Toward a Vision-Based Intelligent System: A Stacked Encoded Deep Learning Framework for Sign Language Recognition.

Sign language recognition, an essential interface between the hearing and deaf-mute communities, faces challenges with high false positive rates and computational costs, even with the use of advanced deep learning techniques. Our proposed solution is a stacked encoded model, combining artificial intelligence (AI) with the Internet of Things (IoT), which refines feature extraction and classification to overcome these challenges. We leverage a lightweight backbone model for preliminary feature extraction and use stacked autoencoders to further refine these features. Our approach harnesses the scalability of big data, showing notable improvement in accuracy, precision, recall, F1-score, and complexity analysis. Our model's effectiveness is demonstrated through testing on the ArSL2018 benchmark dataset, showcasing superior performance compared to state-of-the-art approaches. Additional validation through an ablation study with pre-trained convolutional neural network (CNN) models affirms our model's efficacy across all evaluation metrics. Our work paves the way for the sustainable development of high-performing, IoT-based sign-language-recognition applications.

An Efficient Pest Detection Framework with a Medium-Scale Benchmark to Increase the Agricultural Productivity.

Insect pests and crop diseases are considered the major problems for agricultural production, due to the severity and extent of their occurrence causing significant crop losses. To increase agricultural production, it is significant to protect the crop from harmful pests which is possible via soft computing techniques. The soft computing techniques are based on traditional machine and deep learning-based approaches. However, in the traditional methods, the selection of manual feature extraction mechanisms is ineffective, inefficient, and time-consuming, while deep learning techniques are computationally expensive and require a large amount of training data. In this paper, we propose an efficient pest detection method that accurately localized the pests and classify them according to their desired class label. In the proposed work, we modify the YOLOv5s model in several ways such as extending the cross stage partial network (CSP) module, improving the select kernel (SK) in the attention module, and modifying the multiscale feature extraction mechanism, which plays a significant role in the detection and classification of small and large sizes of pest in an image. To validate the model performance, we develop a medium-scale pest detection dataset that includes the five most harmful pests for agriculture products that are ants, grasshopper, palm weevils, shield bugs, and wasps. To check the model's effectiveness, we compare the results of the proposed model with several variations of the YOLOv5 model, where the proposed model achieved the best results in the experiments. Thus, the proposed model has the potential to be applied in real-world applications and further motivate research on pest detection to increase agriculture production.

An Effective Skin Cancer Classification Mechanism via Medical Vision Transformer.

Skin Cancer (SC) is considered the deadliest disease in the world, killing thousands of people every year. Early SC detection can increase the survival rate for patients up to 70%, hence it is highly recommended that regular head-to-toe skin examinations are conducted to determine whether there are any signs or symptoms of SC. The use of Machine Learning (ML)-based methods is having a significant impact on the classification and detection of SC diseases. However, there are certain challenges associated with the accurate classification of these diseases such as a lower detection accuracy, poor generalization of the models, and an insufficient amount of labeled data for training. To address these challenges, in this work we developed a two-tier framework for the accurate classification of SC. During the first stage of the framework, we applied different methods for data augmentation to increase the number of image samples for effective training. As part of the second tier of the framework, taking into consideration the promising performance of the Medical Vision Transformer (MVT) in the analysis of medical images, we developed an MVT-based classification model for SC. This MVT splits the input image into image patches and then feeds these patches to the transformer in a sequence structure, like word embedding. Finally, Multi-Layer Perceptron (MLP) is used to classify the input image into the corresponding class. Based on the experimental results achieved on the Human Against Machine (HAM10000) datasets, we concluded that the proposed MVT-based model achieves better results than current state-of-the-art techniques for SC classification.

An Efficient and Effective Deep Learning-Based Model for Real-Time Face Mask Detection.

Since December 2019, the COVID-19 pandemic has led to a dramatic loss of human lives and caused severe economic crises worldwide. COVID-19 virus transmission generally occurs through a small respiratory droplet ejected from the mouth or nose of an infected person to another person. To reduce and prevent the spread of COVID-19 transmission, the World Health Organization (WHO) advises the public to wear face masks as one of the most practical and effective prevention methods. Early face mask detection is very important to prevent the spread of COVID-19. For this purpose, we investigate several deep learning-based architectures such as VGG16, VGG19, InceptionV3, ResNet-101, ResNet-50, EfficientNet, MobileNetV1, and MobileNetV2. After these experiments, we propose an efficient and effective model for face mask detection with the potential to be deployable over edge devices. Our proposed model is based on MobileNetV2 architecture that extracts salient features from the input data that are then passed to an autoencoder to form more abstract representations prior to the classification layer. The proposed model also adopts extensive data augmentation techniques (e.g., rotation, flip, Gaussian blur, sharping, emboss, skew, and shear) to increase the number of samples for effective training. The performance of our proposed model is evaluated on three publicly available datasets and achieved the highest performance as compared to other state-of-the-art models.