Garuda - Garba Rujukan Digital

Justifikasi Anggaran Biaya Pembuatan Sistem Informasi Manajemen Klinik Menggunakan Metode Activity Based Costing (Studi Kasus Klinik Mutiara Balapulang) Diani Romiati; Kiki Alfaini Nurrizki; Azkiyatun Nadroh; Imam Ahmad Ashari
Seminar Nasional Penelitian dan Pengabdian Kepada Masyarakat 2022: Prosiding Seminar Nasional Penelitian dan Pengabdian Kepada Masyarakat (SNPPKM 2022)
Publisher : Universitas Harapan Bangsa

Dalam setiap pengembangan suatu sistem informasi, perlu menentukan strategi baik dalam pengerjaan maupun pembiayaan. Biaya yang dibutuhkan untuk pengembangan cukup banyak dan memiliki beberapa parameter yang kompleks, sehingga dibutuhkan salah satu konsep manajemen yakni pengakuratan biaya, dalam kasus ini adalah biaya pengembangan Sistem Informasi Manajemen Klinik. Tujuan dari penelitian ini adalah untuk menguraikan serta menghitung anggaran biaya pengembangan Sistem Informasi Manajemen Klinik. Alokasi biaya yang tepat diperlukan agar keuangan terkelola dengan baik, sehingga digunakan sebuah metode yaitu Activity Based Costing untuk menghitung anggaran biaya pengembangan Sistem Informasi Manajemen Klinik, dimana sistem perhitungannya dengan membebankan biaya pada setiap aktivitas yang terlibat terlebih dahulu sebelum menghitung biaya produk. Banyaknya aktivitas dalam mengembangkan suatu sistem informasi membuat metode ini cocok untuk diterapkan dalam pengakuratan biaya. Hasil dari penelitian ini didapatkan bahwa biaya total yang dibutuhkan sebesar IDR 54.150.000 dalam pengembangan Sistem Informasi Manajemen Klinik pada Klinik Mutiara Balapulang. Hasil total perhitungan tersebut menunjukan bahwa metode Activity Based Costing ini dapat digunakan sebagai perhitungan alokasi proyek sistem informasi dengan tepat sesuai dengan setiap uraian aktivitas.

Overcoming the Home Industry Crisis in Goyor Sarong Wanarejan Utara: Training on Digital Marketing, Product Packaging and Sales Management Imam Ahmad Ashari; Arif Setia Sandi; Deny Nugroho Triwibowo; Irfan Arfianto; Pradestya Bima Arweina
Jurnal Pengabdian dan Pemberdayaan Masyarakat Indonesia Vol. 3 No. 10 (2023)
Publisher : Peneliti Teknologi Teknik Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59247/jppmi.v3i10.223

A crisis is currently affecting the Goyor woven sarong home industry in North Wanarejan Village (Wan-Ut), Pemalang. The Goyor sarong, which is the village's potential, is facing serious issues. The price of sarongs has plummeted, while the cost of raw materials and employee wages has soared. Furthermore, declining market demand has presented numerous challenges for sarong producers in Wan-Ut. Previously, sarong producers manufactured their products without any promotion, so a solution to address this crisis is much needed. One step that can be taken to tackle this issue is to promote the sarongs to increase market demand. Additionally, finding ways to reduce production costs is essential to improve profit margins. To achieve these goals, a community engagement program was conducted, providing training in digital marketing techniques, packaging creation, and sales management to residents of North Wanarejan Village. This program proceeded smoothly, and the residents showed great enthusiasm. Evaluation of the results was carried out directly during the program, where participants applied the sales strategie they had learned to sell Goyor sarongs online. As a result, two participants successfully sold Goyor sarongs online.

Analisis Metode K-Means Clustering untuk Menemukan Faktor-Faktor Penyebab suatu Produk Tidak Laku secara Tiba-Tiba Ashari, Imam Ahmad
Jurnal Teknologi Sistem Informasi Vol 6 No 1 (2025): Jurnal Teknologi Sistem Informasi
Publisher : Program Studi Sistem Informasi, Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/jtsi.v6i1.9502

Penjualan produk menjadi indikator keberhasilan bisnis. Terkadang, faktor-faktor umum seperti perubahan tren pasar, persaingan, atau kebijakan pemerintah dapat mempengaruhi ketertarikan terhadap produk yang sebelumnya laris terjual. Selain itu, faktor teknis seperti lokasi produk, stok kosong, kondisi rusak atau kadaluarsa, atau kesalahan harga juga dapat berperan. Dalam penelitian ini, metode K-Means Clustering digunakan untuk menganalisis penjualan produk dan mengidentifikasi faktor-faktor teknis yang menyebabkan penurunan penjualan. Data penjualan dianalisis untuk mengidentifikasi pola tersembunyi yang ada. Hasil analisis ini membantu dalam mengidentifikasi produk yang tiba-tiba tidak laku dan faktor-faktor yang mempengaruhi penurunan penjualan, sehingga dapat digunakan untuk meningkatkan penjualan. Pada analisis ini, salah satu produk yang ditemukan tiba-tiba tidak laku adalah Frestea Madu 350 ML. Penjualan produk ini mengalami penurunan tajam mulai bulan ke-4 dan tidak laku hingga bulan ke-12. Hasil konfirmasi dari pihak toko menunjukkan bahwa faktor utama penurunan penjualan adalah adanya produk baru yang lebih diminati. Oleh karena itu, diperlukan strategi manajemen produk untuk meningkatkan pendapatan toko terkait masalah ini, seperti tidak menjual lagi produk ini. Dari hasil analisis, dapat disimpulkan bahwa metode K-Means Clustering efektif digunakan dalam mencari produk yang tiba-tiba tidak laku.

Klasterisasi Pemetaan Kedisiplinan Pegawai Berdasarkan Rekap Kehadiran menggunakan Algoritma Clustering K-Means Ashari, Imam Ahmad; Purwono, Purwono; Indriyanto, Jatmiko; Sandi A., Arif Setia
METHOMIKA: Jurnal Manajemen Informatika & Komputerisasi Akuntansi Vol. 9 No. 1 (2025): METHOMIKA: Jurnal Manajemen Informatika & Komputersisasi Akuntansi
Publisher : Universitas Methodist Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46880/jmika.Vol9No1.pp12-18

Employee discipline is one of the key success factors in a company. Work discipline has an important role in the formation of a positive work environment. One of the things that shows employee discipline is the time of attendance. Attendance time is usually recorded at the time the employee enters and leaves. Disciplinary information can be mapped into several groupings so that it is easy for decision makers to read. One of the computational methods that can perform data mapping is the K-Means Clustering method. The K-Means Clustering method can group data based on their characteristics. In this study, attendance data were analyzed using the K-Means method to obtain disciplinary groupings. The number of Clusters is calculated using the elbow method, 3 Clusters are obtained which are the best Cluster choices, namely Clusters 0, 1, and 2. The data analysis process shows Cluster 2 is the Cluster with the best level of discipline. From the analysis, it shows that the K-Means Clustering method can classify data based on employee discipline. Based on these results, decision makers can be helped in assessing employee discipline at Universita Harapan Bangsa using the disciplinary data grouping that has been made.

Boosting real-time vehicle detection in urban traffic using a novel multi-augmentation Ashari, Imam Ahmad; Syafei, Wahyul Amien; Wibowo, Adi
Indonesian Journal of Electrical Engineering and Computer Science Vol 39, No 1: July 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v39.i1.pp656-668

Real-time vehicle object detection in urban traffic is crucial for modern traffic management systems. This study focuses on improving the accuracy of vehicle identification and classification in heavy traffic during peak hours, with particular emphasis on challenges such as small object sizes and interference from light reflections. The use of multi-label images enables the simultaneous detection of various vehicle types within a single frame, providing more detailed information about traffic conditions. You only look once (YOLO) was chosen for its capability to perform real-time object detection with high accuracy. Multi-augmentation techniques were applied to enrich the training data, making the model more robust to varying lighting conditions, viewpoints, object occlusions, and issues related to small objects. YOLOv8n and YOLOv9t were selected for their speed and efficiency. Models without augmentation, 10 single-augmentation techniques, and 5 multi-augmentation techniques were tested. The results show that YOLOv8n with multiaugmentation (scaling, zoom in, brightness adjustment, color jitter, and noise injection) achieved the highest mAP50-95 score of 0.536, surpassing YOLOv8n with single-augmentation Blur, which had an mAP50-95 of 0.465, as well as YOLOv8n without augmentation, which scored 0.390. Multiaugmentation proved to significantly enhance YOLO’s performance.

Traffic flow prediction using long short-term memory-Komodo Mlipir algorithm: metaheuristic optimization to multi-target vehicle detection Ashari, Imam Ahmad; Syafei, Wahyul Amien; Wibowo, Adi
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 14, No 4: August 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v14.i4.pp3343-3353

Multi-target vehicle detection in urban traffic faces challenges such as poor lighting, small object sizes, and diverse vehicle types, impacting traffic flow prediction accuracy. This study introduces an optimized long short-term memory (LSTM) model using the Komodo Mlipir algorithm (KMA) to enhance prediction accuracy. Traffic video data are processed with YOLO for vehicle classification and object counting. The LSTM model, trained to capture traffic patterns, employs parameters optimized by KMA, including learning rate, neuron count, and epochs. KMA integrates mutation and crossover strategies to enable adaptive selection in global and local searches. The model's performance was evaluated on an urban traffic dataset with uniform configurations for population size and key LSTM parameters, ensuring consistent evaluation. Results showed LSTM-KMA achieved a root mean square error (RMSE) of 14.5319, outperforming LSTM (16.6827), LSTM-improved dung beetle optimization (IDBO) (15.0946), and LSTM-particle swarm optimization (PSO) (15.0368). Its mean absolute error (MAE), at 8.7041, also surpassed LSTM (9.9903), LSTM-IDBO (9.0328), and LSTM-PSO (9.0015). LSTM-KMA effectively tackles multi-target detection challenges, improving prediction accuracy and transportation system efficiency. This reliable solution supports real-time urban traffic management, addressing the demands of dynamic urban environments.

Implementasi Wireless Sensor Network: Perbandingan Metode Inverse Distance Weight dan Ordinary Kriging untuk Estimasi Kadar Gas Amonia pada Lingkungan Peternakan Ashari, Imam Ahmad; Setiawan, Retno Agus; Nisa', Khoriun
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 9 No 5: Oktober 2022
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jtiik.2022934394

Wireless Sensor Network merupakan salah satu teknologi yang menjadi tren saat ini. Salah satu sektor bidang yang banyak memanfaatkan penerapan teknologi ini adalah agrikultur. WSN banyak digunakan dalam mengatasi permasalahan di sektor agrikultur, salah satunya pada sektor peternakan. Permasalahan yang sering terjadi di industri peternakan adalah gas beracun yang timbul dari kotoran hewan ternak, yaitu amonia. Peningkatan konsentrasi gas amonia di peternakan dapat menyebabkan keracunan serta kematian unggas ketika mencapai kadar konsentrasi tertentu. Dengan pemanfaatan teknologi WSN kadar gas amonia di lingkungan peternakan dapat diketahui secara realtime. Hanya saja besarnya biaya menjadi kendala pemasangan perangkat WSN di lingkungan peternakan. Oleh karena itu pada penelitian ini di usulkan metode yang mampu mengetahui persebaran gas amonia hanya dengan menggunakan beberapa titik stasiun pemantauan. Metode interpolasi mampu mengatasi permasalahan tersebut. Metode interpolasi yang di pakai dalam penelitian ini adalah metode Inverse Distance Weight (IDW) dan Ordinary Kriging (OK). Dari hasil pengujian menggunakan model MAPE metode IDW menghasilkan nilai MAPE sebesar 23,45% dan metode OK mengasilkan nilai MAPE sebesar 24,95%. Dari hasil pengujian tersebut menunjukkan bahwa metode IDW lebih baik daripada metode OK dalam menentukan nilai taksiran gas amonia di suatu titik lokasi. Abstract Wireless Sensor Network is a technology that is becoming a trend today. WSN is widely used in overcoming problems in the subfield of agricultural, livestock. The problem that often occurs in the livestock industries is the poisonous gas that arises from livestock manure, namely amonia. Increasing the concentration of amonia in the farm can cause poisoning and death of poultry when it reaches a certain concentration. With the use of WSN technology, amonia gas levels in the livestock environment can be known in realtime. It's just that the high cost becomes an obstacle to installing WSN equipment in the farm environment. Therefore, this research proposes a method that is able to determine the distribution of amonia gas only by using several monitoring stations. The interpolation method is able to overcome these problems. The interpolation method used in this study is the Inverse Distance Weight (IDW) and Ordinary Kriging (OK) method. From the test results using the MAPE model, the IDW method produces a MAPE value of 23.45% and the OK method produces a MAPE value of 24.95%. From the test results, it shows that the IDW method is better than the OK method in determining the estimated value of amonia gas at a certain location.

Klasterisasi Pemetaan Kedisiplinan Pegawai Berdasarkan Rekap Kehadiran menggunakan Algoritma Clustering K-Means Ashari, Imam Ahmad; Purwono, Purwono; Indriyanto, Jatmiko; Sandi A., Arif Setia
METHOMIKA: Jurnal Manajemen Informatika & Komputerisasi Akuntansi Vol. 9 No. 1 (2025): METHOMIKA: Jurnal Manajemen Informatika & Komputersisasi Akuntansi
Publisher : Universitas Methodist Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46880/jmika.Vol9No1.pp12-18

Employee discipline is one of the key success factors in a company. Work discipline has an important role in the formation of a positive work environment. One of the things that shows employee discipline is the time of attendance. Attendance time is usually recorded at the time the employee enters and leaves. Disciplinary information can be mapped into several groupings so that it is easy for decision makers to read. One of the computational methods that can perform data mapping is the K-Means Clustering method. The K-Means Clustering method can group data based on their characteristics. In this study, attendance data were analyzed using the K-Means method to obtain disciplinary groupings. The number of Clusters is calculated using the elbow method, 3 Clusters are obtained which are the best Cluster choices, namely Clusters 0, 1, and 2. The data analysis process shows Cluster 2 is the Cluster with the best level of discipline. From the analysis, it shows that the K-Means Clustering method can classify data based on employee discipline. Based on these results, decision makers can be helped in assessing employee discipline at Universita Harapan Bangsa using the disciplinary data grouping that has been made.

Monitoring the pH Levels of Well Water in the Home Industri Sarung Goyor Village, Pemalang, Using IoT Technology and Inverse Distance Weight Method Ashari, Imam Ahmad; Purwono, Purwono; Arfianto, Irfan
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika Vol. 9 No. 4 (2023): December
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26555/jiteki.v9i4.27388

The Sarung Goyor Home Industry business, located in Wanarejan Utara Village, Pemalang, has been running for several years. However, the use of residual textile dyes in the process of making goyor sarongs now poses a threat to the quality of well water in the area where residents live. This condition is a serious concern because some residents rely on water from the well for drinking, cooking, bathing, and washing. One of the impacts of this textile waste is abnormal water pH. The solution requires real-time monitoring of the pH of well water by utilizing Internet of Things (IoT) technology and pH sensors. In this solution, direct sampling using sensors is carried out at 3 monitoring points around the industrial area and processed to estimate the pH level of residents' well water. This monitoring system succeeded in showing that the average pH of well water was in a safe condition, namely 7.18, not much different from tests carried out with reference sensors, namely a pH range between 6.96 to 7.20. The findings show that in testing the assembled sensor, the IDW method has a measurable error rate with an RMSE of about 0.2629 and a MAPE of about 4.669%. When compared with the test results using a reference sensor, the RMSE value reaches around 0.4666 and the MAPE is around 6.553%.

Systematic Literature Review: Penerapan Machine Learning dalam Diagnosis dan Prediksi Penyakit Diabetes Handayani, Oktavia Putri; Purwono; Ashari, Imam Ahmad; Ardianto, Rian
Komputa : Jurnal Ilmiah Komputer dan Informatika Vol 14 No 2 (2025): Komputa : Jurnal Ilmiah Komputer dan Informatika
Publisher : Program Studi Teknik Informatika - Universitas Komputer Indonesia (UNIKOM)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34010/komputa.v14i2.16642

Diabetes mellitus is a chronic disease with a growing global prevalence, posing significant challenges for healthcare systems worldwide. Machine Learning (ML) offers promising solutions for early diagnosis and prediction by analyzing complex medical data efficiently. This study adopts a Systematic Literature Review (SLR) method guided by the PRISMA protocol to analyze 15 open-access articles published between 2022 and 2025 from the ScienceDirect database. These studies explore the use of various ML algorithms—including Support Vector Machine (SVM), Random Forest (RF), and Convolutional Neural Network (CNN)—in diagnosing diabetes. The main objective is to evaluate the effectiveness, strengths, and limitations of each algorithm in clinical applications. The review highlights current trends, performance comparisons, and challenges in implementing ML models for diabetes diagnosis. The findings are expected to provide valuable insights for researchers and practitioners aiming to develop more accurate, efficient, and applicable ML-based diagnostic systems for improved diabetes management and early intervention.

Title

Found 23 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 23 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 23 Documents
Search