Article Per Year (5 Year)
p-Index From 2021 - 2026
2.339
P-Index
This Author published in this journals
All Journal Komatika: Jurnal Pengabdian Kepada Masyarakat Science and Education Journal Journal of Innovative and Creativity Indonesian Journal of Innovation Science and Knowledge JIKTEKS : Jurnal Ilmu Komputer dan Teknologi Informasi Teknik: Jurnal Teknik Mesin, Elektro dan Ilmu Komputer
Alfian Nara Weking
Institut Keguruan dan Teknologi Larantuka
Agriculture, Biological Sciences & Forestry Humanities Computer Science & IT Economics, Econometrics & Finance Education Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Mathematics Social Sciences Other

Published : 16 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 16 Documents
Search

 1   2 
Penerapan Information Gain Untuk Seleksi Fitur Pada Algoritma Naïve Bayes Untuk Analisis Sentimen Identitas Kependudukan Digital Yuliana Nogo Welan; Alfian Nara Weking; Dominikus Boli Watomakin
Jurnal Teknik Mesin, Elektro dan Ilmu Komputer Vol. 5 No. 2 (2025): Juli : Jurnal Teknik Mesin, Elektro dan Ilmu Komputer
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/teknik.v5i2.7433

Abstract

The rise of digital technology has driven the Indonesian government to implement Digital Population Identity (IKD) as a solution to enhance public services. However, user reviews on Google Play Store show diverse responses, requiring sentiment analysis to understand public perception. This study aims to improve sentiment classification accuracy on IKD app reviews using the Naïve Bayes algorithm optimized with Information Gain feature selection. The dataset consists of 1,000 Indonesian-language reviews manually labeled and preprocessed using text cleaning and TF-IDF feature representation. To address class imbalance, the SMOTE technique was applied. Experiments were conducted by comparing models without feature selection and balancing against those using Information Gain and SMOTE. Results indicate that the combination of Information Gain and SMOTE significantly enhances model performance, achieving 68,5% accuracy and 53,0% positive F1-Score. These findings confirm that Information Gain is effective in improving sentiment classification efficiency and accuracy. This study provides valuable insights for developing strategies to improve digital service quality. Kata kunci: Analisis Sentimen, Information Gain, Naïve Bayes, Seleksi Fitur, SMOTE.  
Analisis Tingkat Kepuasan Mahasiswa Terhadap Kinerja Sistem Informasi Akademik Menggunakan Metode Framework CSI Fransiskus Aprilius; Bernadete Deta; Alfian Nara Weking
Jurnal Teknik Mesin, Elektro dan Ilmu Komputer Vol. 5 No. 2 (2025): Juli : Jurnal Teknik Mesin, Elektro dan Ilmu Komputer
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/teknik.v5i2.7605

Abstract

  This study aims to identify factors that influence student satisfaction with SIA performance. The research method uses a quantitative method with data collection using a questionnaire instrument with a Likert scale. The results of the study explain that the validity test on 16 statements is declared valid because the tCount value> tTable. The results of the reliability test on the statements in the questionnaire test with a Likert scale obtained a Cronbach's Alpha value of 0.813. These results indicate that it is reliable because 0.813> 0.6. The results of the calculation of the mean of each attribute or variable are at most 13.8, 14.5, 16, 14.8, and 13.4. This result shows that it is reliable because 0.813 > 0.6. The calculation results of the mean of each attribute or variable are at most 13.8, 14.5, 16, 14.8, and 13.4. The calculation of the mean of the attribute or variable of information quality is at most 4.75, the calculation of the mean of the attribute or variable of system quality is at most 5 and 4.75, the calculation of the mean of the attribute or variable of service quality is at most 5, 4.25 and 4.75, the calculation of the mean of the attribute or variable of academic information system performance is at most 5, 4.33 and 4.67, the calculation of the mean of the attribute or variable of student satisfaction level is at most 4 and 5. The calculation of the Weighted Satisfaction Score (WSS) of student satisfaction is the most, namely 80, 75, 52, and 70. The results of the calculation of the Customer Satisfaction Index (CSI) vlue obtained the most values, namely 87, 107, 100, and 75.  
Diagnosis Gangguan Tidur Berdasarkan Gaya Hidup Menggunakan Algoritma Naïve Bayes Magdalena Herlin Wungubelen; Alfian Nara Weking; Dominikus Boli Watomakin
Jurnal Teknik Mesin, Elektro dan Ilmu Komputer Vol. 5 No. 2 (2025): Juli : Jurnal Teknik Mesin, Elektro dan Ilmu Komputer
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/teknik.v5i2.7609

Abstract

Abstract. Sleep disorders are health problems that often arise due to unhealthy lifestyle patterns and are often overlooked for their impact. This study aims to help detect the risk of sleep disorders using the Naive Bayes algorithm. Data were collected through interviews and examinations, then processed with preprocessing and testing data and achieved a classification accuracy of 88.6% for three categories: Normal, Insomnia, and Sleep Apnea. These results support the application of the Naive Bayes algorithm as a supportive diagnostic method based on lifestyle factors. This finding is also expected to serve as a basis for providing lifestyle improvement recommendations to prevent the risk pf sleep disorders.
Implementasi Random Forest Untuk Identifikasi Jenis Sampah Organik Dan Non-Organik Helminda Yeni Da Silva; Alfian Nara Weking; Dominikus Boli Watomakin
Jurnal Teknik Mesin, Elektro dan Ilmu Komputer Vol. 5 No. 2 (2025): Juli : Jurnal Teknik Mesin, Elektro dan Ilmu Komputer
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/teknik.v5i2.7612

Abstract

Abstract. Waste is a growing environmental problem, especially if it is not managed properly starting from the sorting process. One effort to improve the effectiveness of waste management is through automatic identification of waste types. This study aims to implement the Random Forest algorithm in the process of classifying waste into two categories: organic and non-organic waste. The data used are waste images that have gone through the preprocessing stage and the extraction of color and texture features. The Random Forest model was chosen because it has advantages in handling diverse data and providing stable classification results. Test results show that this model is capable of classifying with a fairly good level of accuracy, with the highest accuracy of 87% on the test data. In addition, this model is also integrated into a mobile application to facilitate users in identifying waste types in real-time. This implementation is expected to help the community sort waste more efficiently and contribute to sustainable environmental management.
Penerapan Api Whatsapp Fonnte Untuk Sistem Pengingat Jadwal Bimbingan Tugas Akhir Mahasiswa Berbasis Web Ignasius Mario Bele Waton; Alfian Nara Weking; Bernadete Deta
Jurnal Teknik Mesin, Elektro dan Ilmu Komputer Vol. 5 No. 2 (2025): Juli : Jurnal Teknik Mesin, Elektro dan Ilmu Komputer
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/teknik.v5i2.7614

Abstract

Abstract. This study aims to develop an automatic reminder system for undergraduate thesis guidance schedules based on web using the Fonnte WhatsApp API. Students often forget their scheduled guidance, so a system is needed to automatically send notifications. The system is built using PHP programming language and MySQL database. Notifications are sent to students' WhatsApp on D-1 and D-day through the Fonnte API. Testing was carried out with latency and response time parameters. The results show the system has an average latency of 265 ms and response time of 62 ms, with effectiveness of 163.5 ms categorized as quite effective. This system is proven to help students be more disciplined in the guidance process.
Sistem Pakar Diagnosis Penyakit Virus Pada Ternak Babi Menggunakan Metode Fuzzy Tsukamoto Berbasis Website Elias Kapitan Bono Tefa; Alfian Nara Weking; Dominikus Boli Watomakin
Jurnal Teknik Mesin, Elektro dan Ilmu Komputer Vol. 5 No. 2 (2025): Juli : Jurnal Teknik Mesin, Elektro dan Ilmu Komputer
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/teknik.v5i2.7631

Abstract

Abstract. Pig farming plays a significant role in enhancing economic value, particularly in pork production. However, pigs are highly susceptible to viral infections such as Hog Cholera or Classical Swine Fever (CSF), Swine Pox, and African Swine Fever (ASF), which have high transmission and mortality rates. The limited availability of veterinary personnel and the difficulty of early diagnosis pose serious challenges for farmers. This study aims to develop a web-based expert system utilizing the Fuzzy Tsukamoto method to diagnose viral infections in pigs based on clinical symptoms. The system is designed to assist farmers in accurately identifying the type of virus and providing appropriate preventive solutions. The test results show that the Fuzzy Tsukamoto method can deliver accurate and field-relevant diagnoses. Therefore, it can be concluded that the Fuzzy Tsukamoto method is effective in developing expert systems for diagnosing viral diseases in pigs.
Co-Authors Alexander Reinaldo R.N Tobi Bernadete Deta Dominikus Boli Watomakin Elias Kapitan Bono Tefa Fransiskus Aprilius Helminda Yeni Da Silva Ignasius Mario Bele Waton Lusia Bince Kumanireng Magdalena Herlin Wungubelen Maria Beliti Hewen Maria D. Elsoin Maria Katarina Liwu Maria Peni Makin Martinus Mado WL. Lamanepa Nadia Damayanti Peuma Roberta Uron Hurit Sesilia Barek Tukan Yosep Kun Nogo Ama Hajon Yoseph F. Kuma Manuk Yuliana Nogo Welan