Claim Missing Document
Check
Articles

Implementasi Clustering Data Kasus Covid 19 Di Indonesia Menggunakan Algoritma K-Means Nofita Sari; Hanny Hikmayanti Handayani; Amril Mutoi Siregar
Bianglala Informatika Vol 11, No 1 (2023): Bianglala Informatika 2023
Publisher : LPPM Universitas Bina Sarana Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/bi.v11i1.14762

Abstract

Covid19 adalah virus pertama kali terdeteksi di Wuhan, Cina pada akhir Desember 2019. Kasus Covid-19 masuk di Indonesia pada Maret 2020, tercatat mencapai 1.511.712 dengan jumlah kematian 40,858 dan sembuh 1.348.330 kasus. Di Indonesia terdapat 34 provinsi yang menjadi persebaran kasus Covid19. Penelitian ini bertujuan untuk mengelompokkan setiap provinsi di Indonesia ke dalam beberapa cluster tertentu agar mengetahui daerah dengan jumlah kasus yang tergolong tinggi, sedang, rendah. Mengelompokan data kasus Covid19 di provinsi Indonesia menggunakan teknik  clustering dengan menggunakan algoritma K-means. Data yang digunakan sebanyak 7098 data dari tanggal 1 Maret hingga 11 Oktober 2020. Dataset yang digunakan dari website AtapData (atapdata.ai). Mengolah data tersebut menggunakan Google Collaboratory dengan bahasa pemrograman python. Pada penelitian dilakukan optimasi menggunakan metode elbow yang menghasilkan jumlah cluster sebanyak 3 cluster. Pengujian dilakukan untuk mendapatkan nilai K yang optimal. Melakukan evaluasi menggunakan Sum of Square Error (SSE). Dari hasil evaluasi memiliki jumlah optimal K: 3 yaitu 228913736548657.56.Kata Kunci : Covid19, algoritma K means, Clustering, Metode ElbowCovid19 is a virus that was first detected in Wuhan, China at the end of December 2019. Covid-19 cases entered Indonesia in March 2020, it was recorded that it had reached 1,511,712 with 40,858 deaths and 1,348,330 cases of recovery. In Indonesia there are 34 provinces where the spread of Covid19 cases. This study aims to classify each province in Indonesia into certain clusters in order to identify areas with high, medium, low number of cases. The grouping of Covid19 case data in the Indonesian province uses a clustering technique using the K-means algorithm. The data used is 7098 data from March 1 to October 11 2020. The dataset used is from the AtapData website (atapdata.ai). Processing the data using Google Collaboratory with the python programming language. In this research, optimization was carried out using the elbow method which resulted in a total of 3 clusters. Tests are carried out to obtain optimal K values. Evaluation using Sum of Square Error (SSE). From the evaluation results, it has an optimal number of K: 3, namely 228913736548657.56.Keywords: Covid19, K mean algorithm, Clustering, Elbow Method
Implementasi Algoritma Logistic Regression Untuk Klasifikasi Penyakit Stroke suhliyyah; Hanny Hikmayanti Handayani; Kiki Ahmad Baihaqi
SYNTAX Jurnal Informatika Vol 12 No 01 (2023): Mei 2023
Publisher : Universitas Singaperbangsa Karawang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35706/syji.v12i01.8329

Abstract

Stroke menyebabkan kerusakan pada bagian otak yang muncul secara mendadak akibat dari gangguan peredaran darah non traumatik. Gangguan tersebut dapat menimbulkan gejala antara lain kelumpuhan seisi wajah atau anggota badan, bicara tidak jelas, bicara tidak lancar, gangguan penglihatan dan perubahan kesadaran. Penyakit stroke merupakan penyakit yang menjadi penyebab kematian nomor tiga tertinggi di indonesia setelah penyakit kanker dan jantung. Di indonesia, jumlah kasus dan prevalensi stroke belum diketahui secara jelas. Diperkirakan 500.000 penduduk terkena stroke setiap tahunnya, sekitar 2,5% atau 12.500 orang meninggal dunia dan sisanya mengalami cacat ringan. Hampir setiap hari, atau minimal rata-rata tiga hari sekali ada seseorang penduduk indonesia baik tua maupun muda meninggal dunia karena serangan penyakit stroke. Penelitian ini dibuat menggunakan metode Confusion matrix dan pengujian menggunakan algoritma Logistic Regression, penelitian ini dilakukan dengan pengumpulan data dan hasil analisis untuk meningkatkan akurasi, berdasarkan variabel berpengaruh meliputi jenis kelamin, hipertensi, penyakit jantung, kadar gula darah, berat badan dan status merokok. Berdasarkan hasil pengumpulan data yang telah dilakukan sebanyak 4981 data diperoleh hasil akurasi sebesar 94%.
Implementasi Model Klasifikasi Jenis Kanker Payudara Menggunakan Algoritma SVM dan Logistic Regression Berbasis Web Nunung Nurjanah; Arphilia Nur Rani; Hanny Hikmayanti Handayani; Anis Fitri Nur Masruriyah
REMIK: Riset dan E-Jurnal Manajemen Informatika Komputer Vol. 7 No. 4 (2023): Volume 7 Nomor 4 Oktober 2023
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/remik.v7i4.12817

Abstract

Menurut Organisasi Kesehatan Dunia (WHO), ada 7 juta pasien kanker payudara, 5 juta di antaranya meninggal setiap tahun. Berdasarkan data Globocan untuk 2018 menunjukkan tingkat kematian rata-rata 17 per 100.000 orang dan insiden 2,1 per 100.000 orang yang menyerang perempuan di Indonesia. Hal itu, menyebabkan kanker payudara ini merusak genetic pada DNA dari sel epitel payudara menjalar ke ductus. Tujuan penelitian ini untuk mengklasifikasi jenis kanker (jinak atau ganas) yang diderita. Perbedaan penelitian sebelumnya dengan penelitian ini adalah metode pengujian algoritma yang dipilih. Pada penelitian ini menggunakan algoritma SVM dan Logistic Regression dengan SMOTE. Beberapa tahapan yang digunakan pada penelitian ini dimulai dengan pengumpulan data, kemudian pre-processing. Selanjutnya implementasi, evaluasi dan deployment pada sistem. Adapun metode K-Fold Cross Validation digunakan pada  penelitian ini untuk melakukan partisi pada data.  Sedangkan evaluasi model menggunakan confusion matrix. Berdasarkan tujuan penelitian, deployment dilakukan menggunakan flask untuk melakukan mengimplementasikan model pada sistem. Adapun metode pengembangan sistem yang digunakan pada penelitian ini yaitu RAD dengan beberapa tahapan. Tahapan dimulai dengan analisis kebutuhan, prototype dan implementasi. Berdasarkan hasil dari penelitian ini menunjukkan bahwa accuracy yang didapat sebesar 1.0, precision 1.0 dan recall 1.0. Selain itu, accuracy yang didapatkan pada sistem yaitu 90%. Maka dari itu, diharapkan berdasarkan hasil penelitian ini dapat membantu tenaga medis untuk mengklasifikasikan jenis kanker payudara, guna melakukan pengobatan secara cepat dan tepat pada penderita penyakit kanker payudara.
Aplikasi Berbasis Web Berdasarkan Model Klasifikasi Algoritma SVM dan Logistic Regression Terhadap Data Diabetes Nita Fitriyani; Dinda Resna Amalia; Hanny Hikmayanti Handayani; Anis Fitri Nur Masruriyah
REMIK: Riset dan E-Jurnal Manajemen Informatika Komputer Vol. 7 No. 4 (2023): Volume 7 Nomor 4 Oktober 2023
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/remik.v7i4.13001

Abstract

Berdasarkan International Diabetes Federation Atlas Tenth edisi 2021, jumlah penderita diabetes mencapai 537 juta orang dalam rentang usia 20-79 tahun. Jumlah penderita diabetes akan terus meningkat mencapai 643 juta pada tahun 2030, bahkan diperkirakan mencapai 783 juta pada tahun 2045. Diabetes tidak hanya menjadi penyebab 6,7 juta kematian, tetapi juga menguras dana kesehatan hingga 966 miliar USD. Tingkat kadar gula darah yang tinggi secara kronis menjadi tanda penyakit diabetes, keadaan ini terjadi ketika tubuh tidak mampu menghasilkan insulin secara efektif. Penelitian ini bertujuan untuk mengembangkan model klasifikasi penderita penyakit diabetes dengan membandingkan dua Algoritma, Support Vector Machine (SVM) dan Regresi Logistik. Dalam penelitian ini, model dievaluasi menggunakan metode K-Fold cross validation dengan membagi dataset menjadi 10 subset. Salah satu subset dipilih sebagai data uji, sementara subset lainnya digunakan sebagai data latih. Hasil penelitian menunjukkan bahwa klasifikasi terbaik diperoleh pada Algoritma SVM dengan teknik SMOTE. Model ini mencapai rata-rata accuracy sebesar 88,77%, precision 88,50%, dan recall 89,21%. Dengan demikian, model yang dikembangkan menggunakan Algoritma SVM dengan SMOTE dapat diimplementasikan ke dalam sebuah sistem klasifikasi penyakit diabetes. Pembuatan aplikasi ini ditujukan kepada pihak medis untuk membantu dalam menguatkan diagnosa pemeriksaan, apakah seseorang menderita penyakit diabetes atau tidak dengan tingkat akurasi yang baik.
Performance Comparison of Support Vector Machine Algorithm and Logistic Regression Algorithm Hanny Hikmayanti; Anis Fitri Nurmasruriyah; Ahmad Fauzi; Nunung Nurjanah; Arphilia Nur Rani
International Journal of Artificial Intelligence Research Vol 7, No 1.1 (2023)
Publisher : STMIK Dharma Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29099/ijair.v7i1.1.1114

Abstract

According to the World Health Organization (WHO), there are around 7 million breast cancer patients each year, with about 5 million of them dying. Based on Globocan 2018 data, the death rate from breast cancer averages 17 per 100,000 people with incidents of 2.1 per 100,000 people attacking women in Indonesia. Hence breast cancer causes spread genetic mutations in the DNA of breast epithelial cells that radiate to the ducts. The purpose of this study was to classify the type of cancer (benign or malignant) that was suffered. The difference between previous research and this research is in the algorithm testing method chosen. In this study the algorithm used is SVM and Logistic Regression by applying the SMOTE technique. The K-fold cross validation method is used in testing this research. The accuracy results obtained are 1.0, precision 1.0 and recall 1.0.While the highest evaluation results for the model without SMOTE were Accuracy 0.97, precision 1.0 and recall 0.90 with the LR method. So based on the results of the comparison, it shows that the evaluation of models using SMOTE tends to be higher than models without SMOTE
Analisis Sentimen Ulasan Aplikasi Identitas Kependudukan Digital Menggunakan Algoritma Logistic Regression dan K-Nearest Neighbor Setiawan, Bagus; Baihaqi, Kiki Ahmad; Nurlaelasari, Euis; Handayani, Hanny Hikmayanti
Building of Informatics, Technology and Science (BITS) Vol 6 No 1 (2024): June 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i1.5389

Abstract

The government has launched the latest innovation in data collection in the realm of population data which relies on digital technology through mobile applications using photos or QR codes which aims to reduce the use of physical prints of identity cards and the availability of blank KTPs with the aim of simplifying the administrative process and no longer requiring population documents. printing or saving in physical format such as an KTP file. In implementing the population identity application, some people feel anxious due to limited internet access, lack of knowledge about the application, as well as concerns about the security and privacy of identity data in digital format. This research aims to conduct sentiment analysis on reviews of digital population identity applications by comparing logistic regression and k-nearest neighbor algorithms. The dataset was taken using the Google Play Scraper library in Python which got 1700 raw data taken from 12-February to 26 March 2024 and then pre-processed and got 1108 clean data. The results of this research show that the comparison between the logistic regression algorithm and k-nearest neighbor algorithm shows that the k-nearest neighbor algorithm is better than the logistic regression algorithm with an accuracy result of 80.43%, a difference of 3.60% compared to k-nearest neighbor. So it can be concluded that the digital population identity application is still considered poor in its use because it has a negative sentiment of 73.9% and it can be seen in this research that the comparison results of the k-nearest neighbor algorithm prove that its performance is better than logistic regression
Implementasi Metode Resampling Dalam Menangani Data Imbalance Pada Klasifikasi Multiclass Penyakit Thyroid Nugraha, Najmi Cahaya; Hikmayanti, Hanny; Indra, Jamaludin; Juwita, Ayu Ratna
Building of Informatics, Technology and Science (BITS) Vol 6 No 2 (2024): September 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i2.5652

Abstract

It is estimated that at least 17 million Indonesians suffer from thyroid disorders. Interestingly, nearly 60% of those living with a thyroid disorder do not receive a diagnosis. Thus, it is necessary to carry out research that applies methods to predict thyroid disease. Before applying prediction methods, it is crucial to implement classification methods to obtain an accurate prediction model. However, to achieve optimal classification results and to avoid inaccuracies, a balance in the used data is required. Data imbalance is a condition where the ratio between classes in the data is uneven, which can result in the generated model becoming biased. The main objective of the research is to present a solution that can improve the accuracy of early detection of thyroid diseases through addressing data imbalance and implementing appropriate classification algorithms. The research methodology began with the collection and analysis of a dataset consisting of 9172 data points. Preprocessing was then performed, resulting in 5321 training data points and 1331 test data points. The testing phase employed 7 different classification algorithms with 7 different resampling methods and evaluation using a confusion matrix. This research achieved the highest accuracy rate of 98%, obtained from the combination of the Random Forest Algorithm and the Random Over Sampling method. It can be concluded that the combination of the Random Forest Algorithm with the Random Over Sampling resampling method can improve early detection accuracy for thyroid diseases.
Prediksi Harga Beras Medium Di Indonesia Dengan Membandingkan Metode Regresi Linear Dan Regresi Polinomial Bilawa, Firdho Akbar; Hikmayanti, Hanny; Rahmat, R
Jurasik (Jurnal Riset Sistem Informasi dan Teknik Informatika) Vol 9, No 2 (2024): Edisi Agustus
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/jurasik.v9i2.810

Abstract

Availability of sufficient and equitable food is one of the pillars of realizing national  food security. Rice, as an important aspect of Indonesian food, has a strategic role and its availability must always be ensured. The majority of Indonesian people’s needs are medium types of rice. The price of medium rice fluctuates, but tends to increase over time. Changes in rice prices have a significant impact on people’s lives and can threaten household food security. Predicting the price of medium rice is very important for the Indonesian government to maintain economic stability. It is hoped that the accurate prediction results can be taken into consideration by the Indonesian government in controlling and determining medium rice price policies in Indonesia. The data used is medium rice price data in Indonesia from January 2013 to February 2024, totaling 134 data. The method used to predict rice prices is the linear regression and polynomial regression methods. This research focuses on the applying and comparing the effectiveness of the two methods by considering their accuracy and error rates.  The accuracy of the prediction results is assessed by calculating the MAPE value.  The research result show that both methods have accurate prediction model performance because the MAPE value is less than 10%. The linear regression method can predict the medium rice price more accurately because it has a smaller MAPE value of 6,29%, compared to the polynomial regression method of  6,88%.
SENTIMENT ANALYSIS OF THE SAMBARA APPLICATION USING THE SUPPORT VECTOR MACHINE ALGORITHM Firdaus, Thoriq Janati; Indra, Jamaludin; Lestari, Santi Arum Puspita; Hikmayanti, Hanny
Jurnal Teknik Informatika (Jutif) Vol. 5 No. 4 (2024): JUTIF Volume 5, Number 4, August 2024
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2024.5.4.2673

Abstract

Rapid technological developments have opened up new opportunities for public services by utilizing digital application innovations. One example is the West Java Samsat Mobile (SAMBARA) designed by the West Java Provincial Revenue Agency (BAPENDA). The SAMBARA application is expected to accelerate annual vehicle tax payment obligations, but several reviews on the Playstore show user dissatisfaction with SAMBARA's performance. This study aims to conduct a sentiment analysis of SAMBARA application reviews using the Support Vector Machine algorithm. SAMBARA user review data on Google Playstore was collected using the python programming language google play scraper library on google colabolatory resulting in 1620 data on January 2, 2024. The data pre-processing stage involves various steps such as data cleaning, lowercase conversion, tokenization, stemming, stop words removal, normalization, and the use of the TF-IDF method. The data is then labeled positive and negative, positive for reviews with scores of 4 and 5 and negative labels for reviews with scores of 1 to 3. The Support Vector Machine (SVM) algorithm is used for classification, a well-known method for accurate classification. Model evaluation was conducted using a confusion matrix to calculate the precision, recall, and F1-Score values. The evaluation results provide an overview of the performance of the classification algorithm in grouping user reviews into positive and negative categories. The evaluation results show that the SVM algorithm provides quite good performance with an accuracy value of 88.75%, precision 87.51%, recall 81.25%, and F1-Score 83.71% which can be the basis for improving the quality of service of the SAMBARA application. Because the Sambara application has a negative sentiment of 73.4%, it can be concluded that it still gets a bad rating in terms of use.
Development of Health Mask Identification Using YOLOv5 Architecture Fauzi, Ahmad; Ajie, Prasetyo; Nur Masruriyah, Anis Fitri; Wahiddin, Deden; Hikmayanti, Hanny; Hananto, April Lia
International Journal of Artificial Intelligence Research Vol 6, No 1.1 (2022)
Publisher : STMIK Dharma Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29099/ijair.v6i1.1.573

Abstract

Coronavirus Disease 2019 (COVID-19) causes the state to suffer losses, especially in the health sector. WHO calls for controlling COVID-19 with health protocols that must be obeyed, one of which is wearing a mask. The use of masks can reduce the transmission of COVID-19. But there are still many people who ignore the protocol to use masks properly. So a system was created to detect the use of masks properly using the YOLOv5 architecture. Aiming to help regulate the use of masks in public areas or open places. The process of this research begins with data collection in the form of images. The collected image data will later be used as a dataset and model training will be carried out using the YOLOv5s model. The accuracy results obtained from this study reached 90.37%