Garuda - Garba Rujukan Digital

PERBANDINGAN OPTIMIZER, BATCH SIZE DAN EPOCH PADA METODE CONVOLUTION NEURAL NETWORK Ramadhan, Ferry Muhamad; Riwurohi, Jan Everhard; Gunawan, Hendry
Jurnal Sistem Informasi Vol 11 No 2 (2024)
Publisher : Universitas Serang Raya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30656/jsii.v11i2.9249

Buffalo meat and beef are two types of red meat that are widely consumed by the public. The demand for meat increases every year. However, not all types of meat can be eaten by Indonesians, such as pork, so the price of pork in Indonesia is lower than the price of beef and buffalo. In general, the texture and colour of pork, beef and buffalo are almost the same. In the introduction of meat, it is only done directly from the colour, texture, and fibre of the type of meat. However, meat circulating in the community is often mixed between beef, buffalo meat and pork. Distinguishing beef, buffalo and pork must first recognise the characteristics of each type of meat, because there are limitations to the human sense of sight in distinguishing between them. In the use of technology with the help of digital images to determine the most optimal optimizer, batch size and epoch in meat classification, using the Convolutional Neural Network (CNN) method with NasNetmobil Architecture. The data set used is 3000 images divided into three classes, with a division of 2400 training data images, 300 testing data images, 300 validation data images. The results showed that the Adam optimiser, batch size 62 and epoch 20 produced an accuracy of 99.00% and a loss value of 0.0243. Keywords: Convolutional Neural Network, Buffalo and Beef Classification,

Forecasting the Electricity Consumptions of PLN UP3 Cengkareng using Deep Learning Dewi, Novia; Riwurohi, Jan Everhard
Jurnal Sisfokom (Sistem Informasi dan Komputer) Vol 13, No 1 (2024): MARET
Publisher : ISB Atma Luhur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32736/sisfokom.v13i1.1849

The consumption of electrical energy for the community every year has increased including the electricity consumption of PLN UP3 Cengkareng customers. Therefore, PLN UP3 Cengkareng must supply electricity to customers in all categories such as Social Category, Household Category, Business Category, Industry Category and Government Category. With customer needs that continue to increase, it is necessary to forecast future electricity needs, so that PLN UP3 Cengkareng can provide the required electrical power. For this reason, it is necessary to predict the electricity demand. This research was conducted to forecast the electricity demand of UP3 Cengkareng by using the Deep Learning Model Long Short-Term Memory (LSTM). The data set used in this study was taken from the PLN UP3 Cengkareng information system, for 10 years, the period from 2012 to 2021. The data used is divided into 2 categories, namely 70% training data and 30% testing data. The results obtained from this prediction are 96,689, with an average neuron value of 32 and an epoch value of 10.

Intergrasi Sistem Minimum IoT Yang Handal Untuk Pertanian Berbasiskan Mikrokontroler dan Protokol Komunikasi Tatang Wirawan Wisjhnuadji; Arsanto Narendro; Yani Prabowo; Jan Everhard; Suwasti Broto
OKTAL : Jurnal Ilmu Komputer dan Sains Vol 3 No 09 (2024): OKTAL : Jurnal Ilmu Komputer Dan Sains
Publisher : CV. Multi Kreasi Media

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

Traditional agriculture refers to farming that utilizes natural and local techniques, relying little on modern technology or chemicals. However, traditional agricultural systems face many challenges, including low productivity; traditional farming may not be as productive as modern methods. Additionally, dependence on weather conditions poses a significant barrier to production. To improve the quality and productivity of traditional agriculture, methodologies such as developing smart farming systems can be implemented. Smart farming applies technology in agriculture to enhance efficiency, productivity, and sustainability through sensors and IoT devices to manage and monitor agricultural activities more effectively. The smart farming system to be developed is based on the SCADA concept, where control of devices such as temperature sensors, soil moisture, light, and rainfall sensors, as well as actuators, is managed via the ModBus protocol based on the RS-485 RTU module. For controllers connected to the internet server, the ESP32 module will be used. Users can access the system using smartphones or laptops equipped with a wireless modem to establish remote connections via the internet. Thus, the application of this technology can significantly increase agricultural productivity and improve the efficiency of managing fields and crops. Users do not need to be physically present on-site, as the system can be controlled and monitored remotely from a distance.

Smart Strategies in Hardware Provisioning for Ai Solutions in The Cloud Yusuf Hambali; Jan Everhard Riwurohi; Victor Akbar
Eduvest - Journal of Universal Studies Vol. 4 No. 12 (2024): Journal Eduvest - Journal of Universal Studies
Publisher : Green Publisher Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59188/eduvest.v4i12.43140

Rapid developments in artificial intelligence (AI) have driven the need for more efficient and powerful computing infrastructure, especially in cloud environments. This research explores smart strategies in providing hardware for AI solutions in the cloud, focusing on the latest innovations in AI hardware such as neuromorphic chips, FPGAs, and ASICs. Through a comprehensive analysis of the current literature, performance benchmarks, and implementation case studies, the study identifies several key strategies. Key findings include the effectiveness of hybrid architectures that combine different types of AI hardware, the potential for resource disaggregators and composable architectures to improve flexibility and efficiency, and the importance of specific acceleration for different phases in the AI pipeline. The study also emphasizes the significance of performance optimization and energy efficiency, as well as the integration of security and data privacy features in AI hardware design. Challenges such as standardization, scalability, and complexity management are discussed along with future opportunities in green AI and computing-in-memory. In conclusion, implementing a smart strategy in the provision of AI hardware in the cloud requires a holistic approach that considers workload diversity, architectural flexibility, energy efficiency, and security aspects. This research provides valuable insights for cloud service providers, hardware manufacturers, and AI practitioners in optimizing infrastructure to support AI innovation in the cloud computing era.

Next-Generation CPU Architectures: A Study of the Influence of Nanometer Technology on Computer Performance Ija Sudija; Jan everhard riwurohi; Muhamad Masruin Masad
Eduvest - Journal of Universal Studies Vol. 4 No. 12 (2024): Journal Eduvest - Journal of Universal Studies
Publisher : Green Publisher Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59188/eduvest.v4i12.44711

Nanometer technology has become one of the most significant innovations in the advancement of modern CPU architecture, enabling substantial improvements in computational performance, energy efficiency, and transistor density. This study examines the impact of 7nm, 5nm, and 3nm technology implementation on CPU performance under various workload scenarios, including multitasking, graphics rendering, and artificial intelligence-based applications. Based on a series of experimental tests, the findings indicate that reducing transistor size directly increases processor speed by up to 30% while reducing power consumption by 20%. However, challenges such as heat dissipation and power leakage become more pronounced with technology below 5nm. Several proposed solutions include the development of more advanced cooling systems and the use of alternative semiconductor materials, such as graphene, to mitigate power leakage. This research provides valuable insights into the future development of CPU architecture and its impact on the technology industry as a whole.

Peningkatan Keterampilan Microsoft Word dan Powerpoint Untuk Staf Administrasi Pada Gereja Orthodox Indonesia Mardi Hardjianto; Agnes Aryasanti; Jan Everhard; Jeremy Jonathan; Hayati, Putri
KRESNA: Jurnal Riset dan Pengabdian Masyarakat Vol 3 No 1 (2023): Jurnal KRESNA Mei 2023
Publisher : DRPM Universitas Budi Luhur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36080/kresna.v3i1.65

Kebutuhan lembaga atau organisasi masyarakat di era informasi saat ini adalah bagaimana mampu membuat laporan dalam bentuk digital dan juga mampu menampilkannya dalam bentuk digital. Sayangnya, kebutuhan tersebut masih belum dirasakan oleh masyarakat luas. Mitra pengabdian kepada masyarakat (PKM) saat ini adalah Gereja Orthodox Indonesia, sebuah organisasi masyarakat yang memiliki catatan tertulis yang harus diinventarisasi dengan baik dan suatu saat dapat disajikan dengan menggunakan media komputer. Permasalahan yang dihadapi Gereja Orthodox adalah tidak semua staf administrasi memahami dengan baik penggunaan teknologi komputer, sehingga proses administrasi tidak dapat dilakukan dengan cepat. Sebelum pelatihan nilai rata-rata pre-test peserta sebesar 59, setelah pelatihan nilai rata-rata post-test adalah 85.38. Hal ini membuktikan terjadi peningkatan keterampilan dan pengetahuan staf administrasi setelah mengikuti pelatihan Microsoft Word dan Powerpoint.

Pelatihan Peningkatan Keterampilan Administrasi Menggunakan Microsoft Excel Pada Siswa-siswi SMK Triguna 1956 Kusumawardani, Ratna; Yulianawati; Mohammad Syafrullah; Purwanto, Purwanto; Jan Everhard
KRESNA: Jurnal Riset dan Pengabdian Masyarakat Vol 3 No 1 (2023): Jurnal KRESNA Mei 2023
Publisher : DRPM Universitas Budi Luhur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36080/kresna.v3i1.68

Penerapan Microsoft Office sudah banyak dilakukan pada semua bidang, salah satunya bidang akademis dalam pengolahan data administrasi pada sebuah SMK namun tidak semua peserta didik menguasai dalam memanfaatkan Microsoft Excel. Institusi ini memiliki peran untuk mendidik para peserta didik yang siap untuk bekerja sesuai dengan skill yang dimilikinya dimana pada jaman sekarang amat sulit mencari sebuah pekerjaan jika tidak memiliki skill atau keterampilan. Untuk memumpuni hal tersebut, maka kami bekerjasama dengan SMK Triguna 1956 untuk melakukan pelatihan administasi bagi peserta didik menggunakan Microsoft Excel. Kegiatan ini bertujuan agar para peserta didik memiliki keterampilan dibidang teknologi khususnya dalam mengoperasikan Microsoft Excel sehingga dapat menjadi bekal untuk mencari pekerjaan. Pelatihan ini menerapkan metode praktikum dengan melib Penerapan Microsoft Office sudah banyak dilakukan pada semua bidang, salah satunya bidang akademis dalam pengolahan data administrasi pada sebuah SMK namun tidak semua peserta didik menguasai dalam memanfaatkan Microsoft Excel. Institusi ini memiliki peran untuk mendidik para peserta didik yang siap untuk bekerja sesuai dengan skill yang dimilikinya dimana pada jaman sekarang amat sulit mencari sebuah pekerjaan jika tidak memiliki skill atau keterampilan. Untuk memumpuni hal tersebut, maka kami bekerjasama dengan SMK Triguna 1956 untuk melakukan pelatihan administasi bagi peserta didik menggunakan Microsoft Excel. Kegiatan ini bertujuan agar para peserta didik memiliki keterampilan dibidang teknologi khususnya dalam mengoperasikan Microsoft Excel sehingga dapat menjadi bekal untuk mencari pekerjaan. Pelatihan ini menerapkan metode praktikum dengan melibatkan 30 orang peserta didik yang dilaksanakan di Laboratorium Komputer Universitas Budi Luhur Jakarta. Berdasarkan data kuesioner yang sudah diolah, menunjukan bahwa yang memahami materi pelatihan sebesar 92%. Diharapkan hasil kegiatan ini dapat menambah keterampilan atau skill para peserta didik untuk melamar pekerjaan usai tamat sekolah. atkan 30 orang peserta didik yang dilaksanakan di Laboratorium Komputer Universitas Budi Luhur Jakarta. Berdasarkan data kuesioner yang sudah diolah, menunjukan bahwa yang memahami materi pelatihan sebesar 92%. Diharapkan hasil kegiatan ini dapat menambah keterampilan atau skill para peserta didik untuk melamar pekerjaan usai tamat sekolah.

Penerapan Konsep Eco Enzyme dan Kerajinan Tangan dari Limbah Rumah Tangga Pada Kelurahan Pesanggrahan Kusumawardani, Ratna; Tutik Sri Susilowati; Triana Anggraini; Everhard, Jan; Samidi, Samidi; Abdullah, Indra Nugraha
KRESNA: Jurnal Riset dan Pengabdian Masyarakat Vol 4 No 1 (2024): Jurnal KRESNA Mei 2024
Publisher : DRPM Universitas Budi Luhur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36080/kresna.v4i1.105

Setiap tahun volume sampah di Indonesia meningkat yang disebabkan oleh beberapa faktor yakni pertumbuhan populasi yang cepat, adanya urbanisasi dan konsumsi masyarakat tinggi. Hal tersebut menyebabkan produksi sampah organik dan anorganik melonjak namun tidak diiringi dengan wawasan masyarakat dalam memilih dan mengelola sampah tersebut. Berdasarkan permasalahan yang dipaparkan, maka peneliti menjalin kerjasama dengan Kelurahan Pesanggrahan sebagai mitra masyarakat guna mengedukasi dalam memanfaatkan sampah organik dengan konsep eco enzyme dan sampah anorganik dengan konsep kerajinan bak sampah yang berasal dari limbah rumah tangga. Sampah organik yang dapat didaur ulang dari limbah rumah tangga, salah satunya dari sisa makanan atau buah-buahan sedangkan sampah anorganik yang dapat dimanfaatkan dari limbah rumah tangga, salah satunya tutup botol sehingga dalam proses penguraian tersebut memakan waktu yang lama. Metode yang diterapkan pada pelatihan ini menggunakan metode ceramah guna menjelaskan dampak dari sampah organik dan anorganik dan praktek secara langsung dalam pemanfaatan limbah rumah tangga serta tanya jawab. Berdasarkan hasil kuesioner yang telah diolah setelah selesai pelatihan, menunjukkan sebanyak 90% masyarakat memperoleh wawasan baru terkait limbah organik yang dapat dijadikan pupuk organik dan 97% masyarakat memperoleh wawasan baru bahwa limbah anorganik yang dapat dijadikan kerajinan bak sampah sehingga masyarakat menghasilkan pendapatan tambahan dari produk ekonomis tersebut.

PERBANDINGAN OPTIMIZER, BATCH SIZE DAN EPOCH PADA METODE CONVOLUTION NEURAL NETWORK Ramadhan, Ferry Muhamad; Riwurohi, Jan Everhard; Gunawan, Hendry
Jurnal Sistem Informasi Vol 11 No 2 (2024)
Publisher : Universitas Serang Raya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30656/jsii.v11i2.9249

Buffalo meat and beef are two types of red meat that are widely consumed by the public. The demand for meat increases every year. However, not all types of meat can be eaten by Indonesians, such as pork, so the price of pork in Indonesia is lower than the price of beef and buffalo. In general, the texture and colour of pork, beef and buffalo are almost the same. In the introduction of meat, it is only done directly from the colour, texture, and fibre of the type of meat. However, meat circulating in the community is often mixed between beef, buffalo meat and pork. Distinguishing beef, buffalo and pork must first recognise the characteristics of each type of meat, because there are limitations to the human sense of sight in distinguishing between them. In the use of technology with the help of digital images to determine the most optimal optimizer, batch size and epoch in meat classification, using the Convolutional Neural Network (CNN) method with NasNetmobil Architecture. The data set used is 3000 images divided into three classes, with a division of 2400 training data images, 300 testing data images, 300 validation data images. The results showed that the Adam optimiser, batch size 62 and epoch 20 produced an accuracy of 99.00% and a loss value of 0.0243. Keywords: Convolutional Neural Network, Buffalo and Beef Classification,

The Role of Cache Memory In Enhancing Microprocessor Performance in PT. Srikandi Sinergi Sakti Hendarin Hendarin; Jan Everhard Riwurohi; Setyo Arief Arachman
Eduvest - Journal of Universal Studies Vol. 4 No. 12 (2024): Journal Eduvest - Journal of Universal Studies
Publisher : Green Publisher Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59188/eduvest.v4i12.43139

Cache memory in microprocessors has an important role in improving computer system performance by reducing data access time. This research aims to test the hypothesis that increasing the size and level of cache memory can significantly improve microprocessor performance. The research methodology involves a literature study on the concept of cache memory and experimental simulations using computer architecture simulators, such as Gem5, to model scenarios with varying cache sizes and levels. In these simulations, performance parameters such as memory access latency, throughput, and Instructions Per Cycle (IPC) were measured and analyzed. The results show that increasing cache size and level generally contributes towards improving microprocessor performance by reducing data access time. Further statistical analysis supports the hypothesis that there is a positive correlation between cache size and level and system efficiency. These findings provide useful insights in future microprocessor architecture design and memory system optimization.

Title

Found 25 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 25 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 25 Documents
Search