An official website of the United States government
Abstract Pollen identification is necessary for several subfields of geology, ecology, and evolutionary biology. However, the existing methods for pollen identification are laborious, time-consuming, and require highly skilled scientists. Therefore, there is a pressing need for an automated and accurate system for pollen identification, which can be beneficial for both basic research and applied issues such as identifying airborne allergens. In this study, we propose a deep learning (DL) approach to classify pollen grains in the Great Basin Desert, Nevada, USA. Our dataset consisted of 10,000 images of 40 pollen species. To mitigate the limitations imposed by the small volume of our training dataset, we conducted an in-depth comparative analysis of numerous pre-trained Convolutional Neural Network (CNN) architectures utilizing transfer learning methodologies. Simultaneously, we developed and incorporated an innovative CNN model, serving to augment our exploration and optimization of data modeling strategies. We applied different architectures of well-known pre-trained deep CNN models, including AlexNet, VGG-16, MobileNet-V2, ResNet (18, 34, and 50, 101), ResNeSt (50, 101), SE-ResNeXt, and Vision Transformer (ViT), to uncover the most promising modeling approach for the classification of pollen grains in the Great Basin. To evaluate the performance of the pre-trained deep CNN models, we measured accuracy, precision, F1-Score, and recall. Our results showed that the ResNeSt-110 model achieved the best performance, with an accuracy of 97.24%, precision of 97.89%, F1-Score of 96.86%, and recall of 97.13%. Our results also revealed that transfer learning models can deliver better and faster image classification results compared to traditional CNN models built from scratch. The proposed method can potentially benefit various fields that rely on efficient pollen identification. This study demonstrates that DL approaches can improve the accuracy and efficiency of pollen identification, and it provides a foundation for further research in the field.
more »
« less
Automated lensless blood sample identification through scattering media using deep learning architectures
Lensless devices paired with deep learning models have recently shown great promise as a novel approach to biological screening. As a first step toward performing automated lensless cell identification non-invasively, we present a field-portable, compact lensless system that can detect and classify smeared whole blood samples through layers of scattering media. In this system, light from a partially coherent laser diode propagates through the sample, which is positioned between two layers of scattering media, and the resultant opto-biological signature is captured by an image sensor. The signature is transformed via local binary pattern (LBP) transformation, and the resultant LBP images are processed by a convolutional neural network (CNN) to identify the type of red blood cells in the sample. We validated our system in an experimental setup where whole blood samples are placed between two diffusive layers of increasing thickness, and the robustness of the system against variations in the layer thickness is investigated. Several CNN models were considered (i.e., AlexNet, VGG-16, and SqueezeNet), individually optimized, and compared against a traditional learning model that consists of principal component decomposition and support vector machine (PCA + SVM). We found that a two-stage SqueezeNet architecture and VGG-16 provide the highest classification accuracy and Matthew’s correlation coefficient (MCC) score when applied to images acquired by our lensless system, with SqueezeNet outperforming the other classifiers when the thickness of the scattering layer is the same in training and test data (accuracy: 97.2%; MCC: 0.96), and VGG-16 resulting the most robust option as the thickness of the scattering layers in test data increases up to three times the value used during training. Altogether, this work provides proof-of-concept for non-invasive blood sample identification through scattering media with lensless devices using deep learning. Our system has the potential to be a viable diagnosis device because of its low cost, field portability, and high identification accuracy.
more »
« less
- Award ID(s):
- 2141473
- PAR ID:
- 10569226
- Publisher / Repository:
- Optical Society of America
- Date Published:
- Journal Name:
- Optics Express
- Volume:
- 33
- Issue:
- 3
- ISSN:
- 1094-4087; OPEXFF
- Format(s):
- Medium: X Size: Article No. 4534
- Size(s):
- Article No. 4534
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Kim, Euishin E (Ed.)Background:Early disease detection is emphasized within ophthalmology now more than ever, and as a result, clinicians and innovators turn to deep learning toexpedite accurate diagnosis and mitigate treatment delay. Efforts concentrate on the creation of deep learning systems that analyze clinical imagedata to detect disease-specific features with maximum sensitivity. Moreover, these systems hold promise of early accurate diagnosis and treatmentof patients with common progressive diseases. DenseNet, ResNet, and VGG-16 are among a few of the deep learning Convolutional NeuralNetwork (CNN) algorithms that have been introduced and are being investigated for potential application within ophthalmology. Methods:In this study, the authors sought to create and evaluate a novel ensembled deep learning CNN model that analyzes a dataset of shuffled retinal colorfundus images (RCFIs) from eyes with various ocular disease features (cataract, glaucoma, diabetic retinopathy). Our aim was to determine (1) therelative performance of our finalized model in classifying RCFIs according to disease and (2) the diagnostic potential of the finalized model toserve as a screening test for specific diseases (cataract, glaucoma, diabetic retinopathy) upon presentation of RCFIs with diverse diseasemanifestations. Results:We found adding convolutional layers to an existing VGG-16 model, which was named as a proposed model in this article that, resulted insignificantly increased performance with 98% accuracy (p<0.05), including good diagnostic potential for binary disease detection in cataract,glaucoma, diabetic retinopathy. Conclusion:The proposed model was found to be suitable and accurate for a decision support system in Ophthalmology Clinical Framework.more » « less
-
In this work, a high-speed and energy-efficient comparator-based N ear- S ensor L ocal B inary P attern accelerator architecture (NS-LBP) is proposed to execute a novel local binary pattern deep neural network. First, inspired by recent LBP networks, we design an approximate, hardware-oriented, and multiply-accumulate (MAC)-free network named Ap-LBP for efficient feature extraction, further reducing the computation complexity. Then, we develop NS-LBP as a processing-in-SRAM unit and a parallel in-memory LBP algorithm to process images near the sensor in a cache, remarkably reducing the power consumption of data transmission to an off-chip processor. Our circuit-to-application co-simulation results on MNIST and SVHN datasets demonstrate minor accuracy degradation compared to baseline CNN and LBP-network models, while NS-LBP achieves 1.25 GHz and an energy-efficiency of 37.4 TOPS/W. NS-LBP reduces energy consumption by 2.2× and execution time by a factor of 4× compared to the best recent LBP-based networks.more » « less
-
null (Ed.)In the realm of computer security, the username/password standard is becoming increasingly antiquated. Usage of the same username and password across various accounts can leave a user open to potential vulnerabilities. Authentication methods of the future need to maintain the ability to provide secure access without a reduction in speed. Facial recognition technologies are quickly becoming integral parts of user security, allowing for a secondary level of user authentication. Augmenting traditional username and password security with facial biometrics has already seen impressive results; however, studying these techniques is necessary to determine how effective these methods are within various parameters. A Convolutional Neural Network (CNN) is a powerful classification approach which is often used for image identification and verification. Quite recently, CNNs have shown great promise in the area of facial image recognition. The comparative study proposed in this paper offers an in-depth analysis of several state-of-the-art deep learning based-facial recognition technologies, to determine via accuracy and other metrics which of those are most effective. In our study, VGG-16 and VGG-19 showed the highest levels of image recognition accuracy, as well as F1-Score. The most favorable configurations of CNN should be documented as an effective way to potentially augment the current username/password standard by increasing the current method’s security with additional facial biometrics.more » « less
-
Agaian, Sos S.; DelMarco, Stephen P.; Asari, Vijayan K. (Ed.)Iris recognition is a widely used biometric technology that has high accuracy and reliability in well-controlled environments. However, the recognition accuracy can significantly degrade in non-ideal scenarios, such as off-angle iris images. To address these challenges, deep learning frameworks have been proposed to identify subjects through their off-angle iris images. Traditional CNN-based iris recognition systems train a single deep network using multiple off-angle iris image of the same subject to extract the gaze invariant features and test incoming off-angle images with this single network to classify it into same subject class. In another approach, multiple shallow networks are trained for each gaze angle that will be the experts for specific gaze angles. When testing an off-angle iris image, we first estimate the gaze angle and feed the probe image to its corresponding network for recognition. In this paper, we present an analysis of the performance of both single and multimodal deep learning frameworks to identify subjects through their off-angle iris images. Specifically, we compare the performance of a single AlexNet with multiple SqueezeNet models. SqueezeNet is a variation of the AlexNet that uses 50x fewer parameters and is optimized for devices with limited computational resources. Multi-model approach using multiple shallow networks, where each network is an expert for a specific gaze angle. Our experiments are conducted on an off-angle iris dataset consisting of 100 subjects captured at 10-degree intervals between -50 to +50 degrees. The results indicate that angles that are more distant from the trained angles have lower model accuracy than the angles that are closer to the trained gaze angle. Our findings suggest that the use of SqueezeNet, which requires fewer parameters than AlexNet, can enable iris recognition on devices with limited computational resources while maintaining accuracy. Overall, the results of this study can contribute to the development of more robust iris recognition systems that can perform well in non-ideal scenarios.more » « less
