An Integrated Lightweight Neural Network Design and FPGA-Accelerated Edge Computing for Chili Pepper Variety and Origin Identification via an E-Nose

A chili pepper variety and origin detection system that integrates a field-programmable gate array (FPGA) with an electronic nose (e-nose) is proposed in this paper to address the issues of variety confusion and origin ambiguity in the chili pepper market. The system uses the AIRSENSE PEN3 e-nose fr...

Full description

Saved in:
Bibliographic Details
Main Authors: Ziyu Guo, Yong Yin, Haolin Gu, Guihua Peng, Xueya Wang, Ju Chen, Jia Yan
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Foods
Subjects:
Online Access:https://www.mdpi.com/2304-8158/14/15/2612
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849405706965352448
author Ziyu Guo
Yong Yin
Haolin Gu
Guihua Peng
Xueya Wang
Ju Chen
Jia Yan
author_facet Ziyu Guo
Yong Yin
Haolin Gu
Guihua Peng
Xueya Wang
Ju Chen
Jia Yan
author_sort Ziyu Guo
collection DOAJ
description A chili pepper variety and origin detection system that integrates a field-programmable gate array (FPGA) with an electronic nose (e-nose) is proposed in this paper to address the issues of variety confusion and origin ambiguity in the chili pepper market. The system uses the AIRSENSE PEN3 e-nose from Germany to collect gas data from thirteen different varieties of chili peppers and two specific varieties of chili peppers originating from seven different regions. Model training is conducted via the proposed lightweight convolutional neural network ChiliPCNN. By combining the strengths of a convolutional neural network (CNN) and a multilayer perceptron (MLP), the ChiliPCNN model achieves an efficient and accurate classification process, requiring only 268 parameters for chili pepper variety identification and 244 parameters for origin tracing, with 364 floating-point operations (FLOPs) and 340 FLOPs, respectively. The experimental results demonstrate that, compared with other advanced deep learning methods, the ChiliPCNN has superior classification performance and good stability. Specifically, ChiliPCNN achieves accuracy rates of 94.62% in chili pepper variety identification and 93.41% in origin tracing tasks involving Jiaoyang No. 6, with accuracy rates reaching as high as 99.07% for Xianjiao No. 301. These results fully validate the effectiveness of the model. To further increase the detection speed of the ChiliPCNN, its acceleration circuit is designed on the Xilinx Zynq7020 FPGA from the United States and optimized via fixed-point arithmetic and loop unrolling strategies. The optimized circuit reduces the latency to 5600 ns and consumes only 1.755 W of power, significantly improving the resource utilization rate and processing speed of the model. This system not only achieves rapid and accurate chili pepper variety and origin detection but also provides an efficient and reliable intelligent agricultural management solution, which is highly important for promoting the development of agricultural automation and intelligence.
format Article
id doaj-art-db5730959fbd4bdcad511cdccf916df5
institution Kabale University
issn 2304-8158
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Foods
spelling doaj-art-db5730959fbd4bdcad511cdccf916df52025-08-20T03:36:35ZengMDPI AGFoods2304-81582025-07-011415261210.3390/foods14152612An Integrated Lightweight Neural Network Design and FPGA-Accelerated Edge Computing for Chili Pepper Variety and Origin Identification via an E-NoseZiyu Guo0Yong Yin1Haolin Gu2Guihua Peng3Xueya Wang4Ju Chen5Jia Yan6College of Artificial Intelligence, Southwest University, Chongqing 400715, ChinaChili Pepper Research Institute, Guizhou Academy of Agricultural Sciences, Guiyang 550006, ChinaCollege of Artificial Intelligence, Southwest University, Chongqing 400715, ChinaChili Pepper Research Institute, Guizhou Academy of Agricultural Sciences, Guiyang 550006, ChinaChili Pepper Research Institute, Guizhou Academy of Agricultural Sciences, Guiyang 550006, ChinaChili Pepper Research Institute, Guizhou Academy of Agricultural Sciences, Guiyang 550006, ChinaCollege of Artificial Intelligence, Southwest University, Chongqing 400715, ChinaA chili pepper variety and origin detection system that integrates a field-programmable gate array (FPGA) with an electronic nose (e-nose) is proposed in this paper to address the issues of variety confusion and origin ambiguity in the chili pepper market. The system uses the AIRSENSE PEN3 e-nose from Germany to collect gas data from thirteen different varieties of chili peppers and two specific varieties of chili peppers originating from seven different regions. Model training is conducted via the proposed lightweight convolutional neural network ChiliPCNN. By combining the strengths of a convolutional neural network (CNN) and a multilayer perceptron (MLP), the ChiliPCNN model achieves an efficient and accurate classification process, requiring only 268 parameters for chili pepper variety identification and 244 parameters for origin tracing, with 364 floating-point operations (FLOPs) and 340 FLOPs, respectively. The experimental results demonstrate that, compared with other advanced deep learning methods, the ChiliPCNN has superior classification performance and good stability. Specifically, ChiliPCNN achieves accuracy rates of 94.62% in chili pepper variety identification and 93.41% in origin tracing tasks involving Jiaoyang No. 6, with accuracy rates reaching as high as 99.07% for Xianjiao No. 301. These results fully validate the effectiveness of the model. To further increase the detection speed of the ChiliPCNN, its acceleration circuit is designed on the Xilinx Zynq7020 FPGA from the United States and optimized via fixed-point arithmetic and loop unrolling strategies. The optimized circuit reduces the latency to 5600 ns and consumes only 1.755 W of power, significantly improving the resource utilization rate and processing speed of the model. This system not only achieves rapid and accurate chili pepper variety and origin detection but also provides an efficient and reliable intelligent agricultural management solution, which is highly important for promoting the development of agricultural automation and intelligence.https://www.mdpi.com/2304-8158/14/15/2612e-noseFPGA-acceleratedlightweight CNNchili peppervariety identificationorigin tracing
spellingShingle Ziyu Guo
Yong Yin
Haolin Gu
Guihua Peng
Xueya Wang
Ju Chen
Jia Yan
An Integrated Lightweight Neural Network Design and FPGA-Accelerated Edge Computing for Chili Pepper Variety and Origin Identification via an E-Nose
Foods
e-nose
FPGA-accelerated
lightweight CNN
chili pepper
variety identification
origin tracing
title An Integrated Lightweight Neural Network Design and FPGA-Accelerated Edge Computing for Chili Pepper Variety and Origin Identification via an E-Nose
title_full An Integrated Lightweight Neural Network Design and FPGA-Accelerated Edge Computing for Chili Pepper Variety and Origin Identification via an E-Nose
title_fullStr An Integrated Lightweight Neural Network Design and FPGA-Accelerated Edge Computing for Chili Pepper Variety and Origin Identification via an E-Nose
title_full_unstemmed An Integrated Lightweight Neural Network Design and FPGA-Accelerated Edge Computing for Chili Pepper Variety and Origin Identification via an E-Nose
title_short An Integrated Lightweight Neural Network Design and FPGA-Accelerated Edge Computing for Chili Pepper Variety and Origin Identification via an E-Nose
title_sort integrated lightweight neural network design and fpga accelerated edge computing for chili pepper variety and origin identification via an e nose
topic e-nose
FPGA-accelerated
lightweight CNN
chili pepper
variety identification
origin tracing
url https://www.mdpi.com/2304-8158/14/15/2612
work_keys_str_mv AT ziyuguo anintegratedlightweightneuralnetworkdesignandfpgaacceleratededgecomputingforchilipeppervarietyandoriginidentificationviaanenose
AT yongyin anintegratedlightweightneuralnetworkdesignandfpgaacceleratededgecomputingforchilipeppervarietyandoriginidentificationviaanenose
AT haolingu anintegratedlightweightneuralnetworkdesignandfpgaacceleratededgecomputingforchilipeppervarietyandoriginidentificationviaanenose
AT guihuapeng anintegratedlightweightneuralnetworkdesignandfpgaacceleratededgecomputingforchilipeppervarietyandoriginidentificationviaanenose
AT xueyawang anintegratedlightweightneuralnetworkdesignandfpgaacceleratededgecomputingforchilipeppervarietyandoriginidentificationviaanenose
AT juchen anintegratedlightweightneuralnetworkdesignandfpgaacceleratededgecomputingforchilipeppervarietyandoriginidentificationviaanenose
AT jiayan anintegratedlightweightneuralnetworkdesignandfpgaacceleratededgecomputingforchilipeppervarietyandoriginidentificationviaanenose
AT ziyuguo integratedlightweightneuralnetworkdesignandfpgaacceleratededgecomputingforchilipeppervarietyandoriginidentificationviaanenose
AT yongyin integratedlightweightneuralnetworkdesignandfpgaacceleratededgecomputingforchilipeppervarietyandoriginidentificationviaanenose
AT haolingu integratedlightweightneuralnetworkdesignandfpgaacceleratededgecomputingforchilipeppervarietyandoriginidentificationviaanenose
AT guihuapeng integratedlightweightneuralnetworkdesignandfpgaacceleratededgecomputingforchilipeppervarietyandoriginidentificationviaanenose
AT xueyawang integratedlightweightneuralnetworkdesignandfpgaacceleratededgecomputingforchilipeppervarietyandoriginidentificationviaanenose
AT juchen integratedlightweightneuralnetworkdesignandfpgaacceleratededgecomputingforchilipeppervarietyandoriginidentificationviaanenose
AT jiayan integratedlightweightneuralnetworkdesignandfpgaacceleratededgecomputingforchilipeppervarietyandoriginidentificationviaanenose