6 research outputs found
Penerapan Teachable Machine Dan Raspberry Pi Pada Sistem Klasifikasi Citra Untuk Inspeksi Cacat Kain
No full textIndustri tekstil memainkan peran krusial dalam ekonomi nasional, menghadapi tantangan signifikan dalam menjaga kualitas produk untuk memenuhi kepuasan konsumen. Cacat produksi, seperti cacat jarang dan cacat slap pada kain, merupakan salah satu faktor utama yang mempengaruhi kualitas produk tekstil. Penelitian ini bertujuan untuk mengembangkan sistem inspeksi cacat kain secara otomatis dengan menggunakan metode pemrosesan citra digital dan machine learning. Sistem ini dirancang untuk diintegrasikan pada mesin penggulungan kain sebagai sistem inspeksi awal sebelum kain didistribusikan. Metode yang digunakan meliputi supervised learning untuk klasifikasi citra kain, memanfaatkan perangkat lunak Google Teachable Machine dan algoritma Convolutional Neural Network (CNN) yang diimplementasikan dengan OpenCV. Perangkat keras yang digunakan terdiri dari kamera web Logitech D320 untuk akuisisi gambar dan Raspberry Pi-3B sebagai pengolah citra. Sistem ini diuji untuk mendeteksi tiga kategori kain: kain bagus, cacat jarang, dan cacat slap. Hasil pengujian menunjukkan bahwa sistem memiliki rata-rata waktu inferensi sebesar 142,47 ms dengan kecepatan rata-rata 6,46 frame per detik (FPS) dan akurasi klasifikasi mencapai 98,48%. Dengan implementasi sistem ini, diharapkan dapat meningkatkan efisiensi produksi, memperkuat kontrol kualitas di industri tekstil, mengurangi intervensi manual, dan menurunkan potensi kerugian akibat produk cacat.
Abstract
The textile industry plays a crucial role in the national economy, facing significant challenges in maintaining product quality to meet consumer satisfaction. Production defects, such as rare defects and slap defects in fabrics, are key factors that affect the quality of textile products. This research aims to develop an automated fabric defect inspection system using digital image processing and machine learning methods. The system is designed to be integrated into fabric winding machines as an initial inspection system before the fabric is distributed. The methods used include supervised learning for fabric image classification, utilizing Google Teachable Machine software and the Convolutional Neural Network (CNN) algorithm implemented with OpenCV. The hardware used consists of a Logitech D320 webcam for image acquisition and a Raspberry Pi-3B as the image processor. The system was tested to detect three categories of fabric: good fabric, rare defects, and slap defects. The test results showed that the system achieved an average inference time of 142.47 ms with an average speed of 6.46 frames per second (FPS) and a classification accuracy of 98.48%. With the implementation of this system, it is expected to enhance production efficiency, strengthen quality control in the textile industry, reduce manual intervention, and decrease potential losses due to defective products
Penerapan Teachable Machine Dan Raspberry Pi Pada Sistem Klasifikasi Citra Untuk Inspeksi Cacat Kain
No full textIndustri tekstil memainkan peran krusial dalam ekonomi nasional, menghadapi tantangan signifikan dalam menjaga kualitas produk untuk memenuhi kepuasan konsumen. Cacat produksi, seperti cacat jarang dan cacat slap pada kain, merupakan salah satu faktor utama yang mempengaruhi kualitas produk tekstil. Penelitian ini bertujuan untuk mengembangkan sistem inspeksi cacat kain secara otomatis dengan menggunakan metode pemrosesan citra digital dan machine learning. Sistem ini dirancang untuk diintegrasikan pada mesin penggulungan kain sebagai sistem inspeksi awal sebelum kain didistribusikan. Metode yang digunakan meliputi supervised learning untuk klasifikasi citra kain, memanfaatkan perangkat lunak Google Teachable Machine dan algoritma Convolutional Neural Network (CNN) yang diimplementasikan dengan OpenCV. Perangkat keras yang digunakan terdiri dari kamera web Logitech D320 untuk akuisisi gambar dan Raspberry Pi-3B sebagai pengolah citra. Sistem ini diuji untuk mendeteksi tiga kategori kain: kain bagus, cacat jarang, dan cacat slap. Hasil pengujian menunjukkan bahwa sistem memiliki rata-rata waktu inferensi sebesar 142,47 ms dengan kecepatan rata-rata 6,46 frame per detik (FPS) dan akurasi klasifikasi mencapai 98,48%. Dengan implementasi sistem ini, diharapkan dapat meningkatkan efisiensi produksi, memperkuat kontrol kualitas di industri tekstil, mengurangi intervensi manual, dan menurunkan potensi kerugian akibat produk cacat.
Abstract
The textile industry plays a crucial role in the national economy, facing significant challenges in maintaining product quality to meet consumer satisfaction. Production defects, such as rare defects and slap defects in fabrics, are key factors that affect the quality of textile products. This research aims to develop an automated fabric defect inspection system using digital image processing and machine learning methods. The system is designed to be integrated into fabric winding machines as an initial inspection system before the fabric is distributed. The methods used include supervised learning for fabric image classification, utilizing Google Teachable Machine software and the Convolutional Neural Network (CNN) algorithm implemented with OpenCV. The hardware used consists of a Logitech D320 webcam for image acquisition and a Raspberry Pi-3B as the image processor. The system was tested to detect three categories of fabric: good fabric, rare defects, and slap defects. The test results showed that the system achieved an average inference time of 142.47 ms with an average speed of 6.46 frames per second (FPS) and a classification accuracy of 98.48%. With the implementation of this system, it is expected to enhance production efficiency, strengthen quality control in the textile industry, reduce manual intervention, and decrease potential losses due to defective products.Industri tekstil memainkan peran krusial dalam ekonomi nasional, menghadapi tantangan signifikan dalam menjaga kualitas produk untuk memenuhi kepuasan konsumen. Cacat produksi, seperti cacat jarang dan cacat slap pada kain, merupakan salah satu faktor utama yang mempengaruhi kualitas produk tekstil. Penelitian ini bertujuan untuk mengembangkan sistem inspeksi cacat kain secara otomatis dengan menggunakan metode pemrosesan citra digital dan machine learning. Sistem ini dirancang untuk diintegrasikan pada mesin penggulungan kain sebagai sistem inspeksi awal sebelum kain didistribusikan. Metode yang digunakan meliputi supervised learning untuk klasifikasi citra kain, memanfaatkan perangkat lunak Google Teachable Machine dan algoritma Convolutional Neural Network (CNN) yang diimplementasikan dengan OpenCV. Perangkat keras yang digunakan terdiri dari kamera web Logitech D320 untuk akuisisi gambar dan Raspberry Pi-3B sebagai pengolah citra. Sistem ini diuji untuk mendeteksi tiga kategori kain: kain bagus, cacat jarang, dan cacat slap. Hasil pengujian menunjukkan bahwa sistem memiliki rata-rata waktu inferensi sebesar 142,47 ms dengan kecepatan rata-rata 6,46 frame per detik (FPS) dan akurasi klasifikasi mencapai 98,48%. Dengan implementasi sistem ini, diharapkan dapat meningkatkan efisiensi produksi, memperkuat kontrol kualitas di industri tekstil, mengurangi intervensi manual, dan menurunkan potensi kerugian akibat produk cacat.
Abstract
The textile industry plays a crucial role in the national economy, facing significant challenges in maintaining product quality to meet consumer satisfaction. Production defects, such as rare defects and slap defects in fabrics, are key factors that affect the quality of textile products. This research aims to develop an automated fabric defect inspection system using digital image processing and machine learning methods. The system is designed to be integrated into fabric winding machines as an initial inspection system before the fabric is distributed. The methods used include supervised learning for fabric image classification, utilizing Google Teachable Machine software and the Convolutional Neural Network (CNN) algorithm implemented with OpenCV. The hardware used consists of a Logitech D320 webcam for image acquisition and a Raspberry Pi-3B as the image processor. The system was tested to detect three categories of fabric: good fabric, rare defects, and slap defects. The test results showed that the system achieved an average inference time of 142.47 ms with an average speed of 6.46 frames per second (FPS) and a classification accuracy of 98.48%. With the implementation of this system, it is expected to enhance production efficiency, strengthen quality control in the textile industry, reduce manual intervention, and decrease potential losses due to defective products
(Peer Review) PENERAPAN AKUNTANSI NIRLABA BERDASARKAN PSAK NO. 45 (STUDI KASUS PADA MASJID AL-BAITUL AMIEN DI JEMBER)
No full textThis study aims to find out how financial management in mosques and see how the method of recording is related to the standards issued by the Indonesian Accounting Association (IAI) in financial reporting for non-profit organizations namely PSAK 45 at Al-Baitul Amien mosque in Jember. The author in conducting this research uses qualitative methods. Data collected by using interviews and documents by looking directly at the financial statements that have been presented by the mosque management. Interviews at the Al-Baitul Amien Mosque in Jember were conducted with the treasurer, financial staff and takmir of the mosque. The results of this study indicate that mosque administrators have managed finances openly as a form of accountability or financial accountability of the mosque by recording cash receipts and disbursements. Financial management is well recorded even though it is still simple. Regarding PSAK 45, mosque administrators have not recorded according to PSAK 45 because these standards are recognized as having never been heard an
(Peer Review + Similarity) PENERAPAN AKUNTANSI NIRLABA BERDASARKAN PSAK NO. 45 (STUDI KASUS PADA MASJID AL-BAITUL AMIEN DI JEMBER)
No full textThis study aims to find out how financial management in mosques and see how the method of recording is related to the standards issued by the Indonesian Accounting Association (IAI) in financial reporting for non-profit organizations namely PSAK 45 at Al-Baitul Amien mosque in Jember. The author in conducting this research uses qualitative methods. Data collected by using interviews and documents by looking directly at the financial statements that have been presented by the mosque management. Interviews at the Al-Baitul Amien Mosque in Jember were conducted with the treasurer, financial staff and takmir of the mosque. The results of this study indicate that mosque administrators have managed finances openly as a form of accountability or financial accountability of the mosque by recording cash receipts and disbursements. Financial management is well recorded even though it is still simple. Regarding PSAK 45, mosque administrators have not recorded according to PSAK 45 because these standards are recognized as having never been heard and introduced to mosque administrators
PENERAPAN AKUNTANSI NIRLABA BERDASARKAN PSAK NO. 45 (STUDI KASUS PADA MASJID AL-BAITUL AMIEN DI JEMBER)
No full textThis study aims to find out how financial management in mosques and see how the method of recording is related to the standards issued by the Indonesian Accounting Association (IAI) in financial reporting for non-profit organizations namely PSAK 45 at Al-Baitul Amien mosque in Jember. The author in conducting this research uses qualitative methods. Data collected by using interviews and documents by looking directly at the financial statements that have been presented by the mosque management. Interviews at the Al-Baitul Amien Mosque in Jember were conducted with the treasurer, financial staff and takmir of the mosque. The results of this study indicate that mosque administrators have managed finances openly as a form of accountability or financial accountability of the mosque by recording cash receipts and disbursements. Financial management is well recorded even though it is still simple. Regarding PSAK 45, mosque administrators have not recorded according to PSAK 45 because these standards are recognized as having never been heard and introduced to mosque administrators.
Keywords: Mosque, PSAK No. 45, and SA
KOMODIFIKASI BUDAYA MINUM KOPI DI KEDAI SANG PEJOANG LEMBANG
No full textABSTRAK
Budaya minum kopi sambil menyaksikan live music saat ini menjadi trend dan marak dimana-mana khusunya di kedai Kopi Sang Pejoang kota Lembang. Teori yang digunakan dalam penelitian ini adalah teori komodifikasi oleh Karl Marx dan Vincent Mosco. Teori ini digunakan untuk mendeskripsikan bagaimana budaya minum kopi di kedai Kopi Sang Pejoang Lembang dan pengaruhnya yang didapatkan melalui live music terhadap aktivitas yang terjadi serta menjelaskan perubahan setelah adanya komodifikasi. Penelitian ini menggunakan metode penelitian kualitatif di mana penulis disini mendeskripsikan hasil analisis data melalui observasi, wawancara, dan dokumentasi. Adapun hasil penelitian yang dihasilkan adalah 1) budaya minum kopi, 2) pengaruh live music, dan 3) gaya hidup yang terjadi di kedai kopi Sang Pejoang Lembang.
Kata Kunci : Kopi, Live music, Komodifikasi.
ABSTRACT
The culture of drinking coffee while watching live music is now trendy and rife everywhere, especially at the Sang Pejoang Coffee shop in Lembang. The theory used in this study is the theory of commodification by Karl Marx and Vincent Mosco. This theory is used to describe how the culture of drinking coffee at the Kopi Sang Pejoang Lembang shop and its influence through live music on the activities that occur and explain the changes after the commodification. This study uses qualitative research methods where the author here describes the results of data analysis through observation, interviews, and documentation. The results of the research are 1) the culture of drinking coffee, 2) the influence of live music, and 3) the lifestyle that occurs at the coffee shop Sang Pejoang Lembang.
Keywords: Coffee, Live music, Commodification
