FVFartash Vasefi

Fartash Vasefi

*This is an algorithmically generated author record based on publicly available information.

Fartash Vasefi has a total of 68 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Handheld UV-C Fluorescence Imaging with Cascaded Denoising and Deep Learning for Escherichia coli Concentration Classification on Diverse Food-Contact Surfaces

    by Zafar Iqbal, Thomas F. Burks, Sriram Thota, Akash Singh, Snehit Vaddi, Pappu Yadav, Jianwei Qin, Moon S. Kim, Mark A. Ritenour, Jiuxu Zhang, et al.

    Rapid, non-destructive assessment of Escherichia coli contamination levels on food-contact surfaces is important for food safety monitoring and sanitation verification. This study developed a deep-learning framework integrating UV-C fluorescence imaging and cascaded denoising to classify predefined E. coli concentration levels on four food-contact surfaces. A SafetySpect CSI-D+ handheld system acquired fluorescence images at four concentration levels: Control (0), 106, 107, and 108 CFU/mL, on stainless steel, white rubber, white plastic, and black plastic. Five image-denoising operators (wavelet thresholding, NLM, unsharp masking, Wiener filtering, and RL-TV) were evaluated in sequential and parallel configurations. Eight deep-learning classifiers, including five YOLO11-cls variants, EfficientNetB7, ConvNeXtBase, and ViT, were benchmarked using consistent evaluation protocols. Classification performance varied with surface type and denoising strategy. The sequential Wavelet → Wiener → RL-TV cascade achieved the highest observed mean test accuracy (94.18%), with surface-specific accuracies of 97.57%, 97.57%, 94.44%, and 87.15% for stainless steel, white rubber, black plastic, and white plastic, respectively. On the most challenging surface (white plastic), the cascade improved accuracy by 11.46 percentage points over the best single operator. YOLO11-based models generally outperformed ViT, although the highest-performing architecture varied by surface. Most misclassifications occurred primarily between 106 and 107 CFU/mL, while the 108 CFU/mL class was consistently classified accurately. Overall, the ordered cascaded denoising can improve robust E. coli concentration classification across diverse food-contact surfaces, providing a promising foundation for rapid, non-destructive food safety inspection. The results also highlight the importance of surface-specific preprocessing and deep learning architectures for robust performance across diverse materials.

  • Open Access

    Fluorescence Imaging and Machine Learning for Surface Contamination Detection: A Comparative Study with ATP Testing

    by Mahsa Aliee, HamidReza Marateb, Fartash Vasefi, Hossein Kashani Zadeh, Benjamin Hu, Kaylee Yaggie, Moon S. Kime, Insuck Baek, Kouhyar Tavakolian, Bo Liang

    Purpose: This study evaluated UVC-induced fluorescence imaging as an alternative to ATP bioluminescence testing for detecting meat residues on food-contact surfaces. Objectives included assessing classification accuracy, correlation with ATP RLUs, key predictors, and model robustness. Methods and Results: Fluorescence imaging at 275 nm and ATP assays produced 957 images, from which 23 intensity, texture, and edge features were extracted. A TabNetClassifier trained with cross-validation and SMOTETomek resampling achieved a Matthews correlation coefficient and Cohen’s Kappa of 0.77. GEE analysis showed no significant effect of resolution, gain, or exposure on sensitivity or specificity, with borderline impact for wood surfaces (p = 0.08). Texture features, especially Local Binary Patterns, were most predictive. Conclusion: Fluorescence imaging with machine learning is a reliable alternative to ATP testing, offering consistent performance and minimal parameter sensitivity. Future work should refine calibration for specific surfaces and address practical deployment issues, including environmental variability, UVC safety, and integration with automated systems.


  • Open Access

    Detecting Escherichia coli on Conventional Food Processing Surfaces Using UV-C Fluorescence Imaging and Deep Learning

    by Zafar Iqbal, Thomas F. Burks, Snehit Vaddi, Pappu Kumar Yadav, Quentin Frederick, Satya Aakash Chowdary Obellaneni, Jianwei Qin, Moon Kim, Mark A. Ritenour, Jiuxu Zhang, et al.

    Detecting Escherichia coli on food preparation and processing surfaces is critical for ensuring food safety and preventing foodborne illness. This study focuses on detecting E. coli contamination on common food processing surfaces using UV-C fluorescence imaging and deep learning. Four concentrations of E. coli (0, 105, 107, and 108 colony forming units (CFU)/mL) and two egg solutions (white and yolk) were applied to stainless steel and white rubber to simulate realistic contamination with organic interference. For each concentration level, 256 droplets were inoculated in 16 groups, and fluorescence videos were captured. Droplet regions were extracted from the video frames, subdivided into quadrants, and augmented to generate a robust dataset, ensuring 3–4 droplets per sample. Wavelet-based denoising further improved image quality, with Haar wavelets producing the highest Peak Signal-to-Noise Ratio (PSNR) values, up to 51.0 dB on white rubber and 48.2 dB on stainless steel. Using this dataset, multiple deep learning (DL) models, including ConvNeXtBase, EfficientNetV2L, and five YOLO11-cls variants, were trained to classify E. coli concentration levels. Additionally, Eigen-CAM heatmaps were used to visualize model attention to bacterial fluorescence regions. Across four dataset groupings, YOLO11-cls models achieved consistently high performance, with peak test accuracies of 100% on white rubber and 99.60% on stainless steel, even in the presence of egg substances. YOLO11s-cls provided the best balance of accuracy (up to 98.88%) and inference speed (4–5 ms) whilst having a compact size (11 MB), outperforming larger models such as EfficientNetV2L. Classical machine learning models lagged significantly behind, with Random Forest reaching 89.65% accuracy and SVM only 67.62%. Overall, the results highlight the potential of combining UV-C fluorescence imaging with deep learning for rapid and reliable detection of E. coli on stainless steel and rubber conveyor belt surfaces. Additionally, this approach could support the design of effective interventions to remove E. coli from food processing environments.


  • Open Access

    Detecting Escherichia coli Contamination on Plant Leaf Surfaces Using UV-C Fluorescence Imaging and Deep Learning

    by Snehit Vaddi, Thomas F. Burks, Zafar Iqbal, Pappu Kumar Yadav, Quentin Frederick, Satya Aakash Chowdary Obellaneni, Jianwei Qin, Moon Kim, Mark A. Ritenour, Jiuxu Zhang, et al.

    The transmission of Escherichia coli through contaminated fruits and vegetables poses serious public health risks and has led to several national outbreaks in the USA. To enhance food safety, rapid and reliable detection of E. coli on produce is essential. This study evaluated the performance of the CSI-D+ system combined with deep learning for detecting varying concentrations of E. coli on citrus and spinach leaves. Eight levels of E. coli contamination, ranging from 0 to 108 colony-forming units (CFU)/mL, were inoculated onto the leaf surfaces. For each concentration level, 10 droplets were applied to 8 citrus and 12 spinach leaf samples (2 cm in diameter), and fluorescence images were captured. The images were then subdivided into quadrants, and several post-processing operations were applied to generate the final dataset, ensuring that each sample contained at least 2–3 droplets. Using this dataset, multiple deep learning (DL) models, including EfficientNetB7, ConvNeXtBase, and five YOLO11 variants (n, s, m, l, x), were trained to classify E. coli concentration levels. Additionally, Eigen-CAM heatmaps were used to visualize the spatial responses of the models to bacterial presence. All YOLO11 models outperformed EfficientNetB7 and ConvNeXtBase. In particular, YOLO11s-cls was identified as the best-performing model, achieving average validation accuracies of 88.43% (citrus) and 92.03% (spinach), and average test accuracies of 85.93% (citrus) and 92.00% (spinach) at a 0.5 confidence threshold. This model demonstrated an inference speed of 0.011 s per image with a size of 11 MB. These findings indicate that fluorescence-based imaging combined with deep learning for rapid E. coli detection could support timely interventions to prevent contaminated produce from reaching consumers.


  • Open Access

    A Blockchain-Based Fish Supply Chain Framework for Maintaining Fish Quality and Authenticity

    by Shereen Ismail, Muhammad Nouman, Hassan Reza, Fartash Vasefi, Hossein Kashani Zadeh

    The fish supply chain (FSC) industry faces a significant challenge in terms of maintaining fish quality and authenticity throughout the chain. The main goal of modern FSC systems is tracking and tracing the fish product at each stage, from harvester to end customer, as well as assessing its quality and authenticity. Integrating FSC with new technologies, such as Blockchain (BC), Big Data, Artificial intelligence (AI), and Internet of Things (IoT), enhances fish product traceability, authenticity, visibility, and security. We propose a BC-based FSC framework that follows a layered architecture consisting of a SC layer, an IoT layer, and a BC layer. We integrate a new AI-based hand-held device, a Quality, Adulteration & Traceability (QAT) device, that can identify fish species and assess fish quality. We leverage the key features of BC and smart contracts, deployed over the Ethereum platform for the proposed framework integrated with QAT technology. Extensive validation of smart contracts is conducted to prove its practical feasibility.


  • Open Access

    A Novel Machine-Learning Framework Based on a Hierarchy of Dispute Models for the Identification of Fish Species Using Multi-Mode Spectroscopy

    by Mitchell Sueker, Amirreza Daghighi, Alireza Akhbardeh, Nicholas MacKinnon, Gregory Bearman, Insuck Baek, Chansong Hwang, Jianwei Qin, Amanda M. Tabb, Jiahleen B. Roungchun, et al.

    Seafood mislabeling rates of approximately 20% have been reported globally. Traditional methods for fish species identification, such as DNA analysis and polymerase chain reaction (PCR), are expensive and time-consuming, and require skilled technicians and specialized equipment. The combination of spectroscopy and machine learning presents a promising approach to overcome these challenges. In our study, we took a comprehensive approach by considering a total of 43 different fish species and employing three modes of spectroscopy: fluorescence (Fluor), and reflectance in the visible near-infrared (VNIR) and short-wave near-infrared (SWIR). To achieve higher accuracies, we developed a novel machine-learning framework, where groups of similar fish types were identified and specialized classifiers were trained for each group. The incorporation of global (single artificial intelligence for all species) and dispute classification models created a hierarchical decision process, yielding higher performances. For Fluor, VNIR, and SWIR, accuracies increased from 80%, 75%, and 49% to 83%, 81%, and 58%, respectively. Furthermore, certain species witnessed remarkable performance enhancements of up to 40% in single-mode identification. The fusion of all three spectroscopic modes further boosted the performance of the best single mode, averaged over all species, by 9%. Fish species mislabeling not only poses health-related risks due to contaminants, toxins, and allergens that could be life-threatening, but also gives rise to economic and environmental hazards and loss of nutritional benefits. Our proposed method can detect fish fraud as a real-time alternative to DNA barcoding and other standard methods. The hierarchical system of dispute models proposed in this work is a novel machine-learning tool not limited to this application, and can improve accuracy in any classification problem which contains a large number of classes.


  • Open Access

    Federated Learning for Clients’ Data Privacy Assurance in Food Service Industry

    by Hamed Taheri Gorji, Mahdi Saeedi, Erum Mushtaq, Hossein Kashani Zadeh, Kaylee Husarik, Seyed Mojtaba Shahabi, Jianwei Qin, Diane E. Chan, Insuck Baek, Moon S. Kim, et al.

    The food service industry must ensure that service facilities are free of foodborne pathogens hosted by organic residues and biofilms. Foodborne diseases put customers at risk and compromise the reputations of service providers. Fluorescence imaging, empowered by state-of-the-art artificial intelligence (AI) algorithms, can detect invisible residues. However, using AI requires large datasets that are most effective when collected from actual users, raising concerns about data privacy and possible leakage of sensitive information. In this study, we employed a decentralized privacy-preserving technology to address client data privacy issues. When federated learning (FL) is used, there is no need for data sharing across clients or data centralization on a server. We used FL and a new fluorescence imaging technology and applied two deep learning models, MobileNetv3 and DeepLabv3+, to identify and segment invisible residues on food preparation equipment and surfaces. We used FedML as our FL framework and Fedavg as the aggregation algorithm. The model achieved training and testing accuracies of 95.83% and 94.94% for classification between clean and contamination frames, respectively, and resulted in intersection over union (IoU) scores of 91.23% and 89.45% for training and testing, respectively, of segmentation of the contaminated areas. The results demonstrated that using federated learning combined with fluorescence imaging and deep learning algorithms can improve the performance of cleanliness auditing systems while assuring client data privacy.


  • Open Access

    Rapid Assessment of Fish Freshness for Multiple Supply-Chain Nodes Using Multi-Mode Spectroscopy and Fusion-Based Artificial Intelligence

    by Hossein Kashani Zadeh, Mike Hardy, Mitchell Sueker, Yicong Li, Angelis Tzouchas, Nicholas MacKinnon, Gregory Bearman, Simon A. Haughey, Alireza Akhbardeh, Insuck Baek, et al.

    This study is directed towards developing a fast, non-destructive, and easy-to-use handheld multimode spectroscopic system for fish quality assessment. We apply data fusion of visible near infra-red (VIS-NIR) and short wave infra-red (SWIR) reflectance and fluorescence (FL) spectroscopy data features to classify fish from fresh to spoiled condition. Farmed Atlantic and wild coho and chinook salmon and sablefish fillets were measured. Three hundred measurement points on each of four fillets were taken every two days over 14 days for a total of 8400 measurements for each spectral mode. Multiple machine learning techniques including principal component analysis, self-organized maps, linear and quadratic discriminant analyses, k-nearest neighbors, random forest, support vector machine, and linear regression, as well as ensemble and majority voting methods, were used to explore spectroscopy data measured on fillets and to train classification models to predict freshness. Our results show that multi-mode spectroscopy achieves 95% accuracy, improving the accuracies of the FL, VIS-NIR and SWIR single-mode spectroscopies by 26, 10 and 9%, respectively. We conclude that multi-mode spectroscopy and data fusion analysis has the potential to accurately assess freshness and predict shelf life for fish fillets and recommend this study be expanded to a larger number of species in the future.


  • Open Access

    Toward an Intelligent Blockchain IoT-Enabled Fish Supply Chain: A Review and Conceptual Framework

    by Shereen Ismail, Hassan Reza, Khouloud Salameh, Hossein Kashani Zadeh, Fartash Vasefi

    The fish industry experiences substantial illegal, unreported, and unregulated (IUU) activities within traditional supply chain systems. Blockchain technology and the Internet of Things (IoT) are expected to transform the fish supply chain (SC) by incorporating distributed ledger technology (DLT) to build trustworthy, transparent, decentralized traceability systems that promote secure data sharing and employ IUU prevention and detection methods. We have reviewed current research efforts directed toward incorporating Blockchain in fish SC systems. We have discussed traceability in both traditional and smart SC systems that make use of Blockchain and IoT technologies. We demonstrated the key design considerations in terms of traceability in addition to a quality model to consider when designing smart Blockchain-based SC systems. In addition, we proposed an Intelligent Blockchain IoT-enabled fish SC framework that uses DLT for the trackability and traceability of fish products throughout harvesting, processing, packaging, shipping, and distribution to final delivery. More precisely, the proposed framework should be able to provide valuable and timely information that can be used to track and trace the fish product and verify its authenticity throughout the chain. Unlike other work, we have investigated the benefits of integrating machine learning (ML) into Blockchain IoT-enabled SC systems, focusing the discussion on the role of ML in fish quality, freshness assessment and fraud detection.


  • Open Access

    Simulated Annealing-Based Wavelength Selection for Robust Tissue Oxygenation Estimation Powered by the Extended Modified Lambert–Beer Law

    by John Chauvin, Alireza Akhbardeh, Robert Brunnemer, Fartash Vasefi, Gregory Bearman, Audrey Huong, Kouhyar Tavakolian

    In this paper, we present a set of algorithms to enable the development of inexpensive hyperspectral sensors capable of estimating tissue oxygenation for wound monitoring. Estimation is conducted using the extended modified Lambert–Beer law, which has previously been proven robust to differences in melanin concentration. We introduce a novel wavelength selection algorithm that enables the estimation to be performed with high accuracy using only a small number (5–10) of wavelengths. Validation performed with Monte Carlo simulation data resulted in prediction errors <1%, with no significant differences among various skin types, for as few as five wavelengths under conditions representing both high precision instrumentation and more cost-effective sensors designed with inexpensive LEDs and/or filters. Validation with in vivo data collected from an occlusion study with 13 Asian volunteers showed statistically significant separation between the estimates for the at-rest and arterial occlusion states. Additional stability testing proved the proposed algorithms to be robust to small changes in the selected wavelengths as may occur in a real LED due to manufacturing tolerances and temperature fluctuations. This work concluded that the development of an inexpensive hyperspectral device for wound monitoring in all skin types is feasible using just a small number of wavelengths.