Articles
Expert System for Sars Cov-2 Disease with Comorbidities Using a Combination of Case Based Reasoning and Certainty Factor Methods
Adinda, Sity Tree;
Samsudin, Samsudin;
Irawan, Muhammad Dedi
Jurnal Penelitian Medan Agama MEDAN AGAMA, VOL. 15, NO. 1, JUNE 2024
Publisher : Universitas Islam Negeri Sumatera Utara
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.58836/jpma.v15i1.21105
Virus Sereve Acute Respirator Syndrome Corona Virus 2 (SARS COV-2) is a virus that is also caused by a corona virus which if exposed to this virus will cause a serious infection that has the potential to be life threatening. In various cases, it turns out that infection with the SARS COV-2 virus can have effects on several organs such as the lungs, heart, blood vessels, kidneys and liver. In this regard, some people think that the SARS COV-2 virus is a scary virus that makes people afraid to come to health services so that it has an impact on uncontrolled blood sugar and is prone to complications. To overcome the increase in mortality due to the SARS COV-2 virus with comorbidities with the help of artificial intelligence to build a knowledge-based system in the medical field for diagnosing SARS COV-2 with comorbidities using a combination of Case Based Reasoning and Certainty Factor methods. The Case Based Reasoning method is used as a rule to detect disease symptoms by diagnosing new cases based on old cases. While the Certainty Factor is used to increase the value of confidence and feasibility. The percentage of confidence value given by experts in order to get maximum results.
Decision Support System Implementation of Decision Tree Algorithm C4.5 In Employee Performance Assessment
Pasaribu, Afifah Balqis;
Dedi Irawan, Muhammad
Jurnal E-Komtek (Elektro-Komputer-Teknik) Vol 8 No 2 (2024)
Publisher : Politeknik Piksi Ganesha Indonesia
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.37339/e-komtek.v8i2.2145
Employee performance assessment can be used as an evaluation tool to improve employee performance to achieve more. Some of the benefits of performance appraisal are such as improving business quality, driving business progress, and improving employee welfare. Yasmin Medical Clinic requires an employee performance appraisal system that can help superiors to process data properly so that it can shorten the time and produce an assessment that is in accordance with the subjective value of decision making. One method that can be used in a decision support system is a decision tree. Current decision trees such as C4.5 and CART are widely used in various fields. The results of the analysis show that the application of the decision support system of the decision tree algorithm c4.5 in employee performance appraisal is able to solve problems at the Yasmin Medical Clinic. A computerized decision support system helps the decision-making process and produces objective decisions that are in accordance with actual conditions.
IMPLEMENTASI ALGORITMA PIXEL VALUE DIFFERENCING (PVD) DALAM KEAMANAN DATA TEKS
Nasution, Ratna Sabrina;
Fakhriza, Muhammad;
Irawan, Muhammad Dedi
JURSIMA Vol 12 No 2 (2025): Volume 12 Nomor 2 2025
Publisher : INSTITUT TEKNOLOGI DAN BISNIS INDOBARU NASIONAL
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.47024/js.v12i2.934
Steganografi telah menjadi solusi penting untuk mengamankan informasi sensitif dalam berkas yang tampak tidak mencurigakan seperti gambar atau dokumen. Makalah ini mengeksplorasi algoritma Pixel Value Differentencing (PVD) untuk menyembunyikan data rahasia dalam teks PDF, memastikan kerahasiaan tanpa menimbulkan kecurigaan. Penelitian ini menganjurkan penggunaan langkah-langkah keamanan yang kuat untuk mencegah akses yang tidak sah, menyoroti tanggung jawab organisasi dalam melindungi informasi sensitif. Dengan memanfaatkan sistem berbasis web yang menggunakan kriptografi Exclusive OR (XOR) dan steganografi PVD, penelitian ini bertujuan untuk meningkatkan perlindungan data terhadap potensi pelanggaran dan kebocoran. Meskipun menghadapi tantangan seperti noise pada gambar stego akibat karakteristik PDF yang disisipkan (teks, tabel, gambar), pendekatan ini secara signifikan mengurangi risiko keamanan, sehingga memperkuat langkah-langkah kerahasiaan untuk data perusahaan.
Combination of Forward Chaining and Certainty Factor Methods In An Expert System for Diagnosis of Cattle Diseases
Ramadan, Chafiz;
Santoso, Heri;
Irawan, Muhammad Dedi
IJISTECH (International Journal of Information System and Technology) Vol 8, No 5 (2025): The February edition
Publisher : Sekolah Tinggi Ilmu Komputer (STIKOM) Tunas Bangsa
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.30645/ijistech.v8i5.375
Cows are one of the most widely cultivated livestock animals in Indonesia, especially in the Asahan district alone, according to data from Asahan in Figures for 2022, in Asahan District in 2021 there will be 146,511 heads spread across 25 sub-districts. Cow disease is no longer a strange thing for livestock breeders. The symptoms that appear in cattle must be known as soon as possible before the disease appears with a ferocity that will cause the risk of death in cattle. death in Mr Poniman's cattle. Due to tympanic disease (bloating), at the time of this incident there were still few cows and people did not know how to treat it, so the cows eventually died with enlarged stomachs. With the availability of technology, the author built an expert system for diagnosing cattle diseases that can diagnose cattle diseases and provide treatment suggestions, both medical and natural, using the forward chaining method and certainty factor. Forward chaining first selects facts that are appropriate to the problem that is occurring, and the certainty factor will determine the result of the percentage of confidence of an expert. This system was built based on a website.
Implementation of the Single Moving Average Method in Forecasting Sales of Motorcycle Spare Parts
Dwika Sherliyanda;
Muhammad Dedi Irawan;
Adnan Buyung Nasution
Indonesian Journal of Data Science, IoT, Machine Learning and Informatics Vol 5 No 1 (2025): February
Publisher : Research Group of Data Engineering, Faculty of Informatics
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.20895/dinda.v5i1.1791
Sales forecasting is an important element in inventory management to ensure product availability in accordance with market demand. One method that can be used for forecasting is the Single Moving Average (SMA), which works by calculating the average sales in a certain period to identify future sales trends. This research aims to implement the SMA method in forecasting sales of motorbike spare parts in order to increase stock management efficiency and reduce the risk of excess or shortage of inventory. This research method involves collecting historical data on sales of motorbike spare parts in a certain period, which is then analyzed using the SMA method with various average period lengths to determine the best accuracy. The research results show that the SMA method can provide fairly accurate estimates of future demand patterns. With better forecasting, stores or distributors can optimize procurement strategies and reduce unnecessary carrying costs. Apart from that, implementing this method also contributes to increasing customer satisfaction because product availability can be more guaranteed. The conclusion of this research shows that the Single Moving Average method is a simple but effective forecasting technique in motorcycle spare parts inventory management. Implementation of this method can help business people make more appropriate decisions in stock planning and marketing strategies.
Combination of Forward Chaining and Certainty Factor Methods In An Expert System for Diagnosis of Cattle Diseases
Ramadan, Chafiz;
Santoso, Heri;
Irawan, Muhammad Dedi
IJISTECH (International Journal of Information System and Technology) Vol 8, No 5 (2025): The February edition
Publisher : Sekolah Tinggi Ilmu Komputer (STIKOM) Tunas Bangsa
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.30645/ijistech.v8i5.375
Cows are one of the most widely cultivated livestock animals in Indonesia, especially in the Asahan district alone, according to data from Asahan in Figures for 2022, in Asahan District in 2021 there will be 146,511 heads spread across 25 sub-districts. Cow disease is no longer a strange thing for livestock breeders. The symptoms that appear in cattle must be known as soon as possible before the disease appears with a ferocity that will cause the risk of death in cattle. death in Mr Poniman's cattle. Due to tympanic disease (bloating), at the time of this incident there were still few cows and people did not know how to treat it, so the cows eventually died with enlarged stomachs. With the availability of technology, the author built an expert system for diagnosing cattle diseases that can diagnose cattle diseases and provide treatment suggestions, both medical and natural, using the forward chaining method and certainty factor. Forward chaining first selects facts that are appropriate to the problem that is occurring, and the certainty factor will determine the result of the percentage of confidence of an expert. This system was built based on a website.
PERBANDINGAN METODE MFEP DAN WSM TERHADAP PROMOSI DAN STRATEGI PEMASARAN BIBIT
Umniati, Naila;
Dedi Irawan, Muhammad
Jurnal Mnemonic Vol 8 No 1 (2025): Mnemonic Vol. 8 No. 1
Publisher : Teknik Informatika, Institut Teknologi Nasional malang
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.36040/mnemonic.v8i1.13512
Penelitian membahas pengoptimalan strategi pemasaran bibit tanaman pada Rian Bibit memakai metode Multi Factor Evaluation Process (MFEP) dan Weighted Sum Model (WSM). Dengan banyak persaingan, memerlukan strategi pemasaran efektif dan efisien dalam memperkenalkan produk secara intensif, meningkatkan kesadaran pasar, dan memperkuat merek. Penelitian bertujuan membandingkan dan menerapkan metode MFEP dan WSM dalam pengambilan keputusan strategi pemasaran bibit tanaman juga distribusi melalui analisis kritis terhadap faktor-faktor yang memengaruhi keputusan pemasaran. Tujuan lainnya menambah wawasan bagi pelaku usaha pertanian dalam mengembangkan bisnis ataupun usaha. Penelitian diawali dengan mengumpulkan data melalui observasi dan wawancara untuk mendapatkan informasi yang diperlukan. Metode MFEP untuk menentukan strategi promosi yang tepat dengan memberikan bobot pada kriteria relevan. Sedangkan metode WSM untuk menghitung nilai evaluasi setiap alternatif strategi. Selanjutnya didapatkan hasil dari kedua metode tersebut untuk ditarik kesimpulan. Metodologi pengembangan sistem yang diadopsi adalah metode waterfall, yaitu metodologi dengan pendekatan software yang mengikuti pola air terjun. Langkah-langkah metode waterfall diawali dari analisis kebutuhan, desain, penerapan, pengujian, dan pemeliharaan. Hasil perangkingan kedua metode menunjukkan hasil konsisten dimana penggunaan metode MFEP dan WSM menunjukkan hasil sama. Berdasarkan penelitian peringkat pertama adalah durian dan terakhir jambu. Hasil penelitian diharapkan memberikan panduan dalam pengembangan strategi pemasaran yang efektif dan efisien
Application Of Expert System In Determining Diseases In Potato Plants
Ikhwan, Ali;
Bi Rahmani , Nur Ahmadi;
H. Aly, Moustafa;
Aslami, Nuri;
Dedi Irawan, Muhammad;
Ahmad, Imam
Indonesian Journal of Information Systems Vol. 7 No. 2 (2025): February 2025
Publisher : Program Studi Sistem Informasi Universitas Atma Jaya Yogyakarta
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.24002/ijis.v7i2.10213
This research aims to develop an expert system in diagnosing diseases in potato plants using the Case Based Reasoning (CBR) method approach combined with the K-Nearest Neighbor (K-NN) algorithm. The system is designed to help farmers identify the type of disease based on the symptoms that appear, as well as provide relevant solutions to increase crop productivity. In previous research, the CBR method showed a limited accuracy rate of 74% because it only relied on one algorithm. Through the application of two methods in data analysis, namely CBR and K-NN, this study succeeded in increasing the diagnosis accuracy to be higher than the previous approach of 80%. The system is implemented in the form of a web-based application that is easily accessible by farmers. The results show that the integration of these two methods provides more optimal, effective, and accurate results in detecting potato plant diseases based on symptom data. The findings are expected to contribute significantly to the development of agricultural technology, especially in improving the harvest success of potato farmers in Indonesia.
Implementation of K-Means Clustering in Recognizing Crime Hotspots and Traffic Issues Through GIS
Pratama, Aryo;
Irawan, Muhammad Dedi;
Andriana, Septiana Dewi
Journal of Computer Networks, Architecture and High Performance Computing Vol. 6 No. 2 (2024): Articles Research Volume 6 Issue 2, April 2024
Publisher : Information Technology and Science (ITScience)
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.47709/cnahpc.v6i2.3771
The challenge of accurately identifying instances of crime and traffic issues has rendered the precise localization thereof difficult, thereby impeding the populace's access to information concerning areas of high risk and safety. Employing a Geographic Information System (GIS)-based mapping system utilizing the K-means clustering method, spatial data pertaining to crime and traffic concerns are grouped. The primary objective is to aid in the identification of high-risk areas concerning crime and traffic matters. The methodology employed in this study revolves around the application of the K-means clustering method to categorize spatial data relevant to crime and traffic issues. K-means clustering represents a non-hierarchical cluster analysis technique designed to partition data into multiple groups based on spatial similarities. Research findings elucidate that through the utilization of the K-means clustering method, three distinct sets of clusters predicated upon the intensity of crime and traffic issues emerge. Consequently, from these clustering outcomes, districts and specific locales falling within each cluster, denoted as moderately vulnerable (C1), vulnerable (C2), and highly vulnerable (C3), can be delineated. This system is poised to furnish recommendations to pertinent authorities for addressing areas exhibiting heightened intensity levels while concurrently facilitating the generation of reports and dissemination of information to the public via a dedicated website pertaining to areas at elevated risk of crime and traffic issues.
Penjadwalan Pembelajaran Narapidana: Penerapan Algoritma Genetika di LPKA Kelas I Tanjung Gusta Medan
Yun Betry Siagian;
Heri Santoso;
Muhammad Dedi Irawan
Journal of Information Technology Vol 4 No 1 (2024): Journal of Information Technology
Publisher : Institut Shanti Bhuana
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.46229/jifotech.v4i1.873
Scheduling in education has been a common issue faced, particularly concerning the mismatch between class hours and teacher availability. Addressing this necessitated careful precision and a significant amount of time for subject scheduling. Genetic algorithms emerged as a suitable choice for managing school subject scheduling due to their capability to address multi-criteria and multi-objective problems inspired by biological evolution. The concept of genetic algorithms could be effectively applied in the context of schedule arrangement within educational institutions. This study employed a quantitative methodology and implemented the Rapid Application Development (RAD) system development method. The utilization of genetic algorithms in subject scheduling, as demonstrated in this research, was deemed beneficial for correctional institutions previously engaged in manual scheduling processes. The outcomes indicated the success of the genetic algorithm approach in resolving school scheduling issues by seeking optimal scheduling combinations, as evidenced by achieving maximum fitness values and minimal errors (in this case, an error value of 0), indicating the absence of class schedule conflicts.