Claim Missing Document
Check
Articles

Found 7 Documents
Search

PELATIHAN PRAKTIS AKUNTANSI: PENINGKATAN KETERAMPILAN MANAJEMEN KEUANGAN BERBASIS TEKNOLOGI INFORMASI PADA UMKM BUMDesa PULE SEJAHTERA Kartikasari, Evi dwi; Rodhiyah, Ma’rufatur; Khotiah, Titik; Wiyanti, Melisa Yuli; Romadhon, Muhammad Farih
Jurnal Abdi Insani Vol 11 No 4 (2024): Jurnal Abdi Insani
Publisher : Universitas Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29303/abdiinsani.v11i4.2037

Abstract

The problems that exist in MSMEs in Pule Village based on an initial survey stated that less than 5% of MSME actors utilize information systems and there are approximately 4% of MSME actors who document their financial management. 92% of MSME actors in Pule Village are lay people who do not come from an Economic Education background so that their ability in financial literacy and managerial management skills are very minimal. So far, MSME managers have only focused on the sale of the products produced without calculating the estimated expected profit. This is a challenge for Accounting Academics to provide insight and training on information technology-based financial management so that the existence of MSMEs can achieve maximum goals. It is hoped that MSMEs in Pule Village will be able to become independent and rapidly developing MSMEs through additional working capital and skills in preparing good financial reports and being able to utilize information technology as a means of supporting activities. This service is carried out using the Community Development method, namely an approach that is oriented towards developing community empowerment by making the community the subject, object of development, and direct involvement in various service activities that will be carried out. The results of this service have a positive and significant impact. The increase in partners' accounting literacy has increased and the ability to prepare financial reports has increased by 80%. It is hoped that this service can become a community service that is continued, meaning that there is monitoring and assistance for partners to continuously implement the results of technology and innovation provided in community service activities.
Optimalisasi Preprocessing untuk Peningkatan Akurasi Pengenalan Plat Nomor pada Citra Tidak Ideal Galahartlambang, Yanuangga; Khotiah, Titik; Basri K, Ilham; Anwar, Masrur; Fahmi Abdillah, David
Nucleus Journal Vol. 3 No. 2 (2024): November
Publisher : Universitas Darul Ulum

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32492/nucleus.v3i2.3206

Abstract

Penelitian ini bertujuan untuk mengevaluasi performa Optical Character Recognition (OCR) dalam mengenali teks pada gambar plat nomor kendaraan yang diambil menggunakan kamera digital. Dataset yang digunakan terdiri dari 10 gambar plat nomor kendaraan dengan karakteristik gambar lalu lintas kendaraan, termasuk pencahayaan rendah, distorsi perspektif, noise, dan ukuran gambar yang kecil. Berbagai teknik perbaikan kualitas gambar diterapkan, seperti Contrast Limited Adaptive Histogram Equalization (CLAHE), Bilateral Filtering, Wavelet Denoising, Unsharp Masking, dan Super-Resolution GAN menggunakan bicubic interpolation. Pengukuran akurasi dilakukan menggunakan dua metrik utama, yaitu Character Accuracy Rate (CAR) dan Word Accuracy Rate (WAR), dengan nilai rata-rata masing-masing sebesar 96,91% dan 90,00%. Hasil penelitian menunjukkan bahwa metode perbaikan kualitas gambar mampu meningkatkan visibilitas karakter pada plat nomor, sehingga OCR dapat mengenali teks dengan akurasi tinggi meskipun terdapat noise dan distorsi pada gambar. Penelitian ini memberikan wawasan tentang efektivitas pipeline perbaikan gambar dan OCR pada kondisi lalu lintas kendaraan, serta menjadi landasan untuk pengembangan sistem pengenalan plat nomor yang lebih baik
Serious Games About Indonesia’s Heroes Day for Education About Events 10 November 1945 Abdillah, David Fahmi; K, Ilham Basri; Khotiah, Titik; Galahartlambang, Yanuangga; Arianto, Fery
Journal of Computer Networks, Architecture and High Performance Computing Vol. 5 No. 1 (2023): Article Research Volume 5 Issue 1, January 2023
Publisher : Information Technology and Science (ITScience)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/cnahpc.v5i1.2005

Abstract

Heroes' Day is one of important days for Indonesia, is a day that commemorates one of the most important historical events, especially for the Indonesian people. The independence of the threatened Indonesian nation could be defended by heroes who sacrificed their lives against the invaders, where the incident coincided on November 10, 1945. but there are still many young people today who still do not understand the importance of their hero's struggle on that day, and consider Heroes' Day an ordinary holiday. The serious game is one of the game genres that is commonly used to provide learning about a topic by using games as learning media. By utilizing games as learning media, it will be easier for youth to understand the events of November 10 directly. The game is designed as a first-person shooter game developed using Unity with players playing the role of fighters against invaders on November 10, 1945. After playing, players will be given a series of questionnaires that contain events that occurred in the game and provide value to the game application. from the results of the questionnaire, the value obtained from the questionnaire was 69 and the value of the aspects of the game was 3.37.
Comparison of Machine Learning Techniques in the Classification of Parkinson’s Desease Sufferers Khotiah, Titik; Abdillah, David Fahmi; K, Ilham Basri; Arianto, Fery; Rohman, Abdul
Journal of Computer Networks, Architecture and High Performance Computing Vol. 5 No. 1 (2023): Article Research Volume 5 Issue 1, January 2023
Publisher : Information Technology and Science (ITScience)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/cnahpc.v5i1.2035

Abstract

Parkinson's disease is a progressive and relatively common neurodegenerative  disorder in the central nervous system where sufferers can have difficulty moving. This disease has a high mortality rate in the world of around 9.3 million in 2021. Meanwhile, in Indonesia, it is estimated that as many as 12,980 people die every year due to Parkinson's cases. This increase in cases of death is due to the lack of information about the initial symptoms and dangers of the disease, besides it is important to know how to prevent it early.  Early detection of Parkinson's disease can prevent symptoms of a certain age thereby increasing life expectancy. The existence of a computer-based system for diagnosing Parkinson's disease is called a classification system where the system applies the Machine Learning method. This study aims to compare the performance of algorithms in the classification system of people with computer diseases. In this study, it used methods in  Machine Learning such as K-NN, Multi Layer Percepteron (MLP), Linear Regression and Support Vector Machine (SVM).  The data set in this study was obtained using the Weka application.  The dataset used was Parkinson's Disease data  totaling 195 rows of data taken from the UCI Machine Learning Repository Datasets.  The results  of the experiment based on the four algorithms showed that  the poor performance was the Multi Layer Percepteron approach  to regression data with an RSME value of 0.459.  Meanwhile, the k-Neural Network Algorithm  is a good classification technique forParkinson's problem with an RMSE value of 0.1895.
Pemetaan Konsumen Berdasarkan Perilaku Transaksi Produk Ritel Pada Distributor XYZ Semarang Galahartlambang, Yanuangga; Khotiah, Titik; Jumain, Jumain
Jurnal JEETech Vol. 3 No. 2 (2022): Nomor 2 November
Publisher : Universitas Darul Ulum

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32492/jeetech.v3i2.3201

Abstract

Customer segmentation is essential for any business to better understand their customers, to maintain customer satisfaction, and to develop product and service needs. The purpose of customer segmentation is to determine how to handle customers in each category to increase each customer's profit for the business. Distributor XYZ Semarang is a multi-branched company engaged in the sale of consumer retail products to serve customers from small (retail) to large (wholesale) businesses. The database used in this study was taken from one branch with a transaction period of 2 years. The purpose of this research is to build a customer segmentation model based on customer demographics and transaction behavior and to help businesses better understand their customers to support marketing strategies. The proposed segmentation model is regarding customer demographic data regarding Recency, Frequency, and Monetary (RFM) resulting from purchasing behavior, customers have been segmented using the K-means grouping technique into various groups based on their similarities, and profiles for each group are identified based on their characteristics. . Thus, companies can find out the behavior of customers from the results of grouping based on how much value they spend, how often they make purchases and what products are their shopping concerns where this can be used as an evaluation basis for marketing strategies and further analysis..
Classification of Chili Fruit Diseases Using Deep Convolutional Neural Network Transfer Learning Anwar, Masrur; Abdillah, David Fahmi; Basri, Ilham; Galahartlambang, Yanuangga; Khotiah, Titik
Journal of Informatics Development Vol. 2 No. 2 (2024): April 2024
Publisher : Institut Teknologi dan Bisnis Widya Gama Lumajang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30741/jid.v2i2.1335

Abstract

Chili peppers are among the highest-value agricultural commodities, often experiencing significant price fluctuations due to supply constraints. The rainy season frequently leads to crop failures caused by diseases affecting chili plants. Existing methods often struggle to accurately differentiate between similar symptoms on leaves and fruits, leading to misdiagnosis and ineffective disease management strategies. Early detection of these diseases, which manifest as symptoms on the leaves and fruits, is crucial for effective pest management. Common diseases include anthracnose, characterized by dry brown spots on the fruit, and fruit rot, where the interior of the fruit decays while the skin remains intact. Identifying these diseases promptly is essential for applying appropriate treatments to ensure optimal yields.In this study, a comprehensive approach is taken to classify diseases in chili pepper plants (Capsicum annuum L.) by incorporating both leaf and fruit segmentation. The research employs Deep Convolutional Neural Networks with Transfer Learning (DCNN) to enhance detection capabilities. The findings reveal that for leaf disease classification, fewer neurons in additional layers yield better accuracy and reduced loss, while for fruit disease classification, a more complex model with additional neurons is necessary. This underscores the need for balancing model complexity to achieve optimal performance and prevent overfitting, particularly in distinguishing between leaf and fruit diseases.
PENGENALAN PLAT NOMOR KENDARAAN REAL-TIME PADA KONDISI GELAP DAN HUJAN MENGGUNAKAN DEEP LEARNING Galahartlambang, Yanuangga; Khotiah, Titik; Fanani, Zahruddin; bastian Dwiki Rahmat, Mohammad
Jurnal Informatika dan Rekayasa Elektronik Vol. 8 No. 1 (2025): JIRE APRIL 2025
Publisher : LPPM STMIK Lombok

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Pengenalan plat nomor kendaraan secara real-time merupakan salah satu teknologi penting dalam sistem transportasi cerdas, terutama pada kondisi lingkungan yang menantang seperti gelap dan hujan. Penelitian ini bertujuan untuk mengembangkan dan menguji metode pengenalan plat nomor menggunakan kombinasi YOLO v8 untuk melakukan deteksi plat nomor kendaraan dan framework screen text recognition TPS-ResNet-BiLSTM-Attn untuk pengenalan teks. Dataset yang digunakan berjumlah 3.000 gambar plat nomor yang dibagi menjadi 70% untuk pelatihan, 15% untuk validasi, dan 15% untuk pengujian. Framework ini dirancang untuk mengatasi tantangan visual seperti pencahayaan rendah dan gangguan akibat hujan melalui tahapan transformasi geometris (TPS), ekstraksi fitur (ResNet), pemodelan urutan karakter (BiLSTM), dan mekanisme transkripsi berbasis perhatian (Attention). Hasil pengujian menunjukkan akurasi yang berbeda pada berbagai kondisi, yaitu 78,6% pada kondisi normal, 82,4% pada kondisi gelap, dan 80,7% pada kondisi hujan. Hal ini menunjukkan bahwa metode deteksi objek YOLO v8 dan pengenalan karakter teks TPS-ResNet-BiLSTM-Attn yang diusulkan mampu menangani tantangan pengenalan plat nomor dalam kondisi lingkungan yang kompleks, sehingga memiliki potensi besar untuk diterapkan dalam sistem pengawasan transportasi yang lebih andal