Sajad Kiani
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Sajad Kiani has a total of 26 co-authors. Here are the top co-authors by number of shared publications:
- Mahdi Ghasemi-Varnamkhasti
Department of Mechanical Engineering of Biosystems, Shahrekord University, Shahrekord, Iran
5 shared publications - Saeid Minaei
Biosystems Engineering Department, Tarbiat Modares University, Tehran, Iran
5 shared publications - Ali Mohammad Kazempour
Biosystems Engineering Department Sari Agricultural Sciences and Natural Resources University Sari Iran
3 shared publications Amin Nikkhah
Department of Food Technology, Safety and Health, Faculty of Bioscience Engineering, Ghent University, Ghent, Belgium
2 shared publicationsDerick Malavi
Department of Food Technology, Safety and Health, Faculty of Bioscience Engineering, Ghent University, Ghent, Belgium
2 shared publicationsHassan Yazdanpanah
Food Safety Research Center, Shahid Beheshti University of Medical Sciences, Tehran, Iran
2 shared publications
Latest Publications
- Open Access
- 3 October 2026
- Published by Elsevier in Journal of Food Composition and Analysis
- Vol. 159
Portable VIS–NIR spectroscopy integrated with machine learning for robust authentication and geographical origin classification of rice
- 3 October 2026
- Published by Elsevier in Journal of Food Composition and Analysis
- Vol. 159
Open AccessPortable VIS–NIR spectroscopy integrated with machine learning for robust authentication and geographical origin classification of rice
- Open Access
- 1 October 2026
- Published by Elsevier in Applied Food Research
- Vol. 6 (2)
Handheld NIR spectroscopy for non-destructive staling monitoring of toast bread: Case 1 – unsupervised clustering-based algorithms
- 1 October 2026
- Published by Elsevier in Applied Food Research
- Vol. 6 (2)
Open AccessHandheld NIR spectroscopy for non-destructive staling monitoring of toast bread: Case 1 – unsupervised clustering-based algorithms
- 24 March 2026
- Published by Wiley in Journal of Food Science
- Vol. 91 (3) , e70891
AI‐Integrated Portable VIS‐NIR Spectroscopy for On‐Site Authenticity Evaluation and Quality Grading of Mutton‐Veal Minced Meat
Minced meat for home cooking is typically made up of 40% mutton and 60% veal, providing a balanced flavor and texture. However, some producers reduce the mutton content to increase profits, leading to consumer dissatisfaction. This study aimed to develop a handheld Visible‐Near Infrared (VIS‐NIR) spectroscopy system coupled with artificial intelligence (AI) algorithms as a rapid, accurate, and non‐destructive method for predicting and grading the mutton‐veal composition of minced meat samples. The weight ratios of the veal in the compositions ranged from 0 to 100% at 2% intervals. Several chemometric and AI methods were used to analyze the spectral data of the prepared minced meat samples captured by a handheld Vis‐NIR spectrometer under LED and bulb light sources. The spectral data were divided for modeling using the stratified and Kennard‐Stone algorithms. Results indicated that the best model was Multi‐Layer Perceptron (MLP) as an artificial neural network algorithm, which achieved R 2 CV and R 2 P (0.879 and 0.916, respectively) for the best scenario of the samples' authenticity prediction. In quality grading, the MLP achieved the highest performance in classifying samples into three quality classes—excellent (Grade A) for 0%–28% veal, medium (Grade B) for 30%–58% veal, and poor (Grade C) for 60%–100% veal—with an accuracy of 92.4%, and precision, recall, and F1 score all reaching 96.2%. These findings confirm that the proposed approach provides a fast, reliable tool for quantifying veal content in minced meat, supporting the development of effective meat quality control systems.
- 24 March 2026
- Published by Wiley in Journal of Food Science
- Vol. 91 (3) , e70891
AI‐Integrated Portable VIS‐NIR Spectroscopy for On‐Site Authenticity Evaluation and Quality Grading of Mutton‐Veal Minced Meat
Minced meat for home cooking is typically made up of 40% mutton and 60% veal, providing a balanced flavor and texture. However, some producers reduce the mutton content to increase profits, leading to consumer dissatisfaction. This study aimed to develop a handheld Visible‐Near Infrared (VIS‐NIR) spectroscopy system coupled with artificial intelligence (AI) algorithms as a rapid, accurate, and non‐destructive method for predicting and grading the mutton‐veal composition of minced meat samples. The weight ratios of the veal in the compositions ranged from 0 to 100% at 2% intervals. Several chemometric and AI methods were used to analyze the spectral data of the prepared minced meat samples captured by a handheld Vis‐NIR spectrometer under LED and bulb light sources. The spectral data were divided for modeling using the stratified and Kennard‐Stone algorithms. Results indicated that the best model was Multi‐Layer Perceptron (MLP) as an artificial neural network algorithm, which achieved R 2 CV and R 2 P (0.879 and 0.916, respectively) for the best scenario of the samples' authenticity prediction. In quality grading, the MLP achieved the highest performance in classifying samples into three quality classes—excellent (Grade A) for 0%–28% veal, medium (Grade B) for 30%–58% veal, and poor (Grade C) for 60%–100% veal—with an accuracy of 92.4%, and precision, recall, and F1 score all reaching 96.2%. These findings confirm that the proposed approach provides a fast, reliable tool for quantifying veal content in minced meat, supporting the development of effective meat quality control systems.
- Open Access
- 1 January 2026
- Published by Wiley in International Journal of Energy Research
- Vol. 2026 (1)
Optimized Simulation of a Solar Reflectance Window‐Infrared Hybrid Dryer With a PV‐Thermal Collector
This study focuses on the simulation, fabrication, and optimization of a combined drying system that uses a reflectance window (RW) integrated with infrared radiation and a photovoltaic‐thermal (PV‐T) solar collector. The simulation tested various configurations, including four layout models (longitudinal, transverse, elliptical, and circular); different pipe diameters (1/4, 1/2, and 3/4 inches) placed behind the PV panel; and multiple irradiation intensities (800, 1000, and 1200 W/m 2 ). This detailed design was created using SolidWorks Flow Simulation software, followed by optimization with Design Expert software. Performance evaluation involved drying apple slices at a fluid temperature of 60°C, water flow rates of 1.5, 2, and 3 L/min, and infrared (IR) intensities of 0.21, 0.33, and 0.49 W/cm 2 . The results showed that the circular pipe arrangement was the most efficient in terms of electrical performance and panel cooling, making it the best configuration. Within this setup, a pipe diameter of 3/4 inch and an irradiation intensity of 1200 W/m 2 achieved the highest overall system efficiency. The optimization results from Design Expert indicated that a linear model best fit the simulated parameters. The maximum drying time and minimum drying rate occurred at 60°C with a hot water flow rate of 1.5 L/min and an IR of 0.21 W/cm 2 , with values of 150 min and 2 g/min, respectively. Conversely, the shortest drying time and highest drying rate were observed at a flow rate of 3 L/min and an IR of 0.49 W/cm 2 , with values of 90 min and 4 g/min, respectively.
- 1 January 2026
- Published by Wiley in International Journal of Energy Research
- Vol. 2026 (1)
Open AccessOptimized Simulation of a Solar Reflectance Window‐Infrared Hybrid Dryer With a PV‐Thermal Collector
This study focuses on the simulation, fabrication, and optimization of a combined drying system that uses a reflectance window (RW) integrated with infrared radiation and a photovoltaic‐thermal (PV‐T) solar collector. The simulation tested various configurations, including four layout models (longitudinal, transverse, elliptical, and circular); different pipe diameters (1/4, 1/2, and 3/4 inches) placed behind the PV panel; and multiple irradiation intensities (800, 1000, and 1200 W/m 2 ). This detailed design was created using SolidWorks Flow Simulation software, followed by optimization with Design Expert software. Performance evaluation involved drying apple slices at a fluid temperature of 60°C, water flow rates of 1.5, 2, and 3 L/min, and infrared (IR) intensities of 0.21, 0.33, and 0.49 W/cm 2 . The results showed that the circular pipe arrangement was the most efficient in terms of electrical performance and panel cooling, making it the best configuration. Within this setup, a pipe diameter of 3/4 inch and an irradiation intensity of 1200 W/m 2 achieved the highest overall system efficiency. The optimization results from Design Expert indicated that a linear model best fit the simulated parameters. The maximum drying time and minimum drying rate occurred at 60°C with a hot water flow rate of 1.5 L/min and an IR of 0.21 W/cm 2 , with values of 150 min and 2 g/min, respectively. Conversely, the shortest drying time and highest drying rate were observed at a flow rate of 3 L/min and an IR of 0.49 W/cm 2 , with values of 90 min and 4 g/min, respectively.
- 13 December 2025
- Published by Elsevier in Journal of Food Engineering
- Vol. 410
AI-powered computer vision system for veal-mutton minced meat authenticity evaluation
- 13 December 2025
- Published by Elsevier in Journal of Food Engineering
- Vol. 410
AI-powered computer vision system for veal-mutton minced meat authenticity evaluation
- 2 December 2025
- Published by Springer Nature in Journal of Food Measurement and Characterization
- Vol. 20 (3) , 2598-2614
Rice authenticity evaluation and adulteration detection using hyperspectral imaging system coupled with deep learning
- 2 December 2025
- Published by Springer Nature in Journal of Food Measurement and Characterization
- Vol. 20 (3) , 2598-2614
Rice authenticity evaluation and adulteration detection using hyperspectral imaging system coupled with deep learning
- 20 April 2025
- Published by Wiley in Cereal Chemistry
- Vol. 102 (3) , 671-680
Integration of Hyperspectral Imaging System and Machine Learning to Predict Amylose Content in Rice
Background and Objectives: This study evaluates the capability of a hyperspectral imaging (HSI) system combined with machine learning techniques as a rapid and non‐destructive technology to predict the percentage of amylose content in rice. Ninety pure rice samples were procured from different geographical origins in Iran. The samples were scanned using the HSI system and then their amylose concentration was determined (based on ISO 6647‐2) to create a reference database.Findings: Spectral data were pre‐processed using MSC and SG algorithms and then were fed to PCA for data reduction. Next, four machine learning methods, PLSR, SVR, MLP, and RBF, were applied to predict the percentage of the amylose content of the rice samples. Results showed that the amylose content was predicted using the PLSR with values of R2val = 0.929, RMSE p = 0.006, and for MLP, RBF, and SVR with values of R2val = 0.971, RMSE p = 0.43, R2val = 0.976, and RMSEP p = 0.0038, and R2val = 0.95, and RMSE p = 0.014, respectively.Conclusions: The artificial intelligence algorithms, MLP and RBF, have predicted similar but better results than the SVR and PLSR methods. Therefore, the HSI system and artificial intelligence algorithms provided satisfactory results.Significance and Novelty: The findings from this study will inform the rice supply chains that the HSI system could be used as a reliable, out‐lab, and fast method for predicting the percentage of amylose content in rice samples.
- 20 April 2025
- Published by Wiley in Cereal Chemistry
- Vol. 102 (3) , 671-680
Integration of Hyperspectral Imaging System and Machine Learning to Predict Amylose Content in Rice
Background and Objectives: This study evaluates the capability of a hyperspectral imaging (HSI) system combined with machine learning techniques as a rapid and non‐destructive technology to predict the percentage of amylose content in rice. Ninety pure rice samples were procured from different geographical origins in Iran. The samples were scanned using the HSI system and then their amylose concentration was determined (based on ISO 6647‐2) to create a reference database.Findings: Spectral data were pre‐processed using MSC and SG algorithms and then were fed to PCA for data reduction. Next, four machine learning methods, PLSR, SVR, MLP, and RBF, were applied to predict the percentage of the amylose content of the rice samples. Results showed that the amylose content was predicted using the PLSR with values of R2val = 0.929, RMSE p = 0.006, and for MLP, RBF, and SVR with values of R2val = 0.971, RMSE p = 0.43, R2val = 0.976, and RMSEP p = 0.0038, and R2val = 0.95, and RMSE p = 0.014, respectively.Conclusions: The artificial intelligence algorithms, MLP and RBF, have predicted similar but better results than the SVR and PLSR methods. Therefore, the HSI system and artificial intelligence algorithms provided satisfactory results.Significance and Novelty: The findings from this study will inform the rice supply chains that the HSI system could be used as a reliable, out‐lab, and fast method for predicting the percentage of amylose content in rice samples.
- 25 May 2024
- Published by Wiley in Journal of Food Science
- Vol. 89 (7) , 4216-4228
Pomegranate molasses authentication using hyperspectral imaging system coupled with automatic clustering algorithm
Pomegranate molasses is made from concentrated pomegranate juice with nothing added. Due to its nutritional value, limitation in production, and high production cost, this product may be adulterated by date syrup. This study was done to differentiate various types of pomegranate molasses and investigate the possibility of nonauthenticity detection in pomegranate molasses samples using the hyperspectral imaging (HSI) technique compared with physicochemical measurement analysis. The physicochemical properties (brix index, sucrose, acidity, ash content, pH, and formalin index) of 24 samples were measured as the reference analysis method, and it was found that the formalin index was a good factor for pomegranate molasses authenticity evaluation. Additionally, an HSI system (400–1000 nm) was used as a nondestructive and rapid screening method to capture spectral data of the samples. The evolutionary wavelength selection algorithm was applied to select effective wavelengths in sample clustering based on the obtained Davies–Bouldin index. Next, principal component analysis was used to visually interpret the spectral data of the sample when using the selected wavelengths and the whole spectra of the samples. Finally, an automatic clustering algorithm by the artificial bee colony as an unsupervised method was developed for the clustering of the authentic and nonauthentic samples. The method did not need descriptively labeled samples and obtained agreed satisfactorily with the degree of nonauthenticity in the samples. This study showed that the developed HSI technique coupled with an automatic clustering algorithm could detect date syrup nonauthenticity in pomegranate samples from the level of 5% adulteration.
- 25 May 2024
- Published by Wiley in Journal of Food Science
- Vol. 89 (7) , 4216-4228
Pomegranate molasses authentication using hyperspectral imaging system coupled with automatic clustering algorithm
Pomegranate molasses is made from concentrated pomegranate juice with nothing added. Due to its nutritional value, limitation in production, and high production cost, this product may be adulterated by date syrup. This study was done to differentiate various types of pomegranate molasses and investigate the possibility of nonauthenticity detection in pomegranate molasses samples using the hyperspectral imaging (HSI) technique compared with physicochemical measurement analysis. The physicochemical properties (brix index, sucrose, acidity, ash content, pH, and formalin index) of 24 samples were measured as the reference analysis method, and it was found that the formalin index was a good factor for pomegranate molasses authenticity evaluation. Additionally, an HSI system (400–1000 nm) was used as a nondestructive and rapid screening method to capture spectral data of the samples. The evolutionary wavelength selection algorithm was applied to select effective wavelengths in sample clustering based on the obtained Davies–Bouldin index. Next, principal component analysis was used to visually interpret the spectral data of the sample when using the selected wavelengths and the whole spectra of the samples. Finally, an automatic clustering algorithm by the artificial bee colony as an unsupervised method was developed for the clustering of the authentic and nonauthentic samples. The method did not need descriptively labeled samples and obtained agreed satisfactorily with the degree of nonauthenticity in the samples. This study showed that the developed HSI technique coupled with an automatic clustering algorithm could detect date syrup nonauthenticity in pomegranate samples from the level of 5% adulteration.
- Open Access
- 9 June 2023
- Published by Springer Nature in Scientific Reports
- Vol. 13 (1) , 1
Author Correction: Prediction of essential oil content in spearmint (Mentha spicata) via near-infrared hyperspectral imaging and chemometrics
- 9 June 2023
- Published by Springer Nature in Scientific Reports
- Vol. 13 (1) , 1
Open AccessAuthor Correction: Prediction of essential oil content in spearmint (Mentha spicata) via near-infrared hyperspectral imaging and chemometrics