Melola Discovery

← Melola Discovery

Akses terbuka Jurnal SINTA 1

Resource optimization of approximate convolutional neural network-based accelerator on FPGA platform

Bulletin of Electrical Engineering and Informatics · Vol. 15 No. 2 (2026) · hlm. 1049–1060

DOI
10.11591/eei.v15i2.11142
ISSN
2089-3191, 2302-9285
Terbit
2026-04-01
Penerbit
Institute of Advanced Engineering and Science (IAES)
Bahasa
en
Lisensi
creativecommons.org/licenses/by-sa/4.0/

Abstrak

A significant number of machine learning techniques use convolutional neural networks (CNN). The hardware acceleration is essential due to the tremendous computation demands of CNNs, as well as the need for improved energy performance and lower usage response time. This manuscript presents the resource-optimized CNN-based hardware accelerator on a field-programmable gate array (FPGA) platform. The design uses LeNet-5 architecture for handwritten digits classification using the MNIST dataset. The CNN accelerator uses three different optimization approaches in this work, including fixed-point (FP) data optimization with shortened bits, approximate multiply-accumulate (MAC) operations, and loop unrolling features with a pipelining mechanism to optimize the hardware resources. These approaches improve the latency and resources, and overall performance of the CNN architecture. The CNN-based accelerator is designed and implemented on the Xilinx Zynq platform with the high-level synthesis (HLS) tool. The proposed MAC unit obtains a latency of 3.58 ms, with a frequency of 120.69 MHz on chip. The design uses only 96 block random access memory (BRAMs), digital signal processing (DSP) units of 106 and obtains the accuracy of 99.01%. The proposed accelerator improves the performance over state-of-the-art accelerators in concerning the area, power and accuracy.

Kata kunci

Jaringan kolaborasi para penulis

23 penulis · 62 tautan kepenulisan bersama · 25 lintas organisasi

Arahkan kursor atau ketuk sebuah nama untuk menyorot rekan penulisnya. Klik dua kali untuk membuka halaman penulis.

  • Dayananda Sagar College of Engineering
  • B.M.S. College of Engineering
  • R.V. College of Engineering
  • Visvesvaraya Technological University
  • PES University
  • Don Bosco Institute of Technology
  • Ramaiah Institute of Technology
  • Organisasi lain
  • Afiliasi tidak diketahui
  • Organisasi berbeda
  • Organisasi sama
  • Afiliasi tidak diketahui
  • Garis lebih tebal = lebih banyak artikel bersama · lingkaran lebih besar = lebih banyak artikel
Tampilkan sebagai tabel
Rekan penulisOrganisasiArtikel bersama
Ambuja KrishnappaB.M.S. College of Engineering2
Trupti Shripad TagareDayananda Sagar College of Engineering1
Santhosh Kumar RamachandragowdaDayananda Sagar College of Engineering1
Shashi Raj KDayananda Sagar College of Engineering1
Aswatha Anoor RangappaDayananda Sagar College of Engineering1
Shruthi MaheshappaDayananda Sagar College of Engineering1
Druva Kumar SiddarajuDayananda Sagar College of Engineering1
Narasimha Murthy Pokale KavyaVisvesvaraya Technological University1
Amith Shekhar ChandrashekharAfiliasi tidak diketahui1
Sarala D VB.M.S. College of Engineering1
Rajani Kallhalli ChannarayappaAfiliasi tidak diketahui1
Bellary KursheedDon Bosco Institute of Technology1
Gauri Sameer RapatePES University1
Sarala Duggonahalli VeereshB.M.S. College of Engineering1
Lakshminarayana MunirathnamRamaiah Institute of Technology1
S RashmiRV University1
Suraksha PrakashAfiliasi tidak diketahui1
Reshma ShafiDayananda Sagar College of Engineering1

Afiliasi berasal dari OpenAlex; metadata OAI-PMH jurnal tidak memuatnya. Penulis tanpa ID OpenAlex dicocokkan berdasarkan nama, sehingga dua orang bisa tergabung atau satu orang bisa terpisah.

Sumber metadata: OpenAlex API (jurnal SINTA, ADR 0048) https://openalex.org/S2765016208, pertama di-harvest 19 Nov 2026, terakhir terlihat 19 Nov 2026.
Metadata asli (oai_dc)
<oai_dc:dc xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/"><dc:title xml:lang="en">Resource optimization of approximate convolutional neural network-based accelerator on FPGA platform</dc:title><dc:creator>Pooja Alana Puttaswamy</dc:creator><dc:creator>Kasaragod Poornima Kamath</dc:creator><dc:creator>Priyadarshini Jainapur</dc:creator><dc:creator>Karanam Sunil Kumar</dc:creator><dc:creator>Kumar Puttaswamy Gowda</dc:creator><dc:subject>convolutional neural network accelerator</dc:subject><dc:subject>FPGA acceleration</dc:subject><dc:subject>resource optimization</dc:subject><dc:subject>loop unrolling</dc:subject><dc:subject>pipelining</dc:subject><dc:subject>LeNet-5</dc:subject><dc:subject>handwritten digit recognition</dc:subject><dc:subject>MNIST</dc:subject><dc:subject>high-level synthesis</dc:subject><dc:subject>Xilinx Zynq</dc:subject><dc:description xml:lang="en">A significant number of machine learning techniques use convolutional neural networks (CNN). The hardware acceleration is essential due to the tremendous computation demands of CNNs, as well as the need for improved energy performance and lower usage response time. This manuscript presents the resource-optimized CNN-based hardware accelerator on a field-programmable gate array (FPGA) platform. The design uses LeNet-5 architecture for handwritten digits classification using the MNIST dataset. The CNN accelerator uses three different optimization approaches in this work, including fixed-point (FP) data optimization with shortened bits, approximate multiply-accumulate (MAC) operations, and loop unrolling features with a pipelining mechanism to optimize the hardware resources. These approaches improve the latency and resources, and overall performance of the CNN architecture. The CNN-based accelerator is designed and implemented on the Xilinx Zynq platform with the high-level synthesis (HLS) tool. The proposed MAC unit obtains a latency of 3.58 ms, with a frequency of 120.69 MHz on chip. The design uses only 96 block random access memory (BRAMs), digital signal processing (DSP) units of 106 and obtains the accuracy of 99.01%. The proposed accelerator improves the performance over state-of-the-art accelerators in concerning the area, power and accuracy.</dc:description><dc:publisher>Institute of Advanced Engineering and Science (IAES)</dc:publisher><dc:date>2026-04-01</dc:date><dc:type>info:eu-repo/semantics/article</dc:type><dc:format>application/pdf</dc:format><dc:identifier>https://doi.org/10.11591/eei.v15i2.11142</dc:identifier><dc:identifier>10.11591/eei.v15i2.11142</dc:identifier><dc:source>Bulletin of Electrical Engineering and Informatics; Vol 15 No 2 (2026); 1049-1060</dc:source><dc:source>2089-3191</dc:source><dc:source>2302-9285</dc:source><dc:language>en</dc:language><dc:relation>https://beei.org/index.php/EEI/article/download/11142/4696</dc:relation><dc:rights>https://creativecommons.org/licenses/by-sa/4.0/</dc:rights></oai_dc:dc>