Narrow Results

This paper proposes a convolutional neural network for diagnosing various lung illnesses from chest CT images based on a customized Medical Image Analysis and Detection network (MIDNet18). With simplified model building, minimal complexity, easy technique, and high-performance accuracy, the MIDNet-18 CNN architecture classifies binary and multiclass medical images. Fourteen convolutional layers, 7 pooling layers, 4 dense layers, and 1 classification layer comprise the MIDNet-18 architecture. The medical image classification process involves training, validating, and testing the MIDNet-18 model. In the Lung CT image binary class dataset, 2214 images as training set, 1800 images as validation set, and 831 as test set are considered for classifying COVID images and normal lung images. In the multiclass dataset, 6720 images as training sets belonging to 3 classes, 3360 images as validation sets and 601 images as test sets are considered for classifying COVID, cancer images and normal images. Independent sample size calculated for binary classification is 26 samples for each group. Similarly, 10 sample sizes are calculated for multiclass dataset classification keeping GPower at 80%. To validate the performance of the MIDNet18 CNN architecture, the medical images of two different datasets are compared with existing models like LeNet-5, VGG-16, VGG-19, ResNet-50. In multiclass classification, the MIDNet-18 architecture gives better training accuracy and test accuracy, while the LeNet5 model obtained 92.6% and 95.9%, respectively. Similarly, VGG-16 is 89.3% and 77.2% respectively; VGG-19 is 85.8% and 85.4%, respectively; ResNet50 is 90.6% and 99%, respectively. For binary classification, the MIDNet18 architecture gives better training accuracy and test accuracy, while the LeNet-5 model has obtained 52.3% and 54.3%, respectively. Similarly, VGG 16 is 50.5% and 45.6%, respectively; VGG-19 is 50.6% and 45.6%, respectively; ResNet-50 is 96.1% and 98.4%, respectively. The classified images are further predicted using detectron-2 model and the results identify abnormalities (cancer, COVID-19) with 99% accuracy. The MIDNET18 is significantly more accurate than LeNet5, VGG19, VGG16 algorithms and is marginally better than the RESNET50 algorithm for the given lung binary dataset (Bonferroni — one-way Anova and pairwise comparison of MIDNET, LeNet5, VGG19, VGG16, and RESNET 50 ($p>0.05$)). The proposed MIDNet18 model is significantly more accurate than LeNet5, VGG19, VGG16, ResNet50 algorithms in classifying the diseases for the given multiclass lung dataset (Bonferroni — one-way Anova and pairwise comparison of MIDNET18, LeNet5, VGG19, VGG16, ResNet50 ($p>0.05$)).

Sign language recognition (SLR) is a useful tool for the deaf-mute to communicate with the outside world. Although many SLR methods have been proposed and have demonstrated good performance, continuous SLR (CSLR) is still challenging. Meanwhile, due to the heavy occlusions and closely interacting motions, there is a higher requirement for the real-time efficiency of CSLR. Therefore, the performance of CSLR needs further improvement. The highlights include: (1) to overcome these challenges, this paper proposes a novel video-based CSLR framework. This framework consists of three components: an OpenPose-based skeleton stream extraction module, a RGB stream extraction module, and a combination module of the BiLSTM network and the conditional hidden Markov model (CHMM) for CSLR. (2) A new residual network with Squeeze-and-Excitation blocks (SEResNet50) for video sequence feature extraction. (3) This paper combines the SEResNet50 module with the BiLSTM network to extract the feature information from video streams with different modalities. To evaluate the effectiveness of our proposed framework, experiments are conducted on two CSL datasets. The experimental results indicate that our method is superior to the methods in the literature.

Accurate identification of vehicles and estimating density in traffic surveillance systems is a challenging task, particularly in scenarios with closely spaced lanes. Single Shot MultiBox Detector (SSD) is introduced in vehicle detection and classification due to its speed and accuracy. It utilizes a transfer learning technique that enables them to utilize features from pretrained Convolutional Neural Networks (CNNs). Although the utilization of multi-scale feature maps in SSD has achieved efficient results in vehicle detection, it struggles to identify key features of vehicles due to its one-stage detection approach. Furthermore, the use of VGG16 as the backbone network in these approaches leads to the loss of fine-grained details, posing challenges in accurately localizing and classifying small vehicles. Also, there is no interaction between high- and low-level features, which restricts the networks ability to effectively integrate and utilize both features for accurate vehicle detection. To overcome these limitations, an improved SSD approach is introduced in this paper, leveraging interactive multi-scale attention characteristics to accurately detect and classify vehicles. This approach utilizes ResNet50 as the network backbone to overcome the limitations of traditional SSDs in detecting small vehicles. Also, an attention block is incorporated into it to focus on key details and assign higher attention to relevant pixels within the feature map. Also, the network employs a parallel detection framework and shares multi-scale layers (both high and low), enabling efficient detection of vehicles with various sizes. Then, traffic density is estimated based on the weights assigned to the categorized vehicles obtained from the improved SSD and the recorded area. Finally, traffic is classified as high, low, or moderate by comparing the estimated density to a threshold value. By adding attention characteristics of different scales to the original detection branch and replacing the VGG16 with ResNet50 of the SSD technique using our method, the feature representation capability and detection accuracy are both significantly improved.

Purpose: During the current pandemic scientists, researchers, and health professionals across the globe are in search of new technological methods for tackling COVID-19. The magnificent performance reported by machine learning and deep learning methods in the previous epidemic has encouraged researchers to develop systems with these methods to diagnose COVID-19.

Methods: In this paper, an ensemble-based multi-level voting model is proposed to diagnose COVID-19 from chest x-rays. The multi-level voting model proposed in this paper is built using four machine learning algorithms namely Random Forest (RF), Logistic Regression (LR), Support Vector Machine (SVM) with a linear kernel, and K-Nearest Neighbor (KNN). These algorithms are trained with features extracted using the ResNet50 deep learning model before merging them to form the voting model. In this work, voting is performed at two levels, at level 1 these four algorithms are grouped into 2 sets consisting of two algorithms each (set 1 — SVM with linear kernel and LR and set 2 — RF and KNN) and intra set hard voting is performed. At level 2 these two sets are merged using hard voting to form the proposed model.

Results: The proposed multilevel voting model outperformed all the machine learning algorithms, pre-trained models, and other proposed works with an accuracy of 100% and specificity of 100%.

Conclusion: The proposed model helps for the faster diagnosis of COVID-19 across the globe.

Categorizing flowers is quite a challenging task as there is so much diversity in the species, and the images of the different flower species could be pretty similar. Flower categorization involves many issues like low resolution and noisy images, occluded images with the leaves and the stems of the plants and sometimes even with the insects. The traditional handcrafted features were used for extraction of the features and the machine learning algorithms were applied but with the advent of the deep neural networks. The focus of the researchers has inclined towards the use of the non-handcrafted features for the image categorization tasks because of their fast computation and efficiency. In this study, the images are pre-processed to enhance the key features and suppress the undesired information’s and the objects are localized in the image through the segmentation to extract the Region of Interest, detect the objects and perform feature extraction and the supervised classification of flowers into five categories: daisy, sunflower, dandelion, tulip and rose. First step involves the pre-processing of the images and the second step involves the feature extraction using the pre-trained models ResNet50, MobileNet, DenseNet169, InceptionV3 and VGG16 and finally the classification is done into five different categories of flowers. Ultimately, the results obtained from these proposed architectures are then analyzed and presented in the form of confusion matrices. In this study, the CNN model has been proposed to evaluate the performance of categorization of flower images, and then data augmentation is applied to the images to address the problem of overfitting. The pre-trained models ResNet50, MobileNet, DenseNet169, InceptionV3 and VGG16 are implemented on the flower dataset to perform categorization tasks. The pre-trained models are empirically implemented and assessed on the various flower datasets. Performance analysis has been done in terms of the training, validation accuracy, validation loss and training loss. The empirical assessment of these pre-trained models demonstrate that these models are quite effective for the categorization tasks. According to the performance analysis, the VGG16 outperforms all the other models and provides a training accuracy of 99.01%. Densenet169 and MobileNet also give comparable validation accuracy. ResNet50 gives the lowest training accuracy of 60.46% as compared with the rest of the pre-trained replica or models.