Skip to content
2000
Volume 3, Issue 1
  • ISSN: 2950-3779
  • E-ISSN: 2950-3787

Abstract

Background

This research paper showcases the creation and assessment of a machine learning model utilizing the Efficient Net B4 architecture for the identification of cumin herbs and any potential adulterants. The research presents a comprehensive overview of the model's structure, emphasizing the different layers, their output dimensions, and the number of parameters.

Methods

The trained model consists of a grand total of 17,684,581 parameters, out of which 10,758 have been found eligible for training. The model has been found to exhibit exceptional performance on the training dataset, with an accuracy of 98.73%, a recall score of 0.95, and an F1 score of 0.93. This demonstrates its usefulness in accurately identifying cumin herbs. A confusion matrix has also been developed, which has showcased the model's remarkable proficiency in accurately detecting cumin herbs. Although there have been few occurrences of misclassification, the model has consistently shown exceptional accuracy by accurately identifying the majority of cases in both the “cumin” and “not cumin” categories.

Results

Upon comparing our model's performance to prior research, it has been found notable for its high accuracy and the potential to be applied more broadly in the field of herbal identification. This work offers an innovative way for recognizing cumin plants using machine learning, despite the little research existing in this area. It also establishes a basis for future research on identifying other important herbal items.

Conclusion

In conclusion, the machine learning model based on EfficientNet B4 has been found to exhibit exceptional accuracy and show potential for practical use in identifying cumin herbs. This study can significantly contribute to improving the authentication and quality assurance processes in the herbal product business, paving the way for future advancements in this field.

Loading

Article metrics loading...

/content/journals/cucs/10.2174/0129503779301717240607070206
2024-07-04
2025-02-23
Loading full text...

Full text loading...

References

  1. SingletaryK.W. Cumin: Potential health benefits.Nutr. Today202156314415110.1097/NT.0000000000000479
    [Google Scholar]
  2. FatimaT. BeenishN.B. GaniG. QadriT. BhatT.A. Antioxidant potential and health benefits of cumin.J Med Plants Stud20186232236
    [Google Scholar]
  3. SowbhagyaH.B. Chemistry, technology, and nutraceutical functions of cumin (Cuminum cyminum L): An overview.Crit. Rev. Food Sci. Nutr.201353111010.1080/10408398.2010.500223 23035918
    [Google Scholar]
  4. NadeemM. RiazA. Cumin (Cuminum cyminum) as a potential source of antioxidants.Pak. J. Food Sci.2012222101107
    [Google Scholar]
  5. OsmanA.G. RamanV. HaiderS. AliZ. ChittiboyinaA.G. KhanI.A. Overview of analytical tools for the identification of adulterants in commonly traded herbs and spices.J. AOAC Int.2019102237638510.5740/jaoacint.18‑0389 30646970
    [Google Scholar]
  6. de LimaA.B.S. BatistaA.S. de JesusJ.C. de Jesus SilvaJ. Fast quantitative detection of black pepper and cumin adulterations by near-infrared spectroscopy and multivariate modeling.Food Control202010710680210.1016/j.foodcont.2019.106802
    [Google Scholar]
  7. RoopashreeS. AnithaJ. MaheshT.R. Vinoth KumarV. ViriyasitavatW. KaurA. An IoT based authentication system for therapeutic herbs measured by local descriptors using machine learning approach.Measurement202220011148410.1016/j.measurement.2022.111484
    [Google Scholar]
  8. SharmaS. NamanS. DwivediJ. BaldiA. Artificial intelligence-based smart identification system using herbal images: Decision making using various machine learning models. Applications of Optimization and Machine Learning in Image Processing and IoT.Chapman and Hall/CRC12315510.1201/9781003364856
    [Google Scholar]
  9. MuneerA. FatiS.M. Efficient and automated herbs classification approach based on shape and texture features using deep learning.IEEE Access2020819674719676410.1109/ACCESS.2020.3034033
    [Google Scholar]
  10. KaurP.P. SinghS. PathakM. Review of machine learning herbal plant recognition systemProceedings of the International Conference on Innovative Computing & Communications (ICICC) 2020, Proceedings of the International Conference on Innovative Computing & Communication (ICICC). April 1202010.2139/ssrn.3565850
    [Google Scholar]
  11. NamanS. SharmaS. KumarM. KumarM. BaldiA. Developing a CNN-based machine learning model for cardamom identification: A transfer learning approach.Lat. Am. J. Pharm.2023426565574
    [Google Scholar]
  12. NamanS. SharmaS. BaldiA. Machine learning based identification of spices: A case study of Chilli.Lat. Am. J. Pharm.20234210248261
    [Google Scholar]
  13. TalukderM.M.H. RiaT.A. HasanM.M. RahmanM.H. SattarA. A computer vision and deep CNN modeling for spices recognition2022 13th International Conference on Computing Communication and Networking Technologies (ICCCNT)Kharagpur, India, 03-05 October 2022, pp. 1-5.10.1109/ICCCNT54827.2022.9984338
    [Google Scholar]
  14. SundaramA. MasudA. AlMarhoonA. SarmahB. Transfer learning approach for classification of widely used spices.YJES202219212110.53370/001c.35690
    [Google Scholar]
  15. KhrisneD.C. SuyadnyaI.M.A. ManhasJ. SharmaV. Classification of spices using machine learning techniques.Int J Knowledge Based Com Sys201810122122410.1109/ICSGTEIS.2018.8709135
    [Google Scholar]
  16. KhrisneD.C. SuyadnyaI.M.A. Indonesian herbs and spices recognition using smaller VGGNet-like network2018 International Conference on Smart Green Technology in Electrical and Information Systems (ICSGTEIS), Bali, Indonesia, 25-27 October 201822122410.1109/ICSGTEIS.2018.8709135
    [Google Scholar]
  17. JanaS. NagasaiP.S. KumarK.S. NageshwarV.M. Categorization and grading of spices using deep learning2022 IEEE International Conference on Data Science and Information System (ICDSIS), Hassan, India, 29-30 July20221610.1109/ICDSIS55133.2022.9915893
    [Google Scholar]
  18. HassanS.M. MajiA.K. JasińskiM. LeonowiczZ. JasińskaE. Identification of plant-leaf diseases using CNN and transfer-learning approach.Electronics20211012138810.3390/electronics10121388
    [Google Scholar]
  19. ZhangP. YangL. LiD. EfficientNet-B4-Ranger: A novel method for greenhouse cucumber disease recognition under natural complex environment.Comput. Electron. Agric.202017610565210.1016/j.compag.2020.105652
    [Google Scholar]
  20. FarmanH. AhmadJ. JanB. ShahzadY. AbdullahM. UllahA. Efficientnet-based robust recognition of peach plant diseases in field images.Comput. Mater. Continua20227112073208910.32604/cmc.2022.018961
    [Google Scholar]
  21. AgarwalM. GuptaS.K. BiswasK.K. Development of efficient CNN model for tomato crop disease identification.Sustainable Computing: Informatics and Systems20202810040710.1016/j.suscom.2020.100407
    [Google Scholar]
  22. BisenD. Deep convolutional neural network based plant species recognition through features of leaf.Multimedia Tools Appl.20218046443645610.1007/s11042‑020‑10038‑w
    [Google Scholar]
  23. LatifG. AbdelhamidS.E. MallouhyR.E. AlghazoJ. KazimiZ.A. Deep learning utilization in agriculture: Detection of rice plant diseases using an improved CNN model.Plants20221117223010.3390/plants11172230 36079612
    [Google Scholar]
  24. GokulnathB.V. Identifying and classifying plant disease using resilient LF-CNN.Ecol. Inform.20216310128310.1016/j.ecoinf.2021.101283
    [Google Scholar]
  25. ZhuH. LiuQ. QiY. HuangX. JiangF. ZhangS. Plant identification based on very deep convolutional neural networks.Multimedia Tools Appl.20187722297792979710.1007/s11042‑017‑5578‑9
    [Google Scholar]
  26. AkterR. HosenM.I. CNN-based leaf image classification for Bangladeshi medicinal plant recognition2020 Emerging Technology in Computing, Communication and Electronics (ETCCE). Bangladesh 21-22 December20201610.1109/ETCCE51779.2020.9350900
    [Google Scholar]
  27. ChenJ. ChenJ. ZhangD. SunY. NanehkaranY.A. Using deep transfer learning for image-based plant disease identification.Comput. Electron. Agric.202017310539310.1016/j.compag.2020.105393
    [Google Scholar]
  28. ChithraM.G. SirilE.A. Morphological variability of aerial vegetative characters among 20 Shatavari (Asparagus racemosus Willd.) collections from Kerala, India.J. Root Crops20174322132
    [Google Scholar]
  29. ZhuX. ZhangX. SunZ. ZhengY. SuS. ChenF. Identification of oil tea (Camellia oleifera C. Abel) cultivars using EfficientNet-B4 CNN model with attention mechanism.Forests2021131110.3390/f13010001
    [Google Scholar]
  30. CaiJ. PanR. LinJ. LiuJ. ZhangL. WenX. ChenX. ZhangX. Improved EfficientNet for corn disease identification.Front. Plant Sci.202314122438510.3389/fpls.2023.1224385 37767299
    [Google Scholar]
  31. ArunY. VikneshG.S. Leaf classification for plant recognition using EfficientNet architecture2022 IEEE Fourth International Conference on Advances in Electronics, Computers and Communications (ICAECC). Bengaluru, India, 10-11 January 2022, 1510.1109/ICAECC54045.2022.9716637
    [Google Scholar]
  32. HanhB.T. Van ManhH. NguyenN.V. Enhancing the performance of transferred efficientnet models in leaf image-based plant disease classification.J. Plant Dis. Prot.2022129362363410.1007/s41348‑022‑00601‑y
    [Google Scholar]
  33. KotwalJ.G. KashyapR. ShafiP.M. Artificial driving based EfficientNet for automatic plant leaf disease classification.Multimedia Tools Appl.202483382093824010.1007/s11042‑023‑16882‑w
    [Google Scholar]
  34. GehlotM. GandhiG.C. “EffiNet-TS”: A deep interpretable architecture using EfficientNet for plant disease detection and visualization.J. Plant Dis. Prot.2023130241343010.1007/s41348‑023‑00707‑x
    [Google Scholar]
  35. KumarA. NelsonL. VenuV.S. EfficientNet-Bl based maize plant leaf disease classification using deep learning2024 2nd International Conference on Intelligent Data Communication Technologies and Internet of Things (IDCIoT) 20241636164210.1109/IDCIoT59759.2024.10467408
    [Google Scholar]
  36. QuocT.N. HoangV.T. Medicinal Plant identification in the wild by using CNN2020 International Conference on Information and Communication Technology Convergence (ICTC), Jeju, Korea (South), 21-23 October 2020, 252910.1109/ICTC49870.2020.9289480
    [Google Scholar]
  37. Al BannaM.H. HaiderM.A. Al NahianM.J. IslamM.M. TaherK.A. KaiserM.S. Camera model identification using deep CNN and transfer learning approach2019 International Conference on Robotics, Electrical and Signal Processing Techniques (ICREST), Dhaka, Bangladesh201962663010.1109/ICREST.2019.8644194
    [Google Scholar]
  38. K.R, H.M, S. Anand, P. Mathikshara, A. Johnson, and M.R, “Attention embedded residual CNN for disease detection in tomato leaves”.Appl. Soft Comput.20208610593310.1016/j.asoc.2019.105933
    [Google Scholar]
  39. NayakTK. RaoA.CS. Recent advances in deep learning CNN models for plant disease detection. In: Recent advances in deep learning CNN models for plant disease detection.SingaporeSpringer2022224726310.1007/978‑981‑16‑9682‑4_14
    [Google Scholar]
  40. AkiyamaT. KobayashiY. SasakiY. SasakiK. KawaguchiT. KishigamiJ. Mobile leaf identification system using CNN applied to plants in Hokkaido2019 IEEE 8th Global Conference on Consumer Electronics (GCCE), Osaka, Japan, 15-18 October 2019,32432510.1109/GCCE46687.2019.9015298
    [Google Scholar]
  41. ZhaoY. SunZ. TianE. HuC. ZongH. YangF. A CNN model for herb identification based on part priority attention mechanism2020IEEE International Conference on Systems, Man, and Cybernetics (SMC), Toronto, ON, Canada, 11-14 October 20202565257110.1109/SMC42975.2020.9283189
    [Google Scholar]
  42. BhuiyanM. Abdullahil-OaphyM. KhanamR.S. IslamM. MediNET: A deep learning approach to recognize Bangladeshi ordinary medicinal plants using CNN. In: Soft Computing Techniques and Applications.Springer202137138010.1007/978‑981‑15‑7394‑1_35
    [Google Scholar]
  43. AmulyaK. DeepikaD.K. KamakshiD.P. An optimized hyper parameter-based CNN approach for predicting medicinal or non- medicinal leaves.Adv. Eng. Softw.202217210318110.1016/j.advengsoft.2022.103181
    [Google Scholar]
  44. TaoriT. GuptaS. BhagatS. GajreS. ManthalkarR. Cross-task cognitive load classification with identity mapping-based distributed CNN and attention-based rnn using gabor decomposed data images.J. Inst. Electron. Telecommun. Eng.202211710.1080/03772063.2022.2098191
    [Google Scholar]
  45. Manoharan JS. Flawless detection of herbal plant leaf by machine learning classifier through two stage authentication procedure.J. Artif. Intell. Capsule Netw.20213212513910.36548/jaicn.2021.2.005
    [Google Scholar]
  46. WathanM.H. WathanM.H. Shallots classification using CNN.Int. J. Inf. Comput.2022325010.35842/ijicom.v3i2.41
    [Google Scholar]
  47. GokhaleA. BabarS. GawadeS. JadhavS. Identification of medicinal plant using image processing and machine learningApplied Computer Vision and Image Processing Proceedings of ICCET 2020Springer2020127228210.1007/978‑981‑15‑4029‑5_27
    [Google Scholar]
  48. KayaA. KeceliA.S. CatalC. YalicH.Y. TemucinH. TekinerdoganB. Analysis of transfer learning for deep neural network based plant classification models.Comput. Electron. Agric.2019158202910.1016/j.compag.2019.01.041
    [Google Scholar]
  49. AtilaÜ. UçarM. AkyolK. UçarE. Plant leaf disease classification using EfficientNet deep learning model.Ecol. Inform.20216110118210.1016/j.ecoinf.2020.101182
    [Google Scholar]
  50. MishraA.M. HarnalS. MohiuddinK. GautamV. NasrO.A. GoyalN. AlwetaishiM. SinghA. A Deep learning-based novel approach for weed growth estimation.Intelligent Automation & Soft Computing20223121157117210.32604/iasc.2022.020174
    [Google Scholar]
  51. QureshiR. RagabM.G. AbdulkaderS.J. AlqushaibA. SumieaE.H. AlhussianH. A comprehensive systematic review of YOLO for medical object detection (2018 to 2023).IEEE Access2023125781557836
    [Google Scholar]
  52. ZhangW. SunX. ZhouL. XieX. ZhaoW. LiangZ. ZhuangP. Dual-branch collaborative learning network for crop disease identification.Front. Plant Sci.202314111747810.3389/fpls.2023.1117478 36844059
    [Google Scholar]
  53. Che SohA. YusofU.K. RadziN.F.M. IshakA.J. HassanM.K. Classification of aromatic herbs using artificial intelligent technique.Pertanika J. Sci. Technol.201725
    [Google Scholar]
  54. WangW. TianW. LiaoW. CaiB. LiB. Identifying chinese herbal medicine by image with three deep CNNsProceedings of the 5th International Conference on Control Engineering and Artificial Intelligence New York, NY, USA, January20211810.1145/3448218.3448221
    [Google Scholar]
  55. SunX. QianH. Chinese herbal medicine image recognition and retrieval by convolutional neural network.PLoS One2016116e015632710.1371/journal.pone.0156327 27258404
    [Google Scholar]
  56. ChenW. TongJ. HeR. LinY. ChenP. ChenZ. LiuX. An easy method for identifying 315 categories of commonly-used Chinese herbal medicines based on automated image recognition using AutoML platforms.Informatics in Medicine Unlocked20212510060710.1016/j.imu.2021.100607
    [Google Scholar]
  57. MukherjeeP.K. Quality control and evaluation of herbal drugs: Evaluating natural products and traditional medicine.Elsevier2019
    [Google Scholar]
  58. BodekerG. OngC-K. WHO global atlas of traditional, complementary and alternative medicine.World Health Organization2005
    [Google Scholar]
  59. EkorM. The growing use of herbal medicines: Issues relating to adverse reactions and challenges in monitoring safety.Front. Pharmacol.2014417710.3389/fphar.2013.00177 24454289
    [Google Scholar]
  60. DubeyK. DubeyK.P. Biodiversity conservation of medicinal plants.J. Res. Educ. Indian Med.2011171–216
    [Google Scholar]
  61. DevanganP. BajadG. LoharkarS. WadateN. GollapalliS. DuttaT. BaldiA. SinghS. KatyalA. ChandraR. SinghP.A. Quality-by-design strategy for developing novel herbal products. In: Introduction to Quality by Design (QbD) From Theory to Practice.Springer202426329510.1007/978‑981‑99‑8034‑5_11
    [Google Scholar]
  62. SinghP.A. SoodA. BaldiA. An agro-ecological zoning model highlighting potential growing areas for medicinal plants in Punjab.IJPER2021552ss492s50010.5530/ijper.55.2s.120
    [Google Scholar]
  63. SinghP.A. BajwaN. ChinnamS. ChandanA. BaldiA. An overview of some important deliberations to promote medicinal plants cultivation.J. Appl. Res. Med. Aromat. Plants20223110040010.1016/j.jarmap.2022.100400
    [Google Scholar]
  64. SinghP.A. SoodA. BaldiA. Determining constraints in medicinal plants adoption: A model geospatial study in the Indian state of Punjab.J. Appl. Res. Med. Aromat. Plants20212510034210.1016/j.jarmap.2021.100342
    [Google Scholar]
  65. BaldiA. BansalP.K. Traditional and herbal medicines: Understanding & exploration (part II).Curr. Tradit. Med.202064258259
    [Google Scholar]
  66. SharmaV. SarkarI.N. Bioinformatics opportunities for identification and study of medicinal plants.Brief. Bioinform.201314223825010.1093/bib/bbs021 22589384
    [Google Scholar]
  67. LuoD. FanD. YuH. LiZ. A new processing technique for the identification of Chinese herbal medicineInternational Conference on Computational and Information Sciences, Shiyang, China 21-23 June201347447710.1109/ICCIS.2013.131
    [Google Scholar]
  68. EverstineK. SpinkJ. KennedyS. Economically motivated adulteration (EMA) of food: Common characteristics of EMA incidents.J. Food Prot.201376472373510.4315/0362‑028X.JFP‑12‑399 23575142
    [Google Scholar]
  69. HeublG. New aspects of DNA-based authentication of Chinese medicinal plants by molecular biological techniques.Planta Med.201076171963197410.1055/s‑0030‑1250519 21058240
    [Google Scholar]
  70. KorirN.K. HanJ. ShangguanL. WangC. KayeshE. ZhangY. FangJ. Plant variety and cultivar identification: Advances and prospects.Crit. Rev. Biotechnol.201333211112510.3109/07388551.2012.675314 22698516
    [Google Scholar]
  71. SinghP.A. BajwaN. NamanS. BaldiA. A review on robust computational approaches based identification and authentication of herbal raw drugs.Lett. Drug Des. Discov.20201791066108310.2174/1570180817666200304125520
    [Google Scholar]
  72. ZhangY.B. ButP.P.H. WangZ.T. ShawP.C. Current approaches for the authentication of medicinal Dendrobium species and its products.Plant Genet. Resour.20053214414810.1079/PGR200578
    [Google Scholar]
  73. SucherN. CarlesM. Genome-based approaches to the authentication of medicinal plants.Planta Med.200874660362310.1055/s‑2008‑1074517 18449847
    [Google Scholar]
  74. ChandaS. Importance of pharmacognostic study of medicinal plants: An overview.J. Pharmacogn. Phytochem.2014256973
    [Google Scholar]
/content/journals/cucs/10.2174/0129503779301717240607070206
Loading
/content/journals/cucs/10.2174/0129503779301717240607070206
Loading

Data & Media loading...


  • Article Type:
    Research Article
Keyword(s): Adulteration; CNN; cumin; efficientNet B4; herbal authentication; machine learning model
This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error
Please enter a valid_number test