Claim Missing Document
Check
Articles

Comparison Of The Effectiveness Of K-Nearest Neighbor (KNN) And Naive Bayes Algorithms In Identifying Diabetes Patients Susanto, Eko Budi; Anzila, Anin Naba; Ismanto, Bambang
Journal of Artificial Intelligence and Software Engineering Vol 5, No 1 (2025): March
Publisher : Politeknik Negeri Lhokseumawe

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30811/jaise.v5i1.6275

Abstract

Delay in diagnosis of diabetes is one of the causes of increasing mortality due to complications before diagnosis is made. In the medical field, the application of machine learning models has opened up significant opportunities in improving the accuracy of early diagnosis of diabetes. This study aims to compare the performance of the K-Nearest Neighbors (KNN) and Naive Bayes Classifier (NBC) algorithms using a secondary dataset of 128 data records and containing 10 data variables relevant to the prediction of diabetes. The results of the analysis show that the KNN algorithm with parameters K = 21 based on the evaluation of the confusion matrix obtained an accuracy of 76.92%, recall 100%, precision 72% and F1-Score 84%. Meanwhile, the naïve Bayes algorithm obtained an accuracy of 65.63%, recall 52%, precision 100% and F1-Score 69%. In the evaluation using the k-fold cross validation method with K = 10, the average accuracy for the KNN algorithm was 73% and for the Naïve Bayes algorithm was 70%. Thus, the KNN algorithm is superior and recommended for diabetes disease classification.
PENGEMBANGAN CHATBOT UNTUK LAYANAN PENERIMAAN MAHASISWA BARU DI INSTITUT WIDYA PRATAMA DENGAN MENGGUNAKAN METODE NAIVE BAYES Susanto, Eko Budi; Mohammad Reza Maulana; Arochman
IC Tech: Majalah Ilmiah Vol 20 No 1 (2025): IC Tech: Majalah Ilmiah Volume XX No. 1 April 2025
Publisher : P3M Institut Widya Pratama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47775/ictech.v20i1.318

Abstract

In this study, a chatbot for new student admissions was developed using the Naïve Bayes algorithm. The data source used was a dialogue between admissions staff and prospective students, which was based on information from the new student admissions brochure of Institut Widya Pratama (formerly STMIK Widya Pratama) for the 2024-2025 academic year. The data was arranged in JSON format, including three elements: question structure, classification, and answers. Data pre-processing steps included text normalization, label encoding, vectorization, and word embedding. The Naïve Bayes algorithm was chosen to train the model because of its ability to predict responses from discrete data. The test results showed that this algorithm achieved an accuracy level of 88%, surpassing the performance of the K-Neighbors-Classifier algorithm. The resulting model was implemented in a desktop-based chatbot application that was run via the command prompt, using the Python programming language and several libraries such as pickle, string, and numpy. This application is able to provide answers to user questions by accessing the model stored in the *.pkl file. The results of the study show that the Naïve Bayes algorithm is effective in predicting user questions, with sufficient accuracy for a new student admissions chatbot application.
PENATALAKSANAAN HOLISTIK PASIEN PADA PEREMPUAN USIA 25 TAHUN DENGAN ASMA PERSITEN RINGAN BERBASIS LAYANAN KEDOKTERAN KELUARGA DI WILAYAH KERJA PUSKESMAS KEDATON Sari, Zada Amalia Agatha; Susanto, Eko Budi
Medula Vol 15 No 2 (2025): Medula
Publisher : CV. Jasa Sukses Abadi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.53089/medula.v15i2.1613

Abstract

Asthma is a heterogeneous disease, characterized by chronic inflammation of the airways characterized by a history of respiratory symptoms such as wheezing, shortness of breath, chest tightness, and coughing that vary in time and intensity, accompanied by variations in expiratory airflow obstruction. The purpose of this study is to apply a holistic and comprehensive family medicine approach in detecting internal and external risk factors and solving problems based on Evidence Based Medicine which is a family approach, patient-centered, community oriented. This research method uses a descriptive study of case reports. Primary data were obtained through autoanamnesis, physical examination, and home visits to patients. Secondary data were obtained from patient medical records at the Kedaton Health Center. The assessment was carried out based on a holistic diagnosis from the beginning, process, and end of the study quantitatively and qualitatively. The results obtained were that patient Ms. S, 25 years old, diagnosed with mild persistent asthma was managed comprehensively, namely given medication in the form of bronchodilators and inhalers and carried out interventions using poster media and showing asthma exercise videos. The evaluation showed that the results were in the form of improved patient complaints, increased understanding of the disease as evidenced by a comparison of pre- and post-test values, and increased family support. The conclusion obtained was that the application of a family doctor approach was needed for holistic and comprehensive management of patients with mild persistent asthma to detect internal and external risk factors in order to support the success of therapy and improve the patient's quality of life.
PENGEMBANGAN KEMAMPUAN UMKM DALAM MEMPRODUKSI KONTEN VIDEO MELALUI CAPCUT SEBAGAI STRATEGI PEMASARAN DIGITAL DI MEDIA SOSIAL Susanto, Eko Budi; Christianto, Paminto Agung; Darmawan, Wachid
Servirisma Vol. 5 No. 1 (2025): Servirisma : Jurnal Pengabdian kepada Masyarakat
Publisher : Lembaga Penelitian dan Pengabdian Masyarakat (LPPM) Universitas Kristen Duta Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21460/servirisma.2025.51.92

Abstract

This Community Service (PkM) activity was carried out with the aim of improving the skills of Micro, Small, and Medium Enterprises (MSMEs) in Setono Village in producing and editing promotional videos using the CapCut application. In today's digital era, the ability to create interesting video content is an important asset for MSMEs in marketing their products. This workshop managed to attract 40 participants, exceeding the initial target of 30 participants, which shows the high enthusiasm of MSMEs to improve their digital skills. The materials presented include the basics of creating video content, effective shooting techniques, introduction and tutorials on using the CapCut application, and product branding strategies to increase sales. The results of the post-test and direct practice showed that participants had understood and were able to apply video editing skills using CapCut. Although face-to-face discussion sessions were limited, interaction and consultation continued through personal communication. This activity is expected to make a significant contribution to increasing the competitiveness of MSMEs in Setono Village through the use of social media as a means of promotion. The success of this program was supported by the enthusiasm of the participants and the relevance of the material to the needs of MSMEs in the digital era.
Protecting Batik Customers and the Existence of Pekalongan Original Batik by Augmented Reality Technology Based on Cloud Computingin Batik Label Christianto, Paminto Agung; Eko Budi Susanto; Ichwan Kurniawan
International Journal of Islamic Business and Economics (IJIBEC) Vol 1 No 1 (2017): Volume 1 Nomor 1 Tahun 2017
Publisher : Universitas Islam Negeri K.H. Abdurrahman Wahid Pekalongan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28918/ijibec.v1i1.896

Abstract

The wrong assumption stating batik printed textilebatik issimilar withoriginal batik bears a loss for batik producers, because customers tend to buy printed textilewhich are cheaper than originalones (”tulis”, ”cap” or ”combination” batik). The misperception used by some batik enterpreneurs who mentioned that products he sold arekinds of original batik, although theyare printed textile. It disrupts the existence of Pekalongan traditional batikas well andmany customers experience losses. This research is an effort to support Indonesian government in maintaining batik as an Indonesian cultural heritage, and Pekalongan city government in maintaining the existence of ”World's city of Batik” byissuing Regional Regulation No. 6 of 2014 Pekalongan about the use of Pekalongan batik label. Through the use of augmented reality technologybased on cloud computing, it will create a ”Batik Pekalongan” label which provides information about the authenticity of Pekalongan batik products through smartphones access, and convenience for Pekalongan city government or Pekalongan ASEPHI in supervising the use of the label. Therefore, it will not be misused by unscrupulous batik entrpreneurs.
Application of TOEH Framework to Analyze Readiness for Adoption of Information Technology in Institutions in Central Java Agung Christianto , Paminto; Susanto, Eko Budi
Computing and Information System Journal Vol. 1 No. 2 (2025): Integration of Automation and Information Systems in Enhancing Organizational C
Publisher : IndoCompt Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Digital transformation in the public sector requires organizational readiness to adopt information technology (IT) effectively. This study aims to analyze the factors that influence IT adoption readiness in agencies in Central Java using the TOEH (Technology, Organization, Environment, Human Resources) framework approach. Data collection was conducted through a survey of 102 respondents representing employees of related agencies, with a purposive sampling technique and a Likert scale questionnaire instrument. The results of the validity test showed that all instrument items were valid, and the reliability test showed that the Technology variable (α = 0.899) was the most reliable compared to Organization (0.659), HR (0.587), and Environment (0.485). The findings showed that aspects of system security, managerial support, government policy, and HR competence were key factors in IT adoption readiness. This study emphasizes the importance of synergy between internal and external elements of the organization in supporting public sector digital transformation.  
Transformasi Pemasaran Usaha Konvensional Menuju Digital Melalui Pelatihan di Kelurahan Medono, Pekalongan Agung Christianto , Paminto; Susanto, Eko Budi
Dedikasi Nusantara: Jurnal Pengabdian Masyarakat Vol. 1 No. 1 (2025): Pemberdayaan Masyarakat dalam UMKM, Digital Marketing, Pelatihan Keterampilan d
Publisher : IndoCompt Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Pemasaran digital menjadi krusial dalam menghadapi keterbatasan promosi konvensional. Warga Kelurahan Medono, Pekalongan Barat, yang mayoritas merupakan pengusaha batik dan tenun, masih mengandalkan brosur dan spanduk dalam mempromosikan produk mereka. Keterbatasan jangkauan dan konten menjadi kendala utama. Kegiatan pengabdian masyarakat ini bertujuan mengatasi permasalahan tersebut melalui pelatihan digital marketing bagi 20 pelaku usaha. Metode pelatihan yang digunakan adalah praktik langsung pembuatan konten digital marketing, disertai pendampingan intensif. Modul tutorial pembuatan konten menggunakan aplikasi Canva diberikan kepada peserta. Hasil kegiatan menunjukkan bahwa peserta mampu membuat media promosi digital menggunakan Canva untuk mendukung usaha mereka. Keterlibatan aktif masyarakat dalam kegiatan ini menunjukkan antusiasme tinggi untuk mengadopsi teknologi digital demi pengembangan usaha, sekaligus memperkuat kolaborasi antara akademisi dan komunitas lokal.
Pengujian Black Box dengan Teknik Equivalence Partitioning pada Aplikasi Monitoring Pemberian Obat Filariasis Berbasis Android Maulana, Mohammad Reza; Eko Budi Susanto; Paminto Agung Christianto
KLIK: Kajian Ilmiah Informatika dan Komputer Vol. 4 No. 4 (2024): Februari 2024
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/klik.v4i4.1603

Abstract

The application of information technology in various sectors, including the health sector, has become a necessity. Dinas Kesehatan (Dinkes) of Pekalongan City uses information technology to support the Pekalongan City Government's vision as a Smart City. One of the main focuses of the Health Department is treating elephantiasis (filariasis). Even though we have implemented a Mass Preventive Medication (Pemberian Obat Pencegahan secara Massal – POPM) program, the mycorrhiza filarial (MF) rate is still above 1%, requiring additional POPM. One of the problems is the monitoring of drug administration by Tenaga Pelaksana Eliminasi (TPE) officers which is not optimal. Therefore, a monitoring mechanism is needed, implemented through an online-based executive dashboard. The data and graphs on the dashboard come from an Android-based recording application installed on the TPE officer's smartphone. Android applications need to be tested to minimize errors or bugs which can be tested using the Black Box method. This research aims to test the system in terms of providing input and output without knowing the details of the code. One technique that can be used in Black Box testing is the Equivalence Partitioning technique, which divides the input into valid and invalid partitions to ensure the results match the test case. The research stages involve determining use cases, criteria, test partitions, creating test data, and test case design. Testing is carried out through test cases that test the login process, inputting drug data, and sending photos as proof of drug consumption. The results show that by testing the seven test cases, the system can be used properly according to the expected scenario. Some recommendations for improvements that are needed are adjustments to the output message to users. In general, the application for monitoring filariasis drug administration has functioned well, under the application design. Evaluation produces recommendations for improvements to improve user experience. This research can become a basis for further development, including thorough testing of the application.
Penerapan Library AR.js pada Aplikasi e-Label Batik untuk Mendukung Kejelasan dan Kecepatan Tampilnya Informasi Keaslian Batik Christianto, Paminto Agung; Restyandito, Restyandito; Susanto, Eko Budi; Maulana, Moh. Reza
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 6 No 3: Juni 2019
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1881.786 KB) | DOI: 10.25126/jtiik.201963985

Abstract

Industri batik printing memproduksi tekstil bermotif batik dengan cara menduplikasinya melalui mesin-mesin printing, sehingga proses pengerjaannya bisa lebih cepat serta harga jual yang lebih murah dan ini memberikan ancaman bagi perkembangan batik asli. Ditambah lagi ketidaktahuan masyarakat dalam membedakan antara batik asli dan produk tekstil bermotif batik, telah menyebabkan masyarakat rentan dengan upaya penipuan oknum penjual batik dan memunculkan kecenderungan membeli produk tekstil bermotif batik yang harganya lebih murah. Untuk itu, diperlukan suatu alat bantu berupa aplikasi yang dapat digunakan oleh masyarakat untuk mengenali keaslian batik, sekaligus sebagai media belajar tentang berbagai hal terkait batik asli. Dari hasil diskusi dengan para penjual batik, diharapkan aplikasi tersebut mampu menampilkan informasi keaslian batik yang mudah dibaca serta memiliki kecepatan tampil yang stabil, walau diambil dari jarak pindai yang berbeda serta sudut kemiringan yang berbeda, sehingga dalam penelitian ini, diputuskan untuk menggunakan library AR.js dalam aplikasi e-label batik.Abstract The batik printing industry produces batik-patterned textiles by duplicating them through printing machines, thus the process may be faster and the selling price is cheaper, and this poses a threat to the development of original batik. The ignorance of the community in distinguishing between original batik and textile products with batik motifs, has caused the community to be vulnerable to fraudulent attempts from the sellers of batik and led to the tendency to buy batik-patterned textile products at a lower price. Hence, needed a tool in the form of applications that can be used by the public to recognize the authenticity of batik, as well as a medium of learning about various things related to original batik.  The discussions with batik sellers resulted that the application is expected to be able to display the authenticity information on batik that is easy to read and has a stable speed in displaying messages, even though taken from different scan distances and different slope angles, thus in this study, it was decided to use the library. AR.js in the e-label batik application.
Closed Beta Testing on Filariasis Treatment Monitoring Applications Eko Budi Susanto; Paminto Agung Christianto; Mohammad Reza Maulana; Nur Fadhilah
International Journal of Information Technology and Business Vol. 5 No. 2 (2023): April : International Journal of Information Technology and Business
Publisher : Universitas Kristen Satya Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24246/ijiteb.522023.06-11

Abstract

Monitoring applications for filariasis treatment have been developed to overcome the problem of elephantiasis or filariasis, one of which is the lack of monitoring during the distribution of elephantiasis medicines. One of the stages of application development is testing. Testing is conducted to ensure the application is ready to be implemented. In this study, closed beta testing was conducted to determine the feasibility of the application. The results of the validity test and reliability test showed that the results obtained were that all items on the questionnaire were declared valid and reliable. While the results of the feasibility test on the questionnaire results stated that the application was very feasible to be implemented.