pith. sign in

arxiv: 2504.10527 · v2 · submitted 2025-04-12 · 💻 cs.AI · cs.CY

Explainable Artificial Intelligence Techniques for Interpretation of Food Models: a Review

Leonardo Arrighi , Ingrid Alves de Moraes , Marco Zullich , Michele Simonato , Douglas Fernandes Barbin , Sylvio Barbon Junior This is my paper

Pith reviewed 2026-05-22 20:52 UTC · model grok-4.3

classification 💻 cs.AI cs.CY
keywords explainable AIfood qualityXAI taxonomySHAPGrad-CAMspectral imagingmodel interpretabilityfood engineering
0
0 comments X

The pith

A taxonomy classifies food quality research using XAI techniques by data types and explanation methods.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

This survey reviews how artificial intelligence models analyze food data for quality control yet often remain opaque in their reasoning. It notes that techniques like SHAP and Grad-CAM can highlight which wavelengths or image areas drive predictions of contaminants or freshness. The main offering is a taxonomy that sorts published work according to the data involved and the explanation approach taken. This organization supplies researchers with a practical map for picking an interpretable method suited to their food engineering task. The review closes by listing current trends, open challenges, and future chances to bring more transparency to the domain.

Core claim

The survey presents a taxonomy for classifying food quality research using XAI techniques, organized by data types and explanation methods, to guide researchers in choosing suitable approaches. It also highlights trends, challenges, and opportunities to encourage the adoption of XAI in Food Engineering.

What carries the argument

The taxonomy organized by data types and explanation methods, which categorizes studies and recommends XAI techniques such as SHAP for feature contributions and Grad-CAM for image region importance in food models.

Load-bearing premise

That general XAI methods transfer directly to food quality models and deliver useful transparency without domain-specific adjustments or further checks in food contexts.

What would settle it

An experiment applying SHAP or Grad-CAM to a spectral food model that produces explanations contradicting established food chemistry knowledge or failing to aid inspectors in verifying predictions.

Figures

Figures reproduced from arXiv: 2504.10527 by Douglas Fernandes Barbin, Ingrid Alves de Moraes, Leonardo Arrighi, Marco Zullich, Michele Simonato, Sylvio Barbon Junior.

Figure 1
Figure 1. Figure 1: Overview scheme, from food quality tasks to XAI techniques. XAI is applied as an endpoint of a data [PITH_FULL_IMAGE:figures/full_fig_p002_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Chart illustrating approximately the trade-off between expressivity or flexibility and interpretability. Expressive [PITH_FULL_IMAGE:figures/full_fig_p005_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Representation of the types of explanations provided by XAI techniques, along with a summary of their key [PITH_FULL_IMAGE:figures/full_fig_p006_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Distribution of papers surveyed in the present work per publication year and data type. Most of the articles [PITH_FULL_IMAGE:figures/full_fig_p016_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Distribution of papers surveyed in the present work per topic and explanation type. [PITH_FULL_IMAGE:figures/full_fig_p017_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Alluvial plot showing the distribution of works surveyed per topic, data type, and explanation type, as [PITH_FULL_IMAGE:figures/full_fig_p018_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Pie chart illustrating the distribution of papers in this survey that utilize global XAI techniques versus local [PITH_FULL_IMAGE:figures/full_fig_p018_7.png] view at source ↗
read the original abstract

Artificial Intelligence (AI) has become essential for analyzing complex data and solving highly-challenging tasks. It is being applied across numerous disciplines beyond computer science, including Food Engineering, where there is a growing demand for accurate and reliable predictions to meet stringent food quality standards. However, this requires increasingly complex AI models, raising concerns. In response, eXplainable AI (XAI) has emerged to provide insights into AI decision-making, aiding model interpretation by developers and users. Nevertheless, XAI remains underutilized in Food Engineering, limiting model reliability. For instance, in food quality control, AI models using spectral imaging can detect contaminants or assess freshness levels, but their opaque decision-making process hinders adoption. XAI techniques such as SHAP (Shapley Additive Explanations) and Grad-CAM (Gradient-weighted Class Activation Mapping) can pinpoint which spectral wavelengths or image regions contribute most to a prediction, enhancing transparency and aiding quality control inspectors in verifying AI-generated assessments. This survey presents a taxonomy for classifying food quality research using XAI techniques, organized by data types and explanation methods, to guide researchers in choosing suitable approaches. We also highlight trends, challenges, and opportunities to encourage the adoption of XAI in Food Engineering.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 2 minor

Summary. This review paper proposes a taxonomy for classifying food quality research that employs XAI techniques. The taxonomy is organized by data types and explanation methods, with concrete examples including the use of SHAP for identifying important spectral wavelengths in contaminant detection and Grad-CAM for highlighting relevant image regions in freshness assessment. The manuscript also identifies trends, challenges, and opportunities for XAI adoption in Food Engineering to improve model transparency and reliability.

Significance. If the taxonomy successfully organizes the literature and provides actionable guidance while accounting for food-specific constraints, it could significantly aid researchers in selecting appropriate XAI methods for their models. This would help address the underutilization of XAI in the field and support the adoption of reliable AI systems in food quality control. The review's value lies in bridging general XAI literature with domain applications, though its impact depends on the depth of analysis regarding domain adaptations.

major comments (2)
  1. [Abstract] Abstract: The central claim that the taxonomy will guide researchers in choosing suitable XAI approaches rests on the transfer of general methods (e.g., SHAP on spectral data, Grad-CAM on images) to food quality models. However, the manuscript supplies no discussion or evidence addressing whether food-engineering specifics such as sensor noise, regulatory traceability requirements, or non-stationary freshness labels alter which explanations are actionable. This directly affects the organizational utility of the taxonomy.
  2. [Introduction / Methods] Review methodology (wherever described, e.g., Introduction or dedicated section): The abstract supports the taxonomy with examples, but there is no detailed account of study selection, including databases searched, search terms, inclusion/exclusion criteria, or number of papers reviewed. Without this, the completeness and representativeness of the taxonomy cannot be verified, undermining the claim that it classifies food quality research comprehensively.
minor comments (2)
  1. [Abstract] The abstract states that XAI 'remains underutilized in Food Engineering' and lists challenges/opportunities; ensure these sections explicitly map back to specific taxonomy entries rather than remaining at a high level.
  2. [Taxonomy section] Notation for data types and explanation methods in the taxonomy should be defined consistently (e.g., abbreviations for spectral vs. image data) to improve readability for readers outside core XAI.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive comments on our manuscript. We address each major point below and have made revisions to strengthen the presentation of the taxonomy and its supporting methodology.

read point-by-point responses

  1. Referee: [Abstract] Abstract: The central claim that the taxonomy will guide researchers in choosing suitable XAI approaches rests on the transfer of general methods (e.g., SHAP on spectral data, Grad-CAM on images) to food quality models. However, the manuscript supplies no discussion or evidence addressing whether food-engineering specifics such as sensor noise, regulatory traceability requirements, or non-stationary freshness labels alter which explanations are actionable. This directly affects the organizational utility of the taxonomy.

    Authors: We agree that explicit consideration of food-specific constraints would improve the taxonomy's guidance value. In the revised manuscript we have added a dedicated paragraph within the Challenges and Opportunities section that discusses how sensor noise can affect SHAP stability on spectral data, the role of regulatory traceability in determining acceptable explanation fidelity, and necessary adaptations for non-stationary freshness labels. Concrete examples and pointers to relevant food-engineering literature are now included. revision: yes

  2. Referee: [Introduction / Methods] Review methodology (wherever described, e.g., Introduction or dedicated section): The abstract supports the taxonomy with examples, but there is no detailed account of study selection, including databases searched, search terms, inclusion/exclusion criteria, or number of papers reviewed. Without this, the completeness and representativeness of the taxonomy cannot be verified, undermining the claim that it classifies food quality research comprehensively.

    Authors: The manuscript is framed as a narrative survey whose primary goal is to propose an organizing taxonomy illustrated by representative examples rather than to deliver an exhaustive systematic review. To increase transparency we have nevertheless inserted a concise 'Review Approach' subsection that lists the main databases consulted, representative search terms employed, and the criteria used to select illustrative papers. We have also clarified that the taxonomy is intended to be illustrative rather than exhaustive. revision: yes

Circularity Check

0 steps flagged

No circularity: survey taxonomy is organizational framework from external literature

full rationale

This is a review paper that proposes a taxonomy for classifying food quality research using XAI techniques, organized by data types and explanation methods. No derivations, equations, predictions, or fitted parameters are presented that could reduce to the paper's own inputs by construction. The central claim draws from cited external literature with independent grounding, and no self-citation load-bearing or ansatz smuggling is evident in the provided text. The taxonomy functions as an organizational guide rather than a self-referential result.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

As a review paper, the work introduces no new free parameters, axioms, or invented entities. The taxonomy is constructed from existing XAI techniques and food engineering applications described in the surveyed literature.

pith-pipeline@v0.9.0 · 5765 in / 1040 out tokens · 39002 ms · 2026-05-22T20:52:40.647928+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. OmniFood8K: Single-Image Nutrition Estimation via Hierarchical Frequency-Aligned Fusion

    cs.CV 2026-04 unverdicted novelty 6.0

    OmniFood8K supplies a large Chinese-food nutrition dataset and a single-image model that predicts depth then hierarchically fuses RGB and depth features in frequency space for improved nutrition estimates.

Reference graph

Works this paper leans on

236 extracted references · 236 canonical work pages · cited by 1 Pith paper · 4 internal anchors

  1. [1]

    A critical review on computer vision and artificial intelligence in food industry

    Vijay Kakani, Van Huan Nguyen, Basivi Praveen Kumar, Hakil Kim, and Visweswara Rao Pasupuleti. A critical review on computer vision and artificial intelligence in food industry. Journal of Agriculture and Food Research, 2:100033, 2020. ISSN 2666-1543. doi:10.1016/j.jafr.2020.100033

    work page doi:10.1016/j.jafr.2020.100033 2020

  2. [2]

    Tagarakis, Georgios Dolias, Remigio Berruto, Dimitrios Kateris, and Dionysis Bochtis

    Lefteris Benos, Aristotelis C. Tagarakis, Georgios Dolias, Remigio Berruto, Dimitrios Kateris, and Dionysis Bochtis. Machine learning in agriculture: A comprehensive updated review. Sensors, 21(11):3758, 2021. ISSN 1424-8220. doi:10.3390/s21113758

    work page doi:10.3390/s21113758 2021

  3. [3]

    Thomas, Samantha Kleinberg, Andrew W

    Diana M. Thomas, Samantha Kleinberg, Andrew W. Brown, Mason Crow, Nathaniel D. Bastian, Nicholas Reisweber, Robert Lasater, Thomas Kendall, Patrick Shafto, Raymond Blaine, Sarah Smith, Daniel Ruiz, Christopher Morrell, and Nicholas Clark. Machine learning modeling practices to support the principles of AI and ethics in nutrition research. Nutrition & Diab...

    work page doi:10.1038/s41387- 2022

  4. [4]

    Suhaili Othman, Nidhi Rajesh Mavani, M. A. Hussain, Norliza Abd Rahman, and Jarinah Mohd Ali. Artificial intelligence-based techniques for adulteration and defect detections in food and agricultural industry: A review. Journal of Agriculture and Food Research, 12:100590, 2023. ISSN 2666-1543. doi:10.1016/j.jafr.2023.100590

    work page doi:10.1016/j.jafr.2023.100590 2023

  5. [5]

    Explainable artificial intelligence (XAI) 2.0: A manifesto of open challenges and interdisciplinary research directions

    Luca Longo, Mario Brcic, Federico Cabitza, Jaesik Choi, Roberto Confalonieri, Javier Del Ser, Riccardo Guidotti, Yoichi Hayashi, Francisco Herrera, Andreas Holzinger, Richard Jiang, Hassan Khosravi, Freddy Lecue, Gianclaudio Malgieri, Andrés Páez, Wojciech Samek, Johannes Schneider, Timo Speith, and Simone Stumpf. Explainable artificial intelligence (XAI)...

    work page doi:10.1016/j.inffus.2024.102301 2024

  6. [6]

    Craigon, Jeremy Frey, Anabel Gutierrez, Naomi Jacobs, Samantha Kanza, Samuel Munday, Justin Sacks, and Simon Pearson

    Louise Manning, Steve Brewer, Peter J. Craigon, Jeremy Frey, Anabel Gutierrez, Naomi Jacobs, Samantha Kanza, Samuel Munday, Justin Sacks, and Simon Pearson. Artificial intelligence and ethics within the food sector: Developing a common language for technology adoption across the supply chain. Trends in Food Science & Technology, 125:33–42, 2022. ISSN 0924...

    work page doi:10.1016/j.tifs.2022.04.025 2022

  7. [7]

    why should i trust you?

    Marco Tulio Ribeiro, Sameer Singh, and Carlos Guestrin. “why should i trust you?” explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, pages 1135–1144, 2016

    work page 2016

  8. [8]

    Lundberg and Su-In Lee

    Scott M. Lundberg and Su-In Lee. A unified approach to interpreting model predictions. In Proceedings of the 31st International Conference on Neural Information Processing Systems, NIPS’17, page 4768–4777, Red Hook, NY , USA, 2017. Curran Associates Inc. ISBN 9781510860964

    work page 2017

  9. [9]

    Learning deep features for discriminative localization

    Bolei Zhou, Aditya Khosla, Agata Lapedriza, Aude Oliva, and Antonio Torralba. Learning deep features for discriminative localization. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 2921–2929, 2016. 20 Explainable Artificial Intelligence techniques for interpretation of food datasets: a review A PREPRINT

    work page 2016

  10. [10]

    David Pfau

    Qingyuan Zhao and Trevor Hastie. Causal interpretations of black-box models. Journal of Business & Economic Statistics, 39(1):272–281, 2021. ISSN 0735-0015. doi:10.1080/07350015.2019.1624293

    work page doi:10.1080/07350015.2019.1624293 2021

  11. [11]

    Bach , author A

    Sebastian Bach, Alexander Binder, Grégoire Montavon, Frederick Klauschen, Klaus-Robert Müller, and Wojciech Samek. On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation.PLOS ONE, 10(7):e0130140, 2015. ISSN 1932-6203. doi:10.1371/journal.pone.0130140

    work page doi:10.1371/journal.pone.0130140 2015

  12. [12]

    The universe of food quality

    Claudio Peri. The universe of food quality. Food Quality and Preference, 17(1):3–8, 2006. ISSN 0950-3293. doi:10.1016/j.foodqual.2005.03.002

    work page doi:10.1016/j.foodqual.2005.03.002 2006

  13. [13]

    Halim-Lim, Nurul H

    Sarina A. Halim-Lim, Nurul H. Ahmad, and Noor Z. N. Hasnan. Quality and safety in the food industry. Wiley StatsRef: Statistics Reference Online, pages 1–7, 2022. doi:10.1002/9781118445112.stat08389

    work page doi:10.1002/9781118445112.stat08389 2022

  14. [14]

    Seal and Kirsten Brandt

    Chris J. Seal and Kirsten Brandt. 3 - nutritional quality of foods. Handbook of Organic Food Safety and Quality, pages 25–40, 2007. doi:10.1533/9781845693411.1.25

    work page doi:10.1533/9781845693411.1.25 2007

  15. [15]

    Malcolmson and Jill K

    Linda J. Malcolmson and Jill K. Winkler-Moser. Flavor and sensory aspects. Bailey’s Industrial Oil and Fat Products, pages 1–17, 2020. doi:10.1002/047167849X.bio032.pub2

    work page doi:10.1002/047167849x.bio032.pub2 2020

  16. [16]

    Recent development in the application of analytical techniques for the traceability and authenticity of food of plant origin

    Syed Abdul Wadood, Guo Boli, Zhang Xiaowen, Imtiaz Hussain, and Wei Yimin. Recent development in the application of analytical techniques for the traceability and authenticity of food of plant origin. Microchemical Journal, 152:104295, 2020. ISSN 0026-265X. doi:10.1016/j.microc.2019.104295

    work page doi:10.1016/j.microc.2019.104295 2020

  17. [17]

    Authenticity and quality of animal origin food investigated by stable-isotope ratio analysis

    Giuliana Vinci, Raffaella Preti, Alessandra Tieri, and Simone Vieri. Authenticity and quality of animal origin food investigated by stable-isotope ratio analysis. Journal of the Science of Food and Agriculture, 93(3):439–448,

    work page

  18. [18]

    doi:10.1002/jsfa.5970

    ISSN 1097-0010. doi:10.1002/jsfa.5970

    work page doi:10.1002/jsfa.5970

  19. [19]

    Turrisi da Costa, Douglas Fernandes Barbin, and José Lucena Barbosa Jr

    Marcus Vinicius da Silva Ferreira, Sylvio Barbon Junior, Victor G. Turrisi da Costa, Douglas Fernandes Barbin, and José Lucena Barbosa Jr. Deep computer vision system and explainable artificial intelligence applied for classification of dragon fruit (Hylocereus spp.). Scientia Horticulturae, 338:113605, 2024. ISSN 0304-4238. doi:10.1016/j.scienta.2024.113605

    work page doi:10.1016/j.scienta.2024.113605 2024

  20. [20]

    Interpretation and explanation of computer vision classification of carambola (Averrhoa carambola L.) according to maturity stage

    Ingrid Alves de Moraes, Sylvio Barbon Junior, and Douglas Fernandes Barbin. Interpretation and explanation of computer vision classification of carambola (Averrhoa carambola L.) according to maturity stage. Food Research International, 192:114836, 2024. ISSN 0963-9969. doi:10.1016/j.foodres.2024.114836

    work page doi:10.1016/j.foodres.2024.114836 2024

  21. [21]

    Food quality, effects on health and sustainability to- day: a model case report

    Vittorio Natale Borroni, Silvia Fargion, Alessandra Mazzocchi, Marco Giachetti, Achille Lanzarini, Margherita Dall’Asta, Francesca Scazzina, and Carlo Agostoni. Food quality, effects on health and sustainability to- day: a model case report. International Journal of Food Sciences and Nutrition , 68(1):117–120, 2017. doi:10.1080/09637486.2016.1221385

    work page doi:10.1080/09637486.2016.1221385 2017

  22. [22]

    Healthy and sustainable diet: a narrative review of the challenges and perspectives

    Suellen Secchi Martinelli and Suzi Barletto Cavalli. Healthy and sustainable diet: a narrative review of the challenges and perspectives. Ciencia & Saude Coletiva , 24(11):4251–4262, 2019. ISSN 1678-4561. doi:10.1590/1413-812320182411.30572017

    work page doi:10.1590/1413-812320182411.30572017 2019

  23. [23]

    An interpretable artificial intelligence based smart agriculture system

    Fariza Sabrina, Shaleeza Sohail, Farnaz Farid, Sayka Jahan, Farhad Ahamed, and Steven Gordon. An interpretable artificial intelligence based smart agriculture system. Computers, Materials & Continua, pages 3777–3797, 2022. ISSN 1546-2218. doi:10.32604/cmc.2022.026363

    work page doi:10.32604/cmc.2022.026363 2022

  24. [24]

    Tsakiridis, Themistoklis Diamantopoulos, Andreas L

    Nikolaos L. Tsakiridis, Themistoklis Diamantopoulos, Andreas L. Symeonidis, John B. Theocharis, Athanasios Iossifides, Periklis Chatzimisios, George Pratos, and Dimitris Kouvas. Versatile internet of things for agriculture: An eXplainable AI approach. Artificial Intelligence Applications and Innovations , pages 180–191, 2020. doi:10.1007/978-3-030-49186-4_16

    work page doi:10.1007/978-3-030-49186-4_16 2020

  25. [25]

    Explainable ai and slime mould algorithm for classification of pistachio species

    Gehad Ismail Sayed and Aboul Ella Hassanien. Explainable ai and slime mould algorithm for classification of pistachio species. Artificial Intelligence: A Real Opportunity in the Food Industry , pages 29–43, 2023. doi:10.1007/978-3-031-13702-0_3

    work page doi:10.1007/978-3-031-13702-0_3 2023

  26. [26]

    Zhiyong Cui, Ninglong Zhang, Tianxing Zhou, Xueke Zhou, Hengli Meng, Yanyang Yu, Zhiwei Zhang, Yin Zhang, Wenli Wang, and Yuan Liu. Conserved sites and recognition mechanisms of t1r1 and t2r14 receptors re- vealed by ensemble docking and molecular descriptors and fingerprints combined with machine learning.Journal of Agricultural and Food Chemistry, 71(14...

    work page doi:10.1021/acs.jafc.3c00591 2023

  27. [27]

    Explainable machine learning approach quantified the long-term (1981–2015) impact of climate and soil properties on yields of major agricultural crops across conus

    Debjani Sihi, Biswanath Dari, Abraham Peedikayil Kuruvila, Gaurav Jha, and Kanad Basu. Explainable machine learning approach quantified the long-term (1981–2015) impact of climate and soil properties on yields of major agricultural crops across conus. Frontiers in Sustainable Food Systems, 6, 2022. ISSN 2571-581X. doi:10.3389/fsufs.2022.847892

    work page doi:10.3389/fsufs.2022.847892 1981

  28. [28]

    Viana, Maurício Santos, Dulce Freire, Patrícia Abrantes, and Jorge Rocha

    Cláudia M. Viana, Maurício Santos, Dulce Freire, Patrícia Abrantes, and Jorge Rocha. Evaluation of the factors explaining the use of agricultural land: A machine learning and model-agnostic approach. Ecological Indicators, 131:108200, 2021. ISSN 1470-160X. doi:10.1016/j.ecolind.2021.108200. 21 Explainable Artificial Intelligence techniques for interpretat...

    work page doi:10.1016/j.ecolind.2021.108200 2021

  29. [29]

    Extreme gradient boosting for yield estimation compared with deep learning approaches

    Florian Huber, Artem Yushchenko, Benedikt Stratmann, and V olker Steinhage. Extreme gradient boosting for yield estimation compared with deep learning approaches. Computers and Electronics in Agriculture , 202: 107346, 2022. ISSN 0168-1699. doi:10.1016/j.compag.2022.107346

    work page doi:10.1016/j.compag.2022.107346 2022

  30. [30]

    Spatial patterns and determinants of av- ocado frontier dynamics in mexico

    Diana Ramírez-Mejía, Christian Levers, and Jean-François Mas. Spatial patterns and determinants of av- ocado frontier dynamics in mexico. Regional Environmental Change, 22(1):28, 2022. ISSN 1436-378X. doi:10.1007/s10113-022-01883-6

    work page doi:10.1007/s10113-022-01883-6 2022

  31. [31]

    Cardel, Michael Skarlinski, Angela Goscilo, Carl Anderson, and Gary D

    Reka Daniel-Weiner, Michelle I. Cardel, Michael Skarlinski, Angela Goscilo, Carl Anderson, and Gary D. Foster. Enabling informed decision making in the absence of detailed nutrition labels: A model to estimate the added sugar content of foods. Nutrients, 15:803, 2023. ISSN 2072-6643. doi:10.3390/nu15040803

    work page doi:10.3390/nu15040803 2023

  32. [32]

    An effective explainable food recommendation using deep image clustering and community detection

    Mehrdad Rostami, Usman Muhammad, Saman Forouzandeh, Kamal Berahmand, Vahid Farrahi, and Mourad Oussalah. An effective explainable food recommendation using deep image clustering and community detection. Intelligent Systems with Applications, 16:200157, 2022. ISSN 2667-3053. doi:10.1016/j.iswa.2022.200157

    work page doi:10.1016/j.iswa.2022.200157 2022

  33. [33]

    Application of multivariate machine learning methods to investigate organic compound content of different pepper spices

    Yusuf Durmu¸ s and Ahmet Ferit Atasoy. Application of multivariate machine learning methods to investigate organic compound content of different pepper spices. Food Bioscience, 51:102216, 2023. ISSN 2212-4292. doi:10.1016/j.fbio.2022.102216

    work page doi:10.1016/j.fbio.2022.102216 2023

  34. [34]

    Identification of soil texture classes under vegetation cover based on sentinel-2 data with SVM and SHAP techniques

    Yanan Zhou, Wei Wu, Huan Wang, Xin Zhang, Chao Yang, and Hongbin Liu. Identification of soil texture classes under vegetation cover based on sentinel-2 data with SVM and SHAP techniques. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 15:3758–3770, 2022. ISSN 2151-1535. doi:10.1109/JSTARS.2022.3164140

    work page doi:10.1109/jstars.2022.3164140 2022

  35. [35]

    Estimating individual-level pig growth trajectories from group-level weight time series using machine learning

    Christian Taylor, Jonathan Guy, and Jaume Bacardit. Estimating individual-level pig growth trajectories from group-level weight time series using machine learning. Computers and Electronics in Agriculture, 208:107790,

    work page

  36. [36]

    doi:10.1016/j.compag.2023.107790

    ISSN 0168-1699. doi:10.1016/j.compag.2023.107790

    work page doi:10.1016/j.compag.2023.107790 2023

  37. [37]

    I-ldd: an interpretable leaf disease detector

    Rashmi Mishra, Ankit Kavita, Rajpal, Varnika Bhatia, Sheetal Rajpal, Manoj Agarwal, and Naveen Kumar. I-ldd: an interpretable leaf disease detector. Soft Computing, 2023. ISSN 1433-7479. doi:10.1007/s00500-023-08512-2

    work page doi:10.1007/s00500-023-08512-2 2023

  38. [38]

    Wheat dis- eases classification and localization using convolutional neural networks and GradCAM visualization

    Elias Ennadifi, Sohaib Laraba, Damien Vincke, Benoît Mercatoris, and Bernard Gosselin. Wheat dis- eases classification and localization using convolutional neural networks and GradCAM visualization. 2020 International Conference on Intelligent Systems and Computer Vision (ISCV) , pages 1–5, 2020. doi:10.1109/ISCV49265.2020.9204258

    work page doi:10.1109/iscv49265.2020.9204258 2020

  39. [39]

    Identifying crop diseases using atten- tion embedded MobileNet-v2 model

    Junde Chen, Defu Zhang, Md Suzauddola, and Adnan Zeb. Identifying crop diseases using atten- tion embedded MobileNet-v2 model. Applied Soft Computing , 113:107901, 2021. ISSN 1568-4946. doi:10.1016/j.asoc.2021.107901

    work page doi:10.1016/j.asoc.2021.107901 2021

  40. [40]

    A lightweight model based on yolov8n in wheat spike detection

    Xuyang Ban, Pan Liu, Lei Xu, and Jinling Zhao. A lightweight model based on yolov8n in wheat spike detection. In 2023 11th International Conference on Agro-Geoinformatics (Agro-Geoinformatics), pages 1–6,

    work page 2023

  41. [41]

    doi:10.1109/Agro-Geoinformatics59224.2023.10233526

    work page doi:10.1109/agro-geoinformatics59224.2023.10233526 2023

  42. [42]

    Batarseh

    Yingjie Wang, Jaganmohan Chandrasekaran, Flora Haberkorn, Yan Dong, Munisamy Gopinath, and Feras A. Batarseh. Deepfarm: Ai-driven management of farm production using explainable causality. In 2022 IEEE 29th Annual Software Technology Conference (STC), pages 27–36, 2022. doi:10.1109/STC55697.2022.00013

    work page doi:10.1109/stc55697.2022.00013 2022

  43. [43]

    Plant disease clas- sification using interpretable vision transformer network

    Ritesh Maurya, Nageshwar Nath Pandey, Vibhav Prakash Singh, and T Gopalakrishnan. Plant disease clas- sification using interpretable vision transformer network. 2023 International Conference on Recent Ad- vances in Electrical, Electronics & Digital Healthcare Technologies (REEDCON) , pages 688–692, 2023. doi:10.1109/REEDCON57544.2023.10151342

    work page doi:10.1109/reedcon57544.2023.10151342 2023

  44. [44]

    Inline nondestructive internal disorder detection in pear fruit using explainable deep anomaly detection on x-ray images

    Tim van de Looverbosch, Jiaqi He, Astrid Tempelaere, Klaas Kelchtermans, Pieter Verboven, Tinne Tuytelaars, Jan Sijbers, and Bart Nicolai. Inline nondestructive internal disorder detection in pear fruit using explainable deep anomaly detection on x-ray images. Computers and Electronics in Agriculture, 197:106962, 2022. ISSN 0168-1699. doi:10.1016/j.compag...

    work page doi:10.1016/j.compag.2022.106962 2022

  45. [45]

    Psychological foundations of explainability and interpretability in artificial intelligence, 2021

    David Broniatowski. Psychological foundations of explainability and interpretability in artificial intelligence, 2021

    work page 2021

  46. [46]

    Springer Texts in Statistics

    Gareth James, Daniela Witten, Trevor Hastie, and Robert Tibshirani.An Introduction to Statistical Learning: with Applications in R. Springer Texts in Statistics. Springer US, 2021. ISBN 978-1-07-161417-4 978-1-07-161418-1. doi:10.1007/978-1-0716-1418-1

    work page doi:10.1007/978-1-0716-1418-1 2021

  47. [47]

    An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

    Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, et al. An image is worth 16x16 words: Transformers for image recognition at scale. CoRR, abs/2010.11929, 2020. 22 Explainable Artificial Intelligence techniques for interpretation of ...

    work page internal anchor Pith review Pith/arXiv arXiv 2010

  48. [48]

    Visualization comparison of vision trans- formers and convolutional neural networks

    Rui Shi, Tianxing Li, Liguo Zhang, and Yasushi Yamaguchi. Visualization comparison of vision trans- formers and convolutional neural networks. IEEE Transactions on Multimedia , 26:2327–2339, 2024. doi:10.1109/TMM.2023.3294805

    work page doi:10.1109/tmm.2023.3294805 2024

  49. [49]

    In: Proceedings of the IEEE/CVF Conference on Computer 25 Vision and Pattern Recognition, pp

    Weibin Wu, Yuxin Su, Xixian Chen, Shenglin Zhao, Irwin King, Michael R. Lyu, and Yu-Wing Tai. Towards global explanations of convolutional neural networks with concept attribution. In 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , pages 8649–8658, 2020. doi:10.1109/CVPR42600.2020.00868

    work page doi:10.1109/cvpr42600.2020.00868 2020

  50. [50]

    GLocalX - from local to global explanations of black box AI models

    Mattia Setzu, Riccardo Guidotti, Anna Monreale, Franco Turini, Dino Pedreschi, and Fosca Giannotti. GLocalX - from local to global explanations of black box AI models. Artificial Intelligence, 294:103457, 2021. ISSN 0004-3702. doi:10.1016/j.artint.2021.103457

    work page doi:10.1016/j.artint.2021.103457 2021

  51. [51]

    PoseNet: A convolutional network for real-time 6-dof camera relocalization,

    Ramprasaath R. Selvaraju, Michael Cogswell, Abhishek Das, Ramakrishna Vedantam, Devi Parikh, and Dhruv Batra. Grad-CAM: Visual explanations from deep networks via gradient-based localization. In 2017 IEEE International Conference on Computer Vision (ICCV), pages 618–626, 2017. doi:10.1109/ICCV .2017.74. ISSN: 2380-7504

    work page doi:10.1109/iccv 2017

  52. [52]

    Derf: Decomposed radiance fields,

    Hila Chefer, Shir Gur, and Lior Wolf. Transformer interpretability beyond attention visualization. 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , pages 782–791, 2021. doi:10.1109/CVPR46437.2021.00084

    work page doi:10.1109/cvpr46437.2021.00084 2021

  53. [53]

    In: ICASSP 2023 - 2023 IEEE Inter- national Conference on Acoustics, Speech and Signal Processing (ICASSP), pp

    Hagar Kafri, Marco Olivieri, Fabio Antonacci, Mordehay Moradi, Augusto Sarti, and Sharon Gannot. Grad-cam- inspired interpretation of nearfield acoustic holography using physics-informed explainable neural network. In ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) , pages 1–5, 2023. doi:10.1109/ICASSP4...

    work page doi:10.1109/icassp49357.2023.10097272 2023

  54. [54]

    Explainable deep learning study for leaf disease classification

    Kaihua Wei, Bojian Chen, Jingcheng Zhang, Shanhui Fan, Kaihua Wu, Guangyu Liu, and Dongmei Chen. Explainable deep learning study for leaf disease classification. Agronomy, 12(5):1035, 2022. ISSN 2073-4395. doi:10.3390/agronomy12051035

    work page doi:10.3390/agronomy12051035 2022

  55. [55]

    Wheat stripe rust grading by deep learning with attention mechanism and images from mobile devices

    Zhiwen Mi, Xudong Zhang, Jinya Su, Dejun Han, and Baofeng Su. Wheat stripe rust grading by deep learning with attention mechanism and images from mobile devices. Frontiers in Plant Science , 11, 2020. ISSN 1664-462X. doi:10.3389/fpls.2020.558126

    work page doi:10.3389/fpls.2020.558126 2020

  56. [56]

    Identification method of corn leaf disease based on improved mobilenetv3 model

    Chunguang Bi, Suzhen Xu, Nan Hu, Shuo Zhang, Zhenyi Zhu, and Helong Yu. Identification method of corn leaf disease based on improved mobilenetv3 model. Agronomy, 13(2):300, 2023. ISSN 2073-4395. doi:10.3390/agronomy13020300

    work page doi:10.3390/agronomy13020300 2023

  57. [57]

    Classification of cassava leaf disease based on a non- balanced dataset using transformer-embedded resnet

    Yiwei Zhong, Baojin Huang, and Chaowei Tang. Classification of cassava leaf disease based on a non- balanced dataset using transformer-embedded resnet. Agriculture, 12(9):1360, 2022. ISSN 2077-0472. doi:10.3390/agriculture12091360

    work page doi:10.3390/agriculture12091360 2022

  58. [58]

    Junde Chen, Defu Zhang, and Y . A. Nanehkaran. Identifying plant diseases using deep transfer learning and enhanced lightweight network. Multimedia Tools and Applications, 79(41):31497–31515, 2020. ISSN 1573-7721. doi:10.1007/s11042-020-09669-w

    work page doi:10.1007/s11042-020-09669-w 2020

  59. [59]

    A fast and lightweight detection model for wheat fusarium head blight spikes in natural environments

    Chunfeng Gao, Wei Guo, Chenghai Yang, Zheng Gong, Jibo Yue, Yuanyuan Fu, and Haikuan Feng. A fast and lightweight detection model for wheat fusarium head blight spikes in natural environments. Computers and Electronics in Agriculture, 216:108484, 2024. ISSN 0168-1699. doi:10.1016/j.compag.2023.108484

    work page doi:10.1016/j.compag.2023.108484 2024

  60. [60]

    A lightweight rice disease identification network based on attention mechanism and dynamic convolution

    Yuan Yang, Ge Jiao, Jiahao Liu, Weichen Zhao, and Jinhua Zheng. A lightweight rice disease identification network based on attention mechanism and dynamic convolution. Ecological Informatics, 78:102320, 2023. ISSN 1574-9541. doi:10.1016/j.ecoinf.2023.102320

    work page doi:10.1016/j.ecoinf.2023.102320 2023

  61. [61]

    Application of image processing and transfer learning for the detection of rust disease

    Fereshteh Shahoveisi, Hamed Taheri Gorji, Seyedmojtaba Shahabi, Seyedali Hosseinirad, Samuel Markell, and Fartash Vasefi. Application of image processing and transfer learning for the detection of rust disease. Scientific Reports, 13(1):5133, 2023. ISSN 2045-2322. doi:10.1038/s41598-023-31942-9

    work page doi:10.1038/s41598-023-31942-9 2023

  62. [62]

    Krishna Pratap and N

    V . Krishna Pratap and N. Suresh Kumar. High-precision multiclass classification of chili leaf disease through customized efficientnetb4 from chili leaf images. Smart Agricultural Technology, 5:100295, 2023. ISSN 2772-3755. doi:10.1016/j.atech.2023.100295

    work page doi:10.1016/j.atech.2023.100295 2023

  63. [63]

    Md Mustak Un Nobi, Md Rifat, M. F. Mridha, Sultan Alfarhood, Mejdl Safran, and Dunren Che. Gld-det: Guava leaf disease detection in real-time using lightweight deep learning approach based on mobilenet. Agronomy, 13 (9):2240, 2023. ISSN 2073-4395. doi:10.3390/agronomy13092240

    work page doi:10.3390/agronomy13092240 2023

  64. [64]

    Junde Chen, Adnan Zeb, Y . A. Nanehkaran, and Defu Zhang. Stacking ensemble model of deep learning for plant disease recognition. Journal of Ambient Intelligence and Humanized Computing , 14(9):12359–12372,

    work page

  65. [65]

    doi:10.1007/s12652-022-04334-6

    ISSN 1868-5145. doi:10.1007/s12652-022-04334-6. 23 Explainable Artificial Intelligence techniques for interpretation of food datasets: a review A PREPRINT

    work page doi:10.1007/s12652-022-04334-6

  66. [66]

    Com- puter aided detection of mercury heavy metal intoxicated fish: an application of machine vision and artificial intelligence technique

    Ritesh Maurya, Arti Srivastava, Ashutosh Srivastava, Vinay Kumar Pathak, and Malay Kishore Dutta. Com- puter aided detection of mercury heavy metal intoxicated fish: an application of machine vision and artificial intelligence technique. Multimedia Tools and Applications , 82(13):20517–20536, 2023. ISSN 1573-7721. doi:10.1007/s11042-023-14358-5

    work page doi:10.1007/s11042-023-14358-5 2023

  67. [67]

    EffiNet-Ts

    Mamta Gehlot and Geeta Chhabra Gandhi. “EffiNet-Ts”: A deep interpretable architecture using EfficientNet for plant disease detection and visualization. Journal of Plant Diseases and Protection, 130:413–430, 2023. ISSN 1861-3837. doi:10.1007/s41348-023-00707-x

    work page doi:10.1007/s41348-023-00707-x 2023

  68. [68]

    Ashraful Haque, Sudeep Marwaha, Chandan Kumar Deb, Sapna Nigam, and Alka Arora

    Md. Ashraful Haque, Sudeep Marwaha, Chandan Kumar Deb, Sapna Nigam, and Alka Arora. Recognition of diseases of maize crop using deep learning models. Neural Computing and Applications, 35(10):7407–7421,

    work page

  69. [69]

    doi:10.1007/s00521-022-08003-9

    ISSN 1433-3058. doi:10.1007/s00521-022-08003-9

    work page doi:10.1007/s00521-022-08003-9

  70. [70]

    Hein, Raju Bheemanahalli, Impa M

    Chaoxin Wang, Doina Caragea, Nisarga Kodadinne Narayana, Nathan T. Hein, Raju Bheemanahalli, Impa M. Somayanda, and S. V . Krishna Jagadish. Deep learning based high-throughput phenotyping of chalkiness in rice exposed to high night temperature. Plant Methods, 18(1):9, 2022. ISSN 1746-4811. doi:10.1186/s13007-022- 00839-5

    work page doi:10.1186/s13007-022- 2022

  71. [71]

    Identification of plant leaf diseases by deep learning based on channel attention and channel pruning

    Riyao Chen, Haixia Qi, Yu Liang, and Mingchao Yang. Identification of plant leaf diseases by deep learning based on channel attention and channel pruning. Frontiers in Plant Science , 13, 2022. ISSN 1664-462X. doi:10.3389/fpls.2022.1023515

    work page doi:10.3389/fpls.2022.1023515 2022

  72. [72]

    Lightweight corn seed disease iden- tification method based on improved shufflenetv2

    Lu Lu, Wei Liu, Wenbo Yang, Manyu Zhao, and Tinghao Jiang. Lightweight corn seed disease iden- tification method based on improved shufflenetv2. Agriculture, 12(11):1929, 2022. ISSN 2077-0472. doi:10.3390/agriculture12111929

    work page doi:10.3390/agriculture12111929 1929

  73. [73]

    Deep learning-based segmentation and classification of leaf images for detection of tomato plant disease

    Muhammad Shoaib, Tariq Hussain, Babar Shah, Ihsan Ullah, Sayyed Mudassar Shah, Farman Ali, and Sang Hyun Park. Deep learning-based segmentation and classification of leaf images for detection of tomato plant disease. Frontiers in Plant Science, 13, 2022. ISSN 1664-462X. doi:10.3389/fpls.2022.1031748

    work page doi:10.3389/fpls.2022.1031748 2022

  74. [74]

    Classification of fine-grained crop disease by dilated con- volution and improved channel attention module

    Xiang Zhang, Huiyi Gao, and Li Wan. Classification of fine-grained crop disease by dilated con- volution and improved channel attention module. Agriculture, 12(10):1727, 2022. ISSN 2077-0472. doi:10.3390/agriculture12101727

    work page doi:10.3390/agriculture12101727 2022

  75. [75]

    Disease detection, severity prediction, and crop loss estimation in maizecrop using deep learning

    Nidhi Kundu, Geeta Rani, Vijaypal Singh Dhaka, Kalpit Gupta, Siddaiah Chandra Nayaka, Eugenio V ocaturo, and Ester Zumpano. Disease detection, severity prediction, and crop loss estimation in maizecrop using deep learning. Artificial Intelligence in Agriculture, 6:276–291, 2022. ISSN 2589-7217. doi:10.1016/j.aiia.2022.11.002

    work page doi:10.1016/j.aiia.2022.11.002 2022

  76. [76]

    Bakhtiar Hasan, Tasnim Ahmed, Md

    Sabbir Ahmed, Md. Bakhtiar Hasan, Tasnim Ahmed, Md. Redwan Karim Sony, and Md. Hasanul Kabir. Less is more: Lighter and faster deep neural architecture for tomato leaf disease classification. IEEE Access, 10: 68868–68884, 2022. ISSN 2169-3536. doi:10.1109/ACCESS.2022.3187203

    work page doi:10.1109/access.2022.3187203 2022

  77. [77]

    Development of health monitoring method for pecan nut trees using side video data and computer vision

    Ryota Nomura and Kazuo Oki. Development of health monitoring method for pecan nut trees using side video data and computer vision. Optical Review, 28(6):730–737, 2021. ISSN 1349-9432. doi:10.1007/s10043-021- 00694-0

    work page doi:10.1007/s10043-021- 2021

  78. [78]

    Meta-learning for few-shot plant disease detection

    Liangzhe Chen, Xiaohui Cui, and Wei Li. Meta-learning for few-shot plant disease detection. Foods, 10(10): 2441, 2021. ISSN 2304-8158. doi:10.3390/foods10102441

    work page doi:10.3390/foods10102441 2021

  79. [79]

    Muhammad E. H. Chowdhury, Tawsifur Rahman, Amith Khandakar, Mohamed Arselene Ayari, Aftab Ullah Khan, Muhammad Salman Khan, Nasser Al-Emadi, Mamun Bin Ibne Reaz, Mohammad Tariqul Islam, and Sawal Hamid Md Ali. Automatic and reliable leaf disease detection using deep learning techniques. AgriEngineering, 3(2):294–312, 2021. ISSN 2624-7402. doi:10.3390/agri...

    work page doi:10.3390/agriengineering3020020 2021

  80. [80]

    Math and Nagaraj V

    RajinderKumar M. Math and Nagaraj V . Dharwadkar. Early detection and identification of grape diseases using convolutional neural networks. Journal of Plant Diseases and Protection, 129(3):521–532, 2022. ISSN 1861-3837. doi:10.1007/s41348-022-00589-5

    work page doi:10.1007/s41348-022-00589-5 2022

Showing first 80 references.