{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T17:13:20Z","timestamp":1790183600309,"version":"4.1.0"},"reference-count":38,"publisher":"MDPI AG","issue":"15","license":[{"start":{"date-parts":[[2025,7,25]],"date-time":"2025-07-25T00:00:00Z","timestamp":1753401600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["SWU-XDJH202319"],"award-info":[{"award-number":["SWU-XDJH202319"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Foods"],"abstract":"<jats:p>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.<\/jats:p>","DOI":"10.3390\/foods14152612","type":"journal-article","created":{"date-parts":[[2025,7,25]],"date-time":"2025-07-25T11:38:41Z","timestamp":1753443521000},"page":"2612","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["An Integrated Lightweight Neural Network Design and FPGA-Accelerated Edge Computing for Chili Pepper Variety and Origin Identification via an E-Nose"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-1282-259X","authenticated-orcid":false,"given":"Ziyu","family":"Guo","sequence":"first","affiliation":[{"name":"College of Artificial Intelligence, Southwest University, Chongqing 400715, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Yin","sequence":"additional","affiliation":[{"name":"Chili Pepper Research Institute, Guizhou Academy of Agricultural Sciences, Guiyang 550006, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8379-9309","authenticated-orcid":false,"given":"Haolin","family":"Gu","sequence":"additional","affiliation":[{"name":"College of Artificial Intelligence, Southwest University, Chongqing 400715, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guihua","family":"Peng","sequence":"additional","affiliation":[{"name":"Chili Pepper Research Institute, Guizhou Academy of Agricultural Sciences, Guiyang 550006, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xueya","family":"Wang","sequence":"additional","affiliation":[{"name":"Chili Pepper Research Institute, Guizhou Academy of Agricultural Sciences, Guiyang 550006, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ju","family":"Chen","sequence":"additional","affiliation":[{"name":"Chili Pepper Research Institute, Guizhou Academy of Agricultural Sciences, Guiyang 550006, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8012-5097","authenticated-orcid":false,"given":"Jia","family":"Yan","sequence":"additional","affiliation":[{"name":"College of Artificial Intelligence, Southwest University, Chongqing 400715, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,7,25]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Xu, J., Lin, J., Peng, S., Zhao, H., Wang, Y., Rao, L., Liao, X., and Zhao, L. (2023). Development of an HPLC-PDA method for the determination of capsanthin, zeaxanthin, lutein, \u03b2-cryptoxanthin and \u03b2-carotene simultaneously in chili peppers and products. Molecules, 28.","DOI":"10.3390\/molecules28052362"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Ahmad, R., Alqathama, A., Aldholmi, M., Riaz, M., Abdalla, A.N., Mostafa, A., Al-Said, H.M., Alqarni, A.M., Ullah, R., and Asgher, S.S. (2022). Gas chromatography-mass spectrometry (GC-MS) metabolites profiling and biological activities of various capsicum annum cultivars. Plants, 11.","DOI":"10.3390\/plants11081022"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1016\/j.foodchem.2017.10.031","article-title":"Optimized and validated method for simultaneous extraction, identification and quantification of flavonoids and capsaicin, along with isotopic composition, in hot peppers from different regions","volume":"267","author":"Feher","year":"2018","journal-title":"Food Chem."},{"key":"ref_4","first-page":"695","article-title":"Molecular biology of capsaicinoid biosynthesis in chili pepper (Capsicum spp.)","volume":"30","year":"2010","journal-title":"Plant Cell Rep."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"135488","DOI":"10.1016\/j.foodchem.2023.135488","article-title":"Multi-dimensional pungency and sensory profiles of powder and oil of seven chili peppers based on descriptive analysis and Scoville heat units","volume":"411","author":"Zhu","year":"2023","journal-title":"Food Chem."},{"key":"ref_6","first-page":"352","article-title":"Electronic nose for improved environmental methane monitoring","volume":"58","author":"Duc","year":"2023","journal-title":"Environ. Sci. Technol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1016\/j.tibtech.2016.08.005","article-title":"Artificial nose technology: Status and prospects in diagnostics","volume":"35","author":"Fitzgerald","year":"2017","journal-title":"Trends Biotechnol."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"112214","DOI":"10.1016\/j.foodres.2022.112214","article-title":"Electronic tongue and electronic nose for food quality and safety","volume":"162","author":"Lu","year":"2022","journal-title":"Food Res. Int."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1016\/j.lwt.2017.08.052","article-title":"Evaluation of the freshness of fresh-cut green bell pepper (Capsicum annuum var. grossum) using electronic nose","volume":"87","author":"Chen","year":"2018","journal-title":"LWT"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"106939","DOI":"10.1016\/j.compag.2022.106939","article-title":"Ultra-lightweight dynamic attention network combined with gas sensor for distinguishing the quality of rice","volume":"197","author":"Men","year":"2022","journal-title":"Comput. Electron. Agric."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"101262","DOI":"10.1016\/j.fochx.2024.101262","article-title":"Effects of different hot-air drying methods on the dynamic changes in color, nutrient and aroma quality of three chili pepper (Capsicum annuum L.) varieties","volume":"22","author":"Liu","year":"2024","journal-title":"Food Chem. X"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"113667","DOI":"10.1016\/j.lwt.2022.113667","article-title":"Preliminary study non-destructive sorting techniques for pepper (Capsicum annuum L.) using odor parameter","volume":"164","author":"Rasekh","year":"2022","journal-title":"LWT"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"107821","DOI":"10.1016\/j.jfca.2025.107821","article-title":"Aroma evaluation for chili pepper using an E-nose combined with a novel feature fusion technology based on machine learning","volume":"145","author":"Yan","year":"2025","journal-title":"J. Food Compos. Anal."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"138207","DOI":"10.1016\/j.foodchem.2023.138207","article-title":"Geographical traceability of soybean: An electronic nose coupled with an effective deep learning method","volume":"440","author":"Sun","year":"2024","journal-title":"Food Chem."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"7075","DOI":"10.1109\/JSEN.2023.3349139","article-title":"Determination of tea quality: A separate domain graph convolution network combined with an electronic nose","volume":"24","author":"Feng","year":"2024","journal-title":"IEEE Sens. J."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"143850","DOI":"10.1016\/j.foodchem.2025.143850","article-title":"An efficient method for chili pepper variety classification and origin tracing based on an electronic nose and deep learning","volume":"479","author":"Chen","year":"2025","journal-title":"Food Chem."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"137356","DOI":"10.1016\/j.snb.2025.137356","article-title":"Origin identification of Angelica dahurica using a bidirectional mixing network combined with an electronic nose system","volume":"429","author":"Wang","year":"2025","journal-title":"Sens. Actuators B Chem."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"108343","DOI":"10.1016\/j.compag.2023.108343","article-title":"An electronic nose based on adaptive fusion of transformer-ELM with active temperature modulation algorithm for accurate odor detection in refrigerators","volume":"214","author":"Sun","year":"2023","journal-title":"Comput. Electron. Agric."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"108038","DOI":"10.1016\/j.engappai.2024.108038","article-title":"A multilevel interleaved group attention-based convolutional network for gas detection via an electronic nose system","volume":"133","author":"Zhai","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"114692","DOI":"10.1016\/j.sna.2023.114692","article-title":"Identification of industrial exhaust based on an electronic nose with an interleaved grouped residual convolutional compression network","volume":"363","author":"Yang","year":"2023","journal-title":"Sens. Actuators A Phys."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1145\/2436256.2436271","article-title":"FPGA programming for the masses","volume":"56","author":"Bacon","year":"2013","journal-title":"Commun. ACM"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Sipola, T., Alatalo, J., Kokkonen, T., and Rantonen, M. (2022, January 27\u201329). Artificial intelligence in the IoT era: A review of edge AI hardware and software. Proceedings of the 31st Conference of Open Innovations Association (FRUCT), Helsinki, Finland.","DOI":"10.23919\/FRUCT54823.2022.9770931"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"107715","DOI":"10.1016\/j.compag.2023.107715","article-title":"FPGA\u2013accelerated CNN for real-time plant disease identification","volume":"207","author":"Luo","year":"2023","journal-title":"Comput. Electron. Agric."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"3740","DOI":"10.1109\/JSTARS.2022.3169330","article-title":"FPGA-based implementation of a CNN architecture for the on-board processing of very high-resolution remote sensing images","volume":"15","author":"Neris","year":"2022","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"21357","DOI":"10.1109\/JIOT.2022.3179016","article-title":"FitNN: A low-resource FPGA-based CNN accelerator for drones","volume":"9","author":"Zhang","year":"2022","journal-title":"IEEE Internet Things J."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1016\/j.micpro.2017.07.012","article-title":"Electronic nose system on the Zynq SoC platform","volume":"53","author":"Djelouat","year":"2017","journal-title":"Microprocess. Microsyst."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Mo, Z., Luo, D., Wen, T., Cheng, Y., and Li, X. (2021). FPGA implementation for odor identification with depthwise separable convolutional neural network. Sensors, 21.","DOI":"10.3390\/s21030832"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"28526","DOI":"10.1109\/JSEN.2023.3323943","article-title":"Multi-gas sensing electronic nose using memristor-based in-memory computing","volume":"23","author":"Tan","year":"2023","journal-title":"IEEE Sens. J."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Liu, B., Zhou, Y., Feng, L., Fu, H., and Fu, P. (2022). Hybrid CNN-SVM inference accelerator on FPGA using HLS. Electronics, 11.","DOI":"10.3390\/electronics11142208"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1016\/j.neucom.2021.07.009","article-title":"A mixed-kernel, variable-dimension memristive CNN for electronic nose recognition","volume":"461","author":"Chen","year":"2021","journal-title":"Neurocomputing"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"4086","DOI":"10.1109\/TNNLS.2020.3016901","article-title":"All-passive hardware implementation of multilayer perceptron classifiers","volume":"32","author":"Ananthakrishnan","year":"2021","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"268","DOI":"10.1109\/72.80252","article-title":"Performance surfaces of a single-layer perceptron","volume":"1","author":"Shynk","year":"1990","journal-title":"IEEE Trans. Neural Netw."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Chen, C.-C., Liu, Z., Yang, G., Wu, C.-C., and Ye, Q. (2020). An improved fault diagnosis using 1D-convolutional neural network model. Electronics, 10.","DOI":"10.20944\/preprints202011.0571.v1"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Peng, P., Zhao, X., Pan, X., and Ye, W. (2018). Gas classification using deep convolutional neural networks. Sensors, 1.","DOI":"10.3390\/s18010157"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"i169","DOI":"10.1093\/bioinformatics\/btae264","article-title":"TA-RNN: An attention-based time-aware recurrent neural network architecture for electronic health records","volume":"40","author":"Olaimat","year":"2024","journal-title":"Bioinformatics"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"114698","DOI":"10.1016\/j.enbuild.2024.114698","article-title":"ISSA-LSTM: A new data-driven method of heat load forecasting for building air conditioning","volume":"321","author":"Zhou","year":"2024","journal-title":"Energy Build."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"110287","DOI":"10.1016\/j.microc.2024.110287","article-title":"A novel bionic olfactory network combined with an electronic nose for identification of industrial exhaust","volume":"200","author":"Yan","year":"2024","journal-title":"Microchem. J."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., and Chen, L.C. (2018, January 18). Mobilenetv2: Inverted residuals and linear bottlenecks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00474"}],"container-title":["Foods"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2304-8158\/14\/15\/2612\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:15:56Z","timestamp":1760033756000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2304-8158\/14\/15\/2612"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,25]]},"references-count":38,"journal-issue":{"issue":"15","published-online":{"date-parts":[[2025,8]]}},"alternative-id":["foods14152612"],"URL":"https:\/\/doi.org\/10.3390\/foods14152612","relation":{},"ISSN":["2304-8158"],"issn-type":[{"value":"2304-8158","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,25]]}}}