Claim Missing Document
Check
Articles

Found 5 Documents
Search
Journal : Journal of Advanced Computer Knowledge and Algorithms

Comparison of the Results of the K-Nearest Neighbor (KNN) and Naïve Bayes Methods in the Classification of ISPA Diseases (Case Study: RSUD Fauziah Bireuen) Putri, Riska Yolanda; Yunizar, Zara; Safwandi, Safwandi
Journal of Advanced Computer Knowledge and Algorithms Vol 1, No 1 (2024): Journal of Advanced Computer Knowledge and Algorithms - January 2024
Publisher : Department of Informatics, Universitas Malikussaleh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29103/jacka.v1i1.14535

Abstract

Acute Respiratory Infection or commonly called (ARI) is a disease caused by bacteria or viruses. (ARI) can attack all ages, especially children. This study aims to compare the accuracy of classification in (ARI) disease. The data used is data from patients affected by (ARI) disease at Fauziah Bireuen Hospital. K-Nearest Neighbors and Naïve Bayes can be used in the classification of (ARI) diseases. Measurement of accuracy using Confusion Matrix in the K-Nearest Neighbors method with the Eulidean Distance approach in the case of (ARI) disease classification obtained a percentage of precision of 91%, recall 84% and accuracy of 88%. While the Naïve Bayes method obtained a percentage of precision of 95%, recall 78% and accuracy of 86%. The results of the accuracy comparison of the two methods show that the K-Nearest Neighbors method has a higher accuracy rate than the Naïve Bayes method.
Comparison of Chen's Fuzzy Time Series and Triple Exponential Smoothing in Forecasting Medicine Stocks at the Blang Cut Kuala Community Health Center Devi, Salma; Yunizar, Zara; Retno, Sujacka
Journal of Advanced Computer Knowledge and Algorithms Vol 1, No 3 (2024): Journal of Advanced Computer Knowledge and Algorithms - July 2024
Publisher : Department of Informatics, Universitas Malikussaleh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29103/jacka.v1i3.16870

Abstract

Forecasting is estimating future conditions by examining conditions in the past. In social life, everything is uncertain and difficult to predict precisely, so forecasting is needed. Efforts are always made to make forecasts in order to minimize the influence of this uncertainty on a problem. In other words, forecasting aims to obtain forecasts that can minimize forecast errors, which are usually measured by the mean absolute percentage error. This method is usually used for time series-based forecasting and uses data or information from the past as a reference when predicting current data. This research will compare the application of the Fuzzy Time Series Chen method and the Triple Exponential Smoothing method in forecasting drug stock determination at the Kuala Community Health Center, Blang Mangat District, Lhokseumawe City Regency, Aceh. The research results showed that the Triple Exponential Smoothing method was better in forecasting drug stock inventories compared to Chen's Fuzzy Time Series method. Chen's Fuzzy Time Series method produces a MAPE value of 17.67%, which means it has an accuracy of 82.33%, while the Triple Exponential Smoothing method produces a MAPE value of 9.842%, which means it has an accuracy of 90.158%
Web-Based Expert System Application for Early Diagnosis of HIV/AIDS Using the Naive Bayes Method Aisah, Sri Purwani; Adek, Rizal Tjut; Yunizar, Zara
Journal of Advanced Computer Knowledge and Algorithms Vol 1, No 4 (2024): Journal of Advanced Computer Knowledge and Algorithms - October 2024
Publisher : Department of Informatics, Universitas Malikussaleh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29103/jacka.v1i4.17809

Abstract

AIDS is a progressive decrease in the immune system so that opportunistic infections can appear and end in death, therefore the author created an early diagnosis system for HIV/AIDS using the website-based Naïve Bayes algorithm. Naïve Bayes is a simple probability classification that can calculate all possibilities by combining a number of combinations and frequencies of a value from the database obtained.the results of the research obtainedThe naïve Bayes algorithm can be implemented for early diagnosis of HIV/AIDS by means that the existing HIV/AIDS symptom data is adjusted to the patient's symptom data processed using the naïve Bayes algorithm and then it is concluded what the symptoms are and What is the solution.
Geographic Information System for Mapping Drug Abuse Areas in Lhokseumawe City Using the Average Linkage Method Syintia, Icut; Fuadi, Wahyu; Yunizar, Zara
Journal of Advanced Computer Knowledge and Algorithms Vol 2, No 1 (2025): Journal of Advanced Computer Knowledge and Algorithms - January 2025
Publisher : Department of Informatics, Universitas Malikussaleh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29103/jacka.v2i1.17804

Abstract

Aceh is one of the provinces in Indonesia where the development of drug abuse has increased. The system that runs at BNN Lhokseumawe City in recording data and information about drug abuse cases has not been integrated with the mapping of drug abuse areas. Therefore, BNN and Lhokseumawe City Police need a drug abuse area mapping system in the Lhokseumawe City area. This research aims to build a webgis-based geographic information system using the Google Maps API for map visualization. The data mining method used is Average Linkage, clustering is done based on the number of cases, number of suspects and population in each sub-district in Lhokseumawe City. Cluster 1 consists of 1 sub-district, namely Banda Sakti, which in cluster 1 has a relatively high average value compared to clusters 2 and 3 so that it is included in a very vulnerable level. In cluster 2 consists of 2 sub-districts, namely Muara Satu and Muara Dua, because this cluster has a medium average value compared to clusters 1 and 3 so that it is included in the vulnerable level. Whereas the cluster in cluster 3 consists of 1 sub-district, namely Blang Mangat, which in cluster 3 has a relatively lower average value than clusters 1 and 2 so that it is included in the moderately vulnerable level.
Diet Recommendation Application for Diabetes Patients Using the Preference Selection Index Method Siregar, Winda Ramadhani; Yunizar, Zara; Afrillia, Yesy
Journal of Advanced Computer Knowledge and Algorithms Vol. 2 No. 2 (2025): Journal of Advanced Computer Knowledge and Algorithms - April 2025
Publisher : Department of Informatics, Universitas Malikussaleh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29103/jacka.v2i2.17810

Abstract

Diabetes mellitus is a chronic condition characterized by elevated blood glucose levels. Effective diet management is crucial for controlling this condition and preventing serious complications. This study aims to develop a meal recommendation application for diabetes patients using the Preference Selection Index (PSI) method. The data used include user identity, health conditions, food preferences, and the nutritional content of meal menus. The PSI implementation process involves several key steps: collecting user data, normalizing nutritional values based on the minimum and maximum values in the database, adjusting the criterion weights according to the user's health conditions and food preferences, and calculating the PSI for each meal menu. The study results show that this application can provide meal recommendations that match the nutritional needs and health conditions of users. From a total of 10 user data analyzed, 50% received "Red Bean Soup with Vegetables" as the best menu, 30% received "Grilled Chicken Breast with Vegetables," and 10% each received "Grilled Chicken with Green Beans" and "Quinoa Salad with Avocado." The conclusion of this study is that the PSI method is effective in helping diabetes patients select an optimal diet, which can assist in better managing their condition and improving their quality of life. Suggestions for future research include increasing the variability of nutritional data, integrating with wearable technology, and developing reminder and education features.
Co-Authors ,, Iqbal ,, Maulidasari ,, Zulaifani ., Yulisma Aidilof, Hafizh Al Kautsar Aidilof, Hafizh Al-Kautsar Aisah, Sri Purwani Amelia, Ulva Aminsyah, Ansharulhaq Arief Fazillah Arif H., Nanda Nan Arnawan Hasibuan Asran Asran Bariah, Hairul Bustami Bustami Cindy Rahayu Dahlan Abdullah Devi, Salma Dhyra Gibran Alinda Dr M Rajeswari Elma Fitria Ananda ERNAWITA ERNAWITA Ersa, Nanda Savira Eva Darnila Fadlisyah Fadlisyah Fajri, Riyadhul Fajri, Ryadhul Fajriana, Fajriana Fardiansyah, T. Fasdarsyah Fasdarsyah Fatimah Zuhra Fatimah Zuhra Fatimah Zuhra Fuadi, Wahyu Hafidh Rafif, Teuku Muhammad Harahap, Ilham Taruna Hasan, Phadlin HENDRA ZULKIFLI Irshad Ahmad Reshi Johan, T. M. Kartika Kartika Kurnia Amanda, Destiara Lidya Rosnita M. Fauzan M.Cs, Iqbal, Maghfirah Maghfirah Maha, Dedi Torang P Mahara, Sabda Mahendra Febriliansyah Maizuar Maizuar Maryana Maryana, Maryana Maulana Helmi, Fathan Maulana, O.K.Muhammad Majid Melizar Meutia Rahmi Misbahul Jannah Muhammad Daud Muhammad Fikry Muhammad Ikhwani Muhammad Muhammad Muharni Muharni Mukhlis Mukhlis Mukhlis Mulaesyi, Syibbran Munar, Munar Munirul Ula Mursyidah Mursyidah MUTHMAINNAH Muthmainnah Muthmainnah NinaUlfauza NinaUlfauza Nunsina, Nunsina Nur Mauliza Nura Usrina Nurdin Nurdin Nuryawan, Nuryawan Putri, Riska Yolanda Ramadhana Juseva Ridha, Ridha Rini Meiyanti Ritonga, Huan Margana Rizal S.Si., M.IT, Rizal Rizki Suwanda Rizky Almunadiansyah Rizky Putra Fhonna Rizky, Rahmat Rizkya, Dini Dara Rozzi Kesuma Dinata Rusnani Rusnani Rusniati Rusniati Ruwaida Ruwaida Safwandi Safwandi Said Fadlan Anshari Savira Ersa, Nanda Siregar, Winda Ramadhani Sriana, Anis Suci Fitriani, Suci Sujacka Retno Syintia, Icut Taufiq Taufiq Tjut Adek, Rizal Wahyu Fuadi Yanti, Winda Yesy Afrillia Zalfie Ardian Zulsuhendra, Edi