Jurnal Komputasi最新文献

{"title":"https://jurnal.fmipa.unila.ac.id/komputasi/issue/view/146/showToc","authors":"Aisyah Nur Fahira, Rani Nooraeni","doi":"10.23960/komputasi.v11i1.3175","DOIUrl":"https://doi.org/10.23960/komputasi.v11i1.3175","url":null,"abstract":"Spatio Temporal DBSCAN (ST-DBSCAN) adalah metode yang dapat diterapkan pada data spasial yang diikuti dengan atribut temporal. Hasil dari ST-DBSCAN tergantung pada penentuan awal tiga parameter. Inisial parameter yang tidak optimal menyebabkan hasil pengelompokan dengan ST-DBSCAN tidak mencapai solusi yang global optimum. Penelitian ini bertujuan untuk mengoptimalkan penentuan parameter awal pada ST-DBSCAN menggunakan metode k Nearest neighborhood dan Algoritma Genetika yang diuji menggunakan data simulasi kemudian diterapkan dalam pengelompokan wilayah bencana alam. Hasil yang didapatkan adalah pemilihan parameter yang dioptimasi menggunakan algoritma genetika menghasilkan cluster dengan koefisien CDBw terbesar pada perbandingan evaluasi, akan tetapi perlu waktu yang lama untuk merunning sehingga metode tersebut diuji coba dengan data dengan jumlah observasi sedikit. Hasil dari implementasi metode terhadap data bencana alam menunjukkan terdapat 22 cluster","PeriodicalId":292117,"journal":{"name":"Jurnal Komputasi","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114448046","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Comparison Algorithm for Diabetes Classification with Consideration of Mutual Information and Information Feature","authors":"Rahmat Ramadhani, T. H. Saragih, Muhammad Itqan Mazdadi, M. Muliadi","doi":"10.23960/komputasi.v11i1.6649","DOIUrl":"https://doi.org/10.23960/komputasi.v11i1.6649","url":null,"abstract":"Diabetes is a prevalent disease in humans that is caused by excessive sugar levels in the body. If left untreated, it can lead to severe consequences such as paralysis, decay in certain parts of the body, and even death. Unfortunately, early detection of diabetes is difficult, and many cases go untreated until it is too late. However, the development of technology has opened up new possibilities for early detection and treatment of diabetes. One such approach is classification, a commonly used method in the field of Computer Science. Classification is used in various fields, including health, agriculture, and animal diseases, to draw conclusions based on input data using cause-and-effect relationships. Many different learning concepts and methods can be used in classification, with the Decision Tree concept being one of the most popular examples. This study compares several classification methods, including Decision Tree, Random Forest, AdaBoost, and Stochastic Gradient Boost, with feature selections carried out using MI and IF. The study aims to evaluate the effectiveness of these methods and the influence of feature selection on improving their performance. Based on the results of the study, it can be concluded that feature selection using Mutual Information and Importance Feature can improve the classification accuracy in some methods, particularly in Random Forest, AdaBoost, and Stochastic Gradient Boost. However, the Decision Tree algorithm did not show any improvement in accuracy after feature selection. The best classification accuracy was achieved with the Stochastic Gradient Boost method using the original dataset without feature selection, while the Random Forest method showed the highest accuracy after using all the features. Overall, the results suggest that feature selection can be a useful technique for improving the performance of classification algorithms in diabetes prediction. The study suggests that future research could investigate other classification methods, such as Neural Network or Deep Learning, and use optimization algorithms like Genetic Algorithm or Particle Swarm Optimization to improve feature selection results.","PeriodicalId":292117,"journal":{"name":"Jurnal Komputasi","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132362542","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"RANCANG BANGUN SISTEM INFORMASI REKAM MEDIS DAN SKRINING BERBASIS WEB (Studi Kasus : Wisma Ataraxis)","authors":"Astria Hijriani, Yohana Tri Utami, N. Marlon, Anisa Raden","doi":"10.23960/komputasi.v11i1.2959","DOIUrl":"https://doi.org/10.23960/komputasi.v11i1.2959","url":null,"abstract":"Wisma Ataraxis adalah Institusi Penerima Wajib Lapor (IPWL) Sosial oleh Kementerian Sosial untuk memberikan pelayanan rehabilitasi. Dalam melaksanakan kegiatan operasionalnya Wisma Ataraxis masih menggunakan cara konvensional untuk mengelola berkas rehabilitan. Banyaknya data yang harus diisi dalam penerimaan rehabilitas dan redundansi data menjadi kekurangan dalam kegiatan ini. Selain itu, pencarian berkas untuk rehabilitan yang akan melakukan rehabilitasi ulang membutuhkan waktu cukup lama karena banyaknya berkas yang ada. Dari permasalahan tersebut maka diusulkan untuk pembangunan sebuah sistem yang dapat membantu petugas dalam kegiatan operasionalnya. Dalam rancang bangun sistem informasi rekam medis dan skrining berbasis website untuk Wisma Ataraxis ini menggunakan metode prototyping. Dari hasil pengujian yang telah dilakukan, pihak Wisma Ataraxis telah menerima sistem sesuai dengan kebutuhan pengguna. Serta kesimpulan rancang bangun sistem ini dapat memberikan kemudahan pada petugas Wisma Ataraxis dalam proses penerimaan rehabilitan dan skrining.","PeriodicalId":292117,"journal":{"name":"Jurnal Komputasi","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134213659","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Implementasi Sistem Informasi E-Campaign Pemilihan Kepala Desa","authors":"Reda Meiningtiyas, Rico Andrian, Dedy Hermawan, D. Kurniawan","doi":"10.23960/komputasi.v11i1.6615","DOIUrl":"https://doi.org/10.23960/komputasi.v11i1.6615","url":null,"abstract":"Campaign are activities carried out to gain public support for potential candidates and convince them to vote for the candidate. Lack of information about the campaigns carried out by the candidates, the dissemination of information through online media. E-campaign is defined as the use of technology by prospective candidates in attracting public trust and assisting in the democratic process. The village head election e-campaign information system was built to help the community get correct information about candidates, make it easier for candidates in the campaign process and the process of collecting village head election requirements data, and make it easier for administrators to collect village head election requirements data. The system development uses the PHP programming language and the Laravel framework. The system development methodology uses the waterfall method. The waterfall method has 5 stages, namely communication, planning, moodelling, construction, and modeling. System testing is done by black box testing and User Acceptance Testing (UAT). The results of the black box testing that have been carried out on the test class are presented successfully or unsuccessfully. The results of the User Acceptance Testing (UAT) that have been carried out have obtained a percentage of 81.2% which can be concluded that the e-campaign information system from user perceptions is very good.","PeriodicalId":292117,"journal":{"name":"Jurnal Komputasi","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122959976","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Perbandingan Ekstraksi Fitur dengan Pembobotan Supervised dan Unsupervised pada Algoritma Random Forest untuk Pemantauan Laporan Penderita COVID-19 di Twitter","authors":"Sulastri Norindah Sari, M. Faisal, Dwi Kartini, I. Budiman, Triando Hamonangan Saragih, Muliadi","doi":"10.23960/komputasi.v11i1.6650","DOIUrl":"https://doi.org/10.23960/komputasi.v11i1.6650","url":null,"abstract":"Dimasa sekarang masyarakat sudah berani melaporkan dirinya terpapar COVID-19 melalui unggahan di media sosial seperti Twitter. Hal ini dapat dimanfaatkan oleh masyarakat sekitar atau lembaga kesehatan untuk memberikan bantuan terhadap pelapor. Pemantauan laporan penderita COVID-19 di Twitter dapat dilakukan secara otomatis dengan algoritma machine learning untuk klasifikasi teks. Pada kasus klasifikasi teks, algoritma machine learning menerima input berupa data terstruktur hasil ekstraksi fitur dengan teknik unigram dengan pembobotan. Metode pembobotan kata unsupervised merupakan pembobotan yang tidak memperhatikan letak term di kelas positif atau negatif. Kemudian metode pembobotan ini dikembangkan menjadi pembobotan supervised, karena dalam proses pembobotannya metode ini membobotkan term dengan memperhatikan letak term di kelas positif atau negatif. Pada riset ini dilakukan perbandingan kedua jenis pembobotan pada klasifikasi data tweet gejala covid dengan algoritma machine learning yaitu Random Forest. Dari hasil penelitian didapat hasil kinerja klasifikasi dengan pembobotan supervised Delta TF-IDF terbukti lebih bagus dengan akurasi sebesar 88,5% sedangkan dengan pembobotan unsupervised TF-IDF diperoleh hasil akurasi 87,9%","PeriodicalId":292117,"journal":{"name":"Jurnal Komputasi","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131040290","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Peningkatan Keamanan Transmisi Data REST API Menggunakan Enkripsi SHA-512","authors":"M. I. Parabi, Didik Kurniawan, Rizky Prabowo","doi":"10.23960/komputasi.v11i1.6652","DOIUrl":"https://doi.org/10.23960/komputasi.v11i1.6652","url":null,"abstract":"Perkembangan teknologi informasi terus meningkat seiring dengan kebutuhan organisasi dalam mengelola proses bisnis menggunakan berbagai sistem yang saling terhubung. Pada proses transmisi data antar sistem, dibutuhkan keamanan tingkat tinggi yang mampu menjamin integritas data dalam hal keutuhan dan konsistensi data, khususnya sistem keuangan yang memiliki data sensitif. Exposure data sensitif melalui Application Programming Interface (API) merupakan salah satu kerentanan pada keamanan sistem berbasis web. Man in the Middle Attack (MitMA) merupakan jenis serangan yang sering terjadi ketika transmisi data menggunakan API. Penelitian ini bertujuan untuk meningkatkan keamanan transmisi data pada Representational State Transfer (REST) API menggunakan enkripsi Secure Hash Algorithm (SHA)-512. Hasil penelitian menunjukkan bahwa penerapan enkripsi SHA-512 mampu meningkatkan keamanan transmisi data dari client ke server maupun sebaliknya. Pada metode POST, data request yang terenkripsi memiliki performa lebih baik 2,8% dibandingkan dengan data request yang tidak terenkripsi. Sedangkan pada metode GET, data request yang terenkripsi lebih lambat 12,5% dibandingkan dengan data request yang tidak terenkripsi. Hal ini dikarenakan adanya proses enkripsi dan dekripsi yang dilakukan server untuk mengelola response sehingga membutuhkan waktu lebih lama.","PeriodicalId":292117,"journal":{"name":"Jurnal Komputasi","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128284321","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Aplikasi Sistem Pakar Untuk Diagnosa Penyakit Ibu Hamil Menggunakan Metode Forward Chaining Berbasis Website","authors":"Samuel Agave, M. B. Ulum","doi":"10.23960/komputasi.v11i1.3070","DOIUrl":"https://doi.org/10.23960/komputasi.v11i1.3070","url":null,"abstract":"Kehamilan merupakan suatu proses yang dialami oleh seluruh wanita di dunia. Dalam melewati proses kehamilan seorang wanita harus mendapatkan persiapan yang benar. Saat hamil banyak perubahan yang terjadi pada tubuh ibu hamil, salah satunya adalah ketahan tubuh yang menjadi berkurang. Penyakit apapun dapat dengan mudah menyerang tubuh apabila ibu hamil tidak menjaga kebugaran serta kesehatan. Salah satu masalah yang dihadapi oleh ibu hamil pada masa kehamilannya yaitu kurangnya informasi mengenai kesehatan pada ibu hamil dan keluhan yang dirasakan pada ibu hamil dianggap hal yang wajar tanpa memeriksakan gejala yang dialami, hal ini memicu tingginya ibu hamil yang terdiagnosis penyakit kehamilan yang menyebabkan meningkatnya Angka Kematian Ibu (AKI). Karena permasalahan tersebut diperlukan aplikasi sistem pakar untuk membantu ibu hamil dalam mendapatkan informasi mengenai penyakit kehamilan dan melakukan diagnosa dini mengenai penyakit kehamilan. metode yang digunakan dalam pembuatan aplikasi sistem pakar ini adalah forward chaining. Penelitian ini menggunakan metode pengembangan sistem extreme programming dengan php native sabagai coding utama dalam pembuatan aplikasi. Hasil dari penelitian ini yaitu dapat memberikan informasi informasi mengenai penyakit kehamilan dan melakukan diagnosa dini mengenai penyakit kehamilan berdasarkan knowledge base, yang terdiri dari 6 data penyakit, 30 data gejala, dan 6 data solusi.","PeriodicalId":292117,"journal":{"name":"Jurnal Komputasi","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130963709","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"ANALISIS PEMILIHAN LAYANAN INTERNET TERBAIK DI KOTA DEPOK MENGGUNAKAN METODE ANALYTICAL HIERARCHY PROCESS","authors":"Amos Saut Parulian Aritonang, Cepi Cahyadi","doi":"10.23960/komputasi.v11i1.5023","DOIUrl":"https://doi.org/10.23960/komputasi.v11i1.5023","url":null,"abstract":"Jangkauan layanan internet saat ini dapat ditemukan di berbagai lokasi atau wilayah yang memudahkan para masyarakat menggunakan layanan tersebut dimana saja untuk aktifitas kesehariannya secara online. Setiap calon pengguna akan memastikan pilihan Internet Service Provider yang akan digunakan nantinya sesuai dengan kebutuhan. Contohnya layanan dengan harga yang relatif mahal namun memiliki kualitas yang baik, atau adanya layanan dengan harga relatif terjangkau dengan bandwidth yang tidak terlalu tinggi Adanya macam macam keunggulan tersebut akan membuat para calon pengguna mengalami kesulitan dalam pemilihan layanan internet yang akan digunakan. Menerapkan AHP sebagai sistem pendukung keputusan adalah solusi untuk membantu masyarakat dalam melakukan pemilihan layanan internet. Dengan perhitungan menggunakan metode AHP, maka diperoleh urutan prioritas kriteria utama yaitu, Harga dengan nilai 39% , untuk kriteria bandwidth dengan nilai 31%,dan untuk kriteria pelayanan dengan nilai 29%. Sedangkan untuk peringkat pada alternatif diperoleh hasil yaitu, Indihome sebesar 33% untuk Firstmedia atau 23%, untuk Biznet 21%, dan untuk Oxygen 21%.","PeriodicalId":292117,"journal":{"name":"Jurnal Komputasi","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129170536","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Prediction of 6 Personality Characters (HEXACO) from Social Media using Random Forest Classifier and Particle Swarm Optimization","authors":"Iksan Ramadhan","doi":"10.23960/komputasi.v10i2.3171","DOIUrl":"https://doi.org/10.23960/komputasi.v10i2.3171","url":null,"abstract":"The importance of personality assessment is required in determining whether an individual can support a job, or which position is suitable and in accordance with his personality. The personality model that is often used is the Myer Brigs Type Indicator, but the model is considered inappropriate for use because the model is too dichotomous in defining one's personality. Unlike the HEXACO personality model, the model provides a numerical assessment of each personality trait. In determining an individual's personality, it can be done by utilizing one's writing using the classification algorithm model. In the test, the data collected previously was classified according to its target to get the results in the form of personality classifications. Testing is done using the PSO algorithm so that the results obtained have a high level of accuracy, equal to 0.9 (90%). The use of PSO algorithm can help to get high accuracy results in the prediction process because the search for parameter values in the prediction model is done automatically.","PeriodicalId":292117,"journal":{"name":"Jurnal Komputasi","volume":"130 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122310886","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"E-Library Interaktif dengan SLiMS Bulian Menggunakan Metode RAD","authors":"Arief Ichwani, Muhammad Visal Bainuri","doi":"10.23960/komputasi.v10i2.3170","DOIUrl":"https://doi.org/10.23960/komputasi.v10i2.3170","url":null,"abstract":"The use of technology in various fields has developed very quickly and has become a necessity in supporting the services of an organization or company. Educational institutions are one of the sectors that are guided in the learning process using Information and Communication Technology (ICT). Education, especially libraries, is one of the fields that uses high ICT, namely the digitalization of libraries or often e-libraries in order to realize quality education and ICT competitiveness in the world of education. As for the e-library in educational institutions, one of the schools is a source of information or reference for students, to increase students' reading interest, as well as to increase students' knowledge and competence. This makes the e-library has a very important role and must be developed to meet these needs such as developing an interactive and interesting e-library. The methods used for data collection are observations to the school library, interviews with library managers, and literature studies to deepen problem understanding. The software development method used is Rapid Application Development (RAD) by utilizing the Unified Modeling Language (UML) to design the system design developed. The results of this study are the existence of a complete e-library and an attractive application design and forum feature that makes the e-library interactive so that it can encourage the level of visits and literacy culture for students. The e-library has been carried out through black box testing and System Usability Test (SUS) with acceptable results.","PeriodicalId":292117,"journal":{"name":"Jurnal Komputasi","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114428579","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}