Claim Missing Document
Check
Articles

Found 18 Documents
Search

Perbandingan Teknik Prediksi Pemakaian Obat Menggunakan Algoritma Simple Linear Regression dan Support Vector Regression Sephia Pratista; Alwis Nazir; Iwan Iskandar; Elvia Budianita; Iis Afrianty
Building of Informatics, Technology and Science (BITS) Vol 5 No 2 (2023): September 2023
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v5i2.4260

Abstract

Public Health Centers (Puskesmas) had a crucial role in furnishing society essential healthcare services and medication management. To preempt errors in stock management, a predictive approach is employed. This prediction methodology involves comparing Data Mining techniques utilizing the Simple Linear Regression algorithm and Machine Learning methodologies harnessing the Support Vector Regression algorithm. This research uses Paracetamol 500 mg and Cetirizine drug data from January 2020 to June 2023. The selection of these algorithms is motivated by the continuous nature of the data variables and their temporal span, spanning 42 months (period). The core aim of this study is to evaluate the magnitude of predictive errors using the Mean Absolute Percentage Error (MAPE) methodology. Implementing these methods was effectuated through the programming language Python with an 80%:20% partitioning of training and testing data. Drawing from experimental endeavors conducted concerning Paracetamol 500 mg, the utilization of the Simple Linear Regression algorithm, yields a MAPE score of 20.85%, categorized as 'Moderate,' whereas the application of the Support Vector Regression algorithm generates a MAPE of 18.39%, classified as 'Good.' Otherwise, experimentation on Cetirizine employing the Simple Linear Regression algorithm, employing an identical division of training and testing data, results in a MAPE of 18.39%, also classified as 'Good.' Meanwhile, resorting to the Support Vector Regression algorithm leads to a MAPE of 17.14%, falling under the 'Good' category. Based on the MAPE obtained, the Support Vector Regression algorithm has better prediction results than the Simple Linear Regression algorithm
Optimasi Kualitas Jaringan WIFI Fakultas Melalui Redesain Topologi Dengan Menggunakan Network Simulator 2 M. Saski; Iwan Iskandar; Novriyanto; Pizaini
KLIK: Kajian Ilmiah Informatika dan Komputer Vol. 4 No. 2 (2023): Oktober 2023
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/klik.v4i2.1272

Abstract

The utilization of WiFi internet networks on campus as tools to support the learning process at the Faculty of Science and Technology is crucial. Therefore, it essential for the campus to provide internet facilities ensure that all activities, including services and the learning process, are effective. This research analyze the quality of WiFi networks at Faculty of Science and Technology using the Quality of Service (QoS) method with parameters such  throughput, delay, packet loss, and jitter. In this study, testing was conducted on WiFi networks in three buildings within the Faculty of Science and Technology, under different conditions during peak hours and off-peak hours, using several SSIDs such as Pegawai, Pimpinan, Uinsuska, Labor TIF dan Baru Belajar, with bandwidths of up to 100Mbps. Test results indicate that the values obtained for throughput, delay, packet loss, and jitter in the three buildings were categorized as "Excellent" with an index of 4. However, in the Lab building, some parameters were found to be low. Therefore, this research conducted a redesign of the topology in the Lab building using Network Simulator 2 (NS2) to improve the quality of the WiFi network. Four nodes were recommended for each floor of the Lab building in the topology redesign. The results of these tests provided QoS parameter values that were used as information for the tested topology recommendations, showing good parameter quality with a throughput value 4738.7 Kbps, a packet loss value 0%, delay value 3.9639249 ms, and jitter value 0,381779103 ms. The results of this testing can be used as information and analystt for the campus PTIPD to enhance the quality of WiFi networks in the Faculty of Science and Technology
Perbandingan Prediksi Obat Berdasarkan Pemakaian Menggunakan Algoritma Single Moving Average dan Support Vector Regression Said Nurfan Hidayad Tillah; Alwis Nazir; Iwan Iskandar; Elvia Budianita; Iis Afrianty
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 7, No 4 (2023): Oktober 2023
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v7i4.6859

Abstract

To ensure the availability and quality of drugs, Public Health Centers (PHC) must pay attention to the planning and procurement process. The problem that often arises is the increase in drug stock due to the stable use of drugs each month, resulting in excess and expired drugs that are not used. In addition, it is necessary to avoid inappropriate drug demand, which affects stock availability. Drug usage prediction is done with several methods such as the Single Moving Average (SMA) algorithm in the data mining method and the Support Vector Regression (SVR) algorithm in the machine learning method. This algorithm was chosen because the drug data of Diazepam 5 mg and Mefenamic Acid 500 mg is sustainable from January 2020 to June 2023 (42 months). Implementation using the Phyton programming language. Testing using the Mean Absolute Percentage Error (MAPE) method, this study aims to measure the accuracy of predictions in each algorithm. In research with Diazepam 5 mg and Mefenamic Acid 500 mg drugs, with a division of 80% in training data and 20% in test data. With a calculation of 3 periods, the SMA algorithm produces MAPE values of 4.10% and 4.29%, in the "very good" range. The SVR algorithm, which uses an RBF kernel with a complexity parameter of 1.0 and an epsilon parameter of 0.1, produces MAPE results of 7.35% and 9.52%, in the "Very Good" range. Thus, the SMA algorithm predicts better than the SVR algorithm.
Klasifikasi Kebakaran Hutan Riau Menggunakan Random Forest dan Visualisasi Citra Sentinel-2 Ahmad Efendi; Iwan Iskandar; Rahmad Kurniawan; Muhammad Affandes
KLIK: Kajian Ilmiah Informatika dan Komputer Vol. 4 No. 3 (2023): Desember 2023
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/klik.v4i3.1521

Abstract

In September 2019, Riau was severely affected by hazardous haze, impacting the health of the population and disrupting the activities of approximately 6.5 million people. This situation necessitated swift and accurate actions for the mitigation and anticipation of forest and land fires. This research aims to classify forest fires in Riau using Machine Learning algorithms, specifically Random Forests. However, a comprehensive understanding of forest fires requires the visualization of Sentinel-2 satellite imagery using the Normalized Burn Ratio (NBR) index. Sentinel-2 imagery recreates a pivotal role in identifying burnt areas, measuring fire intensity, and assessing environmental impacts. Weather data spanning from January 2015 to September 2019, totaling 1733 data points have been utilized in this study. Experimental results demonstrate that the Random Forest algorithm achieved the highest accuracy of 71% with an 90% training data allocation. Meanwhile, Sentinel-2 imagery can visualize burnt areas with an overall accuracy of 94% and a kappa coefficient of 0.92. This study offers an integrated approach to addressing forest fires in Riau, resulting in improved predictions and a deeper understanding of forest fire disasters. In the context of disaster mitigation, the combination of Machine Learning and Sentinel-2 imagery visualization holds significant potential for providing critical information to stakeholders and authorities
Penerapan Algoritma Apriori Pada E-commerce Elektronik Nur Iza; Alwis Nazir; Iwan Iskandar; Elvia Budianita; Pizaini Pizaini
Journal of Computer System and Informatics (JoSYC) Vol 4 No 3 (2023): May 2023
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v4i3.3403

Abstract

Because there are so many advantages to using e-commerce, it is now expanding quickly. E-commerce, particularly for electronic items, makes it simpler for customers to execute transactions without traveling. Because businesses (business actors) do not yet have a pattern and strategy for the products they sell, the use of e-commerce has not yet reached its full potential. As a result, sales occasionally suffer because the supply of products does not meet consumer needs, forcing consumers to leave without purchasing these products, which has an impact on transactions. sales firm. Businesses (businesspeople) must use data mining to implement data processing. For this reason, researchers use an application strategy that is appropriate in this situation: the a priori algorithm. Finding frequent itemsets that frequently show up in the data set with the strongest pattern is frequently done using the a priori algorithm. This algorithm's output can be used to assist management in making decisions. According to the study's findings, the rule "if you buy AA Batteries (4-pack), you will buy AAA Batteries (4-pack), "if you buy AA Batteries (4-pack), you will buy a USB-C Charging Cable," and "if you buy AA Batteries (4-pack) and AAA Batteries (4-pack), you will buy a USB-C Charging Cable" all have a support and confidence value of 100%.
Klasifikasi Tingkat Keberhasilan Produksi Ayam Broiler di Riau Menggunakan Algoritma K-Nearest Neighbor Beni Basuki; Alwis Nazir; Siska Kurnia Gusti; Lestari Handayani; Iwan Iskandar
Jurnal Sistem Komputer dan Informatika (JSON) Vol. 4 No. 3 (2023): Maret 2023
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v4i3.5800

Abstract

Livestock is a crucial component of the Indonesian agriculture sector. One of the most widely practiced types of livestock farming is broiler chicken farming. The production of broiler chickens continues to increase due to the increasing consumption of broiler chickens. Presently, companies are facing an urgent requirement to support farmers, regardless of their level of experience, whether they are newly entering the sector or have been established for some time. Core companies encounter challenges in modeling the success rate of broiler chicken farmer production because of the vast quantity of data coming from collaborating farmers, which makes it arduous for the company to establish the success rate of broiler chicken production. Establishing the level of production success is very helpful in selecting the appropriate farmers to be guided, thus enabling accurate decision-making. A classification procedure utilizing data mining and K-Nearest Neighbor (KNN) algorithm is necessary to manage the growing volume of data. The study examined 927 livestock production data from Riau, where the data was divided into two sets, with 80% allocated for training and the remaining 20% for testing purposes. The findings of the confusion matrix analysis showed that the optimal result was achieved at k = 3, with an accuracy rate of 86.49%, precision of 75.00%, and recall of 70.21%.
Pemodelan Klasifikasi Untuk Menentukan Penyakit Diabetes dengan Faktor Penyebab Menggunakan Decision Tree C4.5 Pada Wanita Nining Nur Habibah; Alwis Nazir; Iwan Iskandar; Fadhilah Syafria; Lola Oktavia; Ihda Syurfi
Jurnal Sistem Komputer dan Informatika (JSON) Vol. 4 No. 4 (2023): Juni 2023
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v4i4.6202

Abstract

Diabetes is closely related to the pancreas, where the pancreas produces the natural hormone insulin, but its function is problematic which causes an increase in blood sugar levels in the body. Rising blood pressure can affect organ function in damaging the function of organs in a person's body such as the kidneys, heart and brain. Where makes a person have a history of diabetes. Diabetes that attacks adults can be prevented through exercise and a regular and healthy diet. According to the International Diabetes Federation (IDF) organization, it is estimated that at least 19.5 million Indonesian people between the ages of 20 and 79 will suffer from diabetes in 2021. China is in first place with diabetes with 140.9 million people. India is next in line with the number of people with diabetes of 74.2 million people. Therefore, early diagnosis is very important because it aims to reduce diabetes and diabetes complications in the future. It is necessary to collect data on patients with diabetes who are expected to be able to do prevention. Therefore applying classification techniques with data mining with the C4.5 algorithm. Where the classification can achieve better accuracy. Algorithm C4.5 is generally used in determining the nodes of a decision tree. Based on the test results, the accuracy is 76.67 percent, the precision is 72 percent, and the recall is 41.67 percent.
Klasifikasi Tingkat Keberhasilan Produksi Ayam Broiler di Riau Menggunakan Algoritma Naïve Bayes Syahbudin Hamwar; Alwis Nazir; Siska Kurnia Gusti; Iwan Iskandar; Fitri Insani
Jurnal Sistem Komputer dan Informatika (JSON) Vol. 5 No. 2 (2023): Desember 2023
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v5i2.7038

Abstract

Livestock is becoming one of the important animal protein source providers, along with the fisheries sector, to meet the protein needs of the community at large. One type of livestock business that is popular is the maintenance of broiler chickens because of the potential for meat yield. Today, many breeders run a partnership pattern with large companies where breeders play the role of the main supplier and the company as the core. This step helps maintain the stability of production and income of farmers. The success of farmers in broiler chicken production can be measured by looking at the performance index (IP), if the performance is not good then coaching from the core company is needed. The large amount of data obtained from farmers makes it difficult for core companies to model the success rate of farmer production, this can make it difficult for core companies to choose farmers who need coaching. The application of data mining methods using the Naïve Bayes algorithm classification model has the potential to provide solutions to this problem. The purpose of this study was to predict how much success rate of broiler chicken production in Riau region by utilizing the Naïve Bayes Classifier algorithm. This study utilizes a production data set involving 952 broiler chicken farmers in Riau, with 3 scenarios dividing the data ratio of 90:10, 80:20, and 70:30. The results of the analysis showed that through the evaluation of the confusion matrix, it was best found in a data ratio of 90:10 with accuracy results reaching 89,58%, precision reaching 89,89%, and recall reaching 90,16%.