IU Indianapolis ScholarWorks :: Browsing by Subject "convolutional neural network"

Browsing by Subject "convolutional neural network"

Now showing 1 - 8 of 8

CondenseNeXtV2: Light-Weight Modern Image Classifier Utilizing Self-Querying Augmentation Policies
(MDPI, 2022) Kalgaonkar, Priyank; El-Sharkawy, Mohamed; Electrical and Computer Engineering, School of Engineering and Technology
Artificial Intelligence (AI) combines computer science and robust datasets to mimic natural intelligence demonstrated by human beings to aid in problem-solving and decision-making involving consciousness up to a certain extent. From Apple’s virtual personal assistant, Siri, to Tesla’s self-driving cars, research and development in the field of AI is progressing rapidly along with privacy concerns surrounding the usage and storage of user data on external servers which has further fueled the need of modern ultra-efficient AI networks and algorithms. The scope of the work presented within this paper focuses on introducing a modern image classifier which is a light-weight and ultra-efficient CNN intended to be deployed on local embedded systems, also known as edge devices, for general-purpose usage. This work is an extension of the award-winning paper entitled ‘CondenseNeXt: An Ultra-Efficient Deep Neural Network for Embedded Systems’ published for the 2021 IEEE 11th Annual Computing and Communication Workshop and Conference (CCWC). The proposed neural network dubbed CondenseNeXtV2 utilizes a new self-querying augmentation policy technique on the target dataset along with adaption to the latest version of PyTorch framework and activation functions resulting in improved efficiency in image classification computation and accuracy. Finally, we deploy the trained weights of CondenseNeXtV2 on NXP BlueBox which is an edge device designed to serve as a development platform for self-driving cars, and conclusions will be extrapolated accordingly.
Convolutional neural network model for soil moisture prediction and its transferability analysis based on laboratory Vis-NIR spectral data
(Elsevier, 2021-12) Chen, Yu; Li, Lin; Whiting, Michael; Chen, Fang; Sun, Zhongchang; Song, Kaishan; Wang, Qinjun; Earth Sciences, School of Science
Laboratory visible near infrared reflectance (Vis-NIR, 400–2500 nm) spectroscopy has the advantages of simplicity, fast and non-destructive which was used for SM prediction. However, many previously proposed models are difficult to transfer to unknown target areas without recalibration. In this study, we first developed a suitable Convolutional Neutral Network (CNN) model and transferred the model to other target areas for two situations using different soil sample backgrounds under 1) the same measurement conditions (DSSM), and 2) under different measurement conditions (DSDM). We also developed the CNN models for the target areas based on their own datasets and traditional PLS models was developed to compare their performances. The results show that one dimensional model (1D-CNN) performed strongly for SM prediction with average R2 up to 0.989 and RPIQ up to 19.59 in the laboratory environment (DSSM). Applying the knowledge-based transfer learning method to an unknown target area improved the R2 from 0.845 to 0.983 under the DSSM and from 0.298 to 0.620 under the DSDM, which performed better than data-based spiking calibration method for traditional PLS models. The results show that knowledge-based transfer learning was suitable for SM prediction under different soil background and measurement conditions and can be a promising approach for remotely estimating SM with the increasing amount of soil dataset in the future.
Deep Learning Algorithm for the Confirmation of Mucosal Healing in Crohn’s Disease, Based on Confocal Laser Endomicroscopy Images
(2021) Udristoiu, Anca Loredana; Stefanescu, Daniela; Gruionu, Gabriel; Gruionu, Lucian Gheorghe; Iacob, Andreea Valentina; Karstensen, John Gasdal; Vilman, Peter; Saftoiu, Adrian; Medicine, School of Medicine
Background and Aims: Mucosal healing (MH) is associated with a stable course of Crohn’s disease (CD) which can be assessed by confocal laser endomicroscopy (CLE). To minimize the operator’s errors and automate assessment of CLE images, we used a deep learning (DL) model for image analysis. We hypothesized that DL combined with convolutional neural networks (CNNs) and long short-term memory (LSTM) can distinguish between normal and inflamed colonic mucosa from CLE images. Methods: The study included 54 patients, 32 with known active CD, and 22 control patients (18 CD patients with MH and four normal mucosa patients with no history of inflammatory bowel diseases). We designed and trained a deep convolutional neural network to detect active CD using 6,205 endomicroscopy images classified as active CD inflammation (3,672 images) and control mucosal healing or no inflammation (2,533 images). CLE imaging was performed on four colorectal areas and the terminal ileum. Gold standard was represented by the histopathological evaluation. The dataset was randomly split in two distinct training and testing datasets: 80% data from each patient were used for training and the remaining 20% for testing. The training dataset consists of 2,892 images with inflammation and 2,189 control images. The testing dataset consists of 780 images with inflammation and 344 control images of the colon. We used a CNN-LSTM model with four convolution layers and one LSTM layer for automatic detection of MH and CD diagnosis from CLE images. Results: CLE investigation reveals normal colonic mucosa with round crypts and inflamed mucosa with irregular crypts and tortuous and dilated blood vessels. Our method obtained a 95.3% test accuracy with a specificity of 92.78% and a sensitivity of 94.6%, with an area under each receiver operating characteristic curves of 0.98. Conclusions: Using machine learning algorithms on CLE images can successfully differentiate between inflammation and normal ileocolonic mucosa and can be used as a computer aided diagnosis for CD. Future clinical studies with a larger patient spectrum will validate our results and improve the CNN-SSTM model.
Image Classification with CondenseNeXt for ARM-Based Computing Platforms
(IEEE, 2021-04) Kalgaonkar, Priyank; El-Sharkawy, Mohamed; Electrical and Computer Engineering, School of Engineering and Technology
In this paper, we demonstrate the implementation of our ultra-efficient deep convolutional neural network architecture: CondenseNeXt on NXP BlueBox, an autonomous driving development platform developed for self-driving vehicles. We show that CondenseNeXt is remarkably efficient in terms of FLOPs, designed for ARM-based embedded computing platforms with limited computational resources and can perform image classification without the need of a CUDA enabled GPU. CondenseNeXt utilizes the state-of-the-art depthwise separable convolution and model compression techniques to achieve a remarkable computational efficiency. Extensive analyses are conducted on CIFAR-10, CIFAR-100 and ImageNet datasets to verify the performance of Con-denseNeXt Convolutional Neural Network (CNN) architecture. It achieves state-of-the-art image classification performance on three benchmark datasets including CIFAR-10 (4.79% top-1 error), CIFAR-100 (21.98% top-1 error) and ImageNet (7.91% single model, single crop top-5 error). CondenseNeXt achieves final trained model size improvement of 2.9+ MB and up to 59.98% reduction in forward FLOPs compared to CondenseNet and can perform image classification on ARM-Based computing platforms without needing a CUDA enabled GPU support, with outstanding efficiency.
Increasing CNN Representational Power Using Absolute Cosine Value Regularization
(IEEE, 2020-08) Singleton, William; El-Sharkawy, Mohamed; Electrical and Computer Engineering, School of Engineering and Technology
The Convolutional Neural Network (CNN) is a mathematical model designed to distill input information into a more useful representation. This distillation process removes information over time through a series of dimensionality reductions, which ultimately, grant the model the ability to resist noise and generalize effectively. However, CNNs often contain elements that are ineffective at contributing towards useful representations. This paper aims at providing a remedy for this problem by introducing Absolute Cosine Value Regularization (ACVR). This is a regularization technique hypothesized to increase the representational power of CNNs by using a Gradient Descent Orthogonalization algorithm to force the vectors that constitute their filters at any given convolutional layer to occupy unique positions in ℝ n . This method should in theory, lead to a more effective balance between information loss and representational power, ultimately, increasing network performance. The following paper examines the mathematics and intuition behind this Regularizer, as well as its effects on the filters of a low-dimensional CNN.
Mitotic cell detection in H&E stained meningioma histopathology slides
(2019-12) Cheng, Huiwen; Tsechpenakis, Gavriil; Tuceryan, Mihran; Jiang, Yu zheng
Meningioma represent more than one-third of all primary central nervous system (CNS) tumors, and it can be classified into three grades according to WHO (World Health Organization) in terms of clinical aggressiveness and risk of recurrence. A key component of meningioma grades is the mitotic count, which is defined as quantifying the number of cells in the process of dividing (i.e., undergoing mitosis) at a specific point in time. Currently, mitosis counting is done manually by a pathologist looking at 10 consecutive high-power fields (HPF) on a glass slide under a microscope, which is an extremely laborious and time-consuming process. The goal of this thesis is to investigate the use of computerized methods to automate the detection of mitotic nuclei with limited labeled data. We built computational methods to detect and quantify the histological features of mitotic cells on a whole slides image which mimic the exact process of pathologist workflow. Since we do not have enough training data from meningioma slide, we learned the mitotic cell features through public available breast cancer datasets, and predicted on meingioma slide for accuracy. We use either handcrafted features that capture certain morphological, statistical, or textural attributes of mitoses or features learned with convolutional neural networks (CNN). Hand crafted features are inspired by the domain knowledge, while the data-driven VGG16 models tend to be domain agnostic and attempt to learn additional feature bases that cannot be represented through any of the handcrafted features. Our work on detection of mitotic cells shows 100% recall , 9% precision and 0.17 F1 score. The detection using VGG16 performs with 71% recall, 73% precision, and 0.77 F1 score. Finally, this research of automated image analysis could drastically increase diagnostic efficiency and reduce inter-observer variability and errors in pathology diagnosis, which would allow fewer pathologists to serve more patients while maintaining diagnostic accuracy and precision. And all these methodologies will increasingly transform practice of pathology, allowing it to mature toward a quantitative science.
NextDet: Efficient Sparse-to-Dense Object Detection with Attentive Feature Aggregation
(MDPI, 2022-11-28) Kalgaonkar, Priyank; El-Sharkawy, Mohamed; Electrical and Computer Engineering, School of Engineering and Technology
Object detection is a computer vision task of detecting instances of objects of a certain class, identifying types of objects, determining its location, and accurately labelling them in an input image or a video. The scope of the work presented within this paper proposes a modern object detection network called NextDet to efficiently detect objects of multiple classes which utilizes CondenseNeXt, an award-winning lightweight image classification convolutional neural network algorithm with reduced number of FLOPs and parameters as the backbone, to efficiently extract and aggregate image features at different granularities in addition to other novel and modified strategies such as attentive feature aggregation in the head, to perform object detection and draw bounding boxes around the detected objects. Extensive experiments and ablation tests, as outlined in this paper, are performed on Argoverse-HD and COCO datasets, which provide numerous temporarily sparse to dense annotated images, demonstrate that the proposed object detection algorithm with CondenseNeXt as the backbone result in an increase in mean Average Precision (mAP) performance and interpretability on Argoverse-HD’s monocular ego-vehicle camera captured scenarios by up to 17.39% as well as COCO’s large set of images of everyday scenes of real-world common objects by up to 14.62%.
Three Dimensional Nuclei Segmentation and Classification of Fluorescence Microscopy Images
(IEEE, 2020-04) Han, Shuo; Lee, Soonam; Chen, Alain; Yang, Changye; Salama, Paul; Dunn, Kenneth W.; Delp, Edward J.; Electrical and Computer Engineering, School of Engineering and Technology
Segmentation and classification of cell nuclei in fluorescence 3D microscopy image volumes are fundamental steps for image analysis. However, accurate cell nuclei segmentation and detection in microscopy image volumes are hampered by poor image quality, crowding of nuclei, and large variation in nuclei size and shape. In this paper, we present an unsupervised volume to volume translation approach adapted from the Recycle-GAN using modified Hausdorff distance loss for synthetically generating nuclei with better shapes. A 3D CNN with a regularization term is used for nuclei segmentation and classification followed by nuclei boundary refinement. Experimental results demonstrate that the proposed method can successfully segment nuclei and identify individual nuclei.

Browsing by Subject "convolutional neural network"

Results Per Page

Sort Options