoritma Apriori pada dataset kemiskinan untuk mencari pola hubungan antar indikator. Dataset yang terdiri dari 46 atribut merupakan data sekunder BPS Kabupaten Tanah Laut dan BPS Provinsi Kalimantan Selatan tahun 2010-2014. Hasil penerapan association rules dengan algoritma apriori menggunakan minimum support 30% dan minimum confidence 80% menghasilkan 4614 rules hubungan antar indikator.
- 1 November 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
The application of rough set and fuzzy rough set based algorithm to classify incomplete meteorological data
Weather has an important role in people's lives, such as agriculture, economics, socio-economic, disaster management, and finance. So, weather prediction is very important to be considered. In the prediction process we are often faced with the problem of data incompleteness. Therefore, it needs a proper classification algorithm that able to handle incomplete attribute values in the training data. In this paper, we use two approaches to handle incomplete data, namely are rough set and fuzzy rough set based algorithms. To test the performance of the two algorithms, we use meteorological data to classify rain or dry season. Conclusion of the study showed that the rough set approach is more efficient than the fuzzy rough sets approach. The advantage of fuzzy rough set approach can predict all the conditions that may occur, which can't be done by the rough set approach.
- 1 November 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
The application of rough set and fuzzy rough set based algorithm to classify incomplete meteorological data
Weather has an important role in people's lives, such as agriculture, economics, socio-economic, disaster management, and finance. So, weather prediction is very important to be considered. In the prediction process we are often faced with the problem of data incompleteness. Therefore, it needs a proper classification algorithm that able to handle incomplete attribute values in the training data. In this paper, we use two approaches to handle incomplete data, namely are rough set and fuzzy rough set based algorithms. To test the performance of the two algorithms, we use meteorological data to classify rain or dry season. Conclusion of the study showed that the rough set approach is more efficient than the fuzzy rough sets approach. The advantage of fuzzy rough set approach can predict all the conditions that may occur, which can't be done by the rough set approach.