Mobile users are increasing exponentially to adopt ubiquitous services offered by various sectors. This has attracted attention for a secure communication framework to access e-health data on mobile devices. The wearable sensor device is attached to the patient’s body which monitors the blood pressure, body temperature, serum cholesterol, glucose level, etc. In the proposed secure framework, first, the task starts with the patient authentication, after that the sensors device linked to the patient is activated and the sensor values of the patient are transmitted to the cloud server. The patient’s biometrics information has been added as a parameter in addition to the user name and password. The authentication scheme is coined with the SHA-512 algorithm that ensures integrity. To securely send the sensor information, the method follows two kinds of encryption: Substitution-Ceaser cipher and improved Elliptical Curve Cryptography (IECC). Whereas in improved ECC, an additional key (secret key) is generated to enhance the system’s security. In this way, the intricacy of the two phases is augmented. The computational cost of the scheme in the proposed framework is 4H + Ec + Dc which is less than the existing schemes. The average correlation coefficient value is about 0.045 which is close to zero shows the strength of the algorithm. The obtained encryption and decryption time are 1.032 μs and 1.004 μs respectively. The overall performance is analyzed by comparing the proposed improved ECC with existing Rivest–Shamir–Adleman (RSA)and ECC algorithms.

In order for a country’s economy to grow, agricultural development is essential. Plant diseases, however, severely hamper crop growth rate and quality. In the absence of domain experts and with low contrast information, accurate identification of these diseases is very challenging and time-consuming. This leads to an agricultural management system in need of a method for automatically detecting disease at an early stage. As a consequence of dimensionality reduction, CNN-based models use pooling layers, which results in the loss of vital information, including the precise location of the most prominent features. In response to these challenges, we propose a fine-tuned technique, GreenViT, for detecting plant infections and diseases based on Vision Transformers (ViTs). Similar to word embedding, we divide the input image into smaller blocks or patches and feed these to the ViT sequentially. Our approach leverages the strengths of ViTs in order to overcome the problems associated with CNN-based models. Experiments on widely used benchmark datasets were conducted to evaluate the proposed GreenViT performance. Based on the obtained experimental outcomes, the proposed technique outperforms state-of-the-art (SOTA) CNN models for detecting plant diseases.

Opinion mining has significantly supported knowledge and decision-making. This research analysed the content of online reviews including the text of reviews and their rankings. The restaurant reviews of Yelp website have been analysed into two sentiment classifications, binary classification (positive and negative) and ternary classification (positive, negative, and neutral). Three different types of predictive models have been applied including: machine learning, deep learning and transfer learning models. In addition, we propose a new unsupervised approach to apply for aspect-level sentiment classification based on semantic similarity, which allows our framework to leverage the powerful capacity of pre-trained language models like GloVe and eliminated many of the complications associated with the supervised learning models. Food, service, ambience, and price are the aspects that have been categorized according to their sentiment context. In conclusion, 98.30% of the maximum accuracy obtained using ALBERT model. The proposed aspect extraction method achieved an accuracy of 83.04%.

The lumbar spine plays a very important role in our load transfer and mobility. Vertebrae localization and segmentation are useful in detecting spinal deformities and fractures. Understanding of automated medical imagery is of main importance to help doctors in handling the time-consuming manual or semi-manual diagnosis. Our paper presents the methods that will help clinicians to grade the severity of the disease with confidence, as the current manual diagnosis by different doctors has dissimilarity and variations in the analysis of diseases. In this paper we discuss the lumbar spine localization and segmentation which help for the analysis of lumbar spine deformities. The lumber spine is localized using YOLOv5 which is the fifth variant of the YOLO family. It is the fastest and the lightest object detector. Mean average precision (mAP) of 0.975 is achieved by YOLOv5. To diagnose the lumbar lordosis, we correlated the angles with region area that is computed from the YOLOv5 centroids and obtained 74.5% accuracy. Cropped images from YOLOv5 bounding boxes are passed through HED U-Net, which is a combination of segmentation and edge detection frameworks, to obtain the segmented vertebrae and its edges. Lumbar lordortic angles (LLAs) and lumbosacral angles (LSAs) are found after detecting the corners of vertebrae using a Harris corner detector with very small mean errors of 0.29° and 0.38°, respectively. This paper compares the different object detectors used to localize the vertebrae, the results of two methods used to diagnose the lumbar deformity, and the results with other researchers.

Recently, social media platforms have been widely used as a communication tool on social networks. Many users have utilized these platforms to reflect their personal lives. These users differ in terms of background, language, age, and educational level. The close relationship between these platforms and their users has created rich information that is related to these users and can be exploited by researchers. Their posts can be analysed using natural language processing (NLP) to predict psychological traits such as depression. However, to the best of our knowledge, no study has utilized social media to predict mental health disorders in Arabic posts, especially depression. Therefore, in this study, we investigate the application of natural language processing and machine learning on Arabic text for the prediction of depression, and we evaluate and compare the performance. Our research method is based on the collection of Arabic text from online forums and the application of either a lexicon-based approach or a machine-learning-based approach. In the former approach, the ArabDep lexicon is created, and a rule-based algorithm is used to predict depression symptoms using the created lexicon; however, in the latter approach, the data are annotated with the help of a psychologist, text features are extracted from Arabic posts, and machine learning algorithms are ultimately applied to predict depression symptoms. We demonstrate that our applied approaches exhibit promising performance in predicting whether a post corresponds to depression symptoms, with an accuracy of more than 80%, a recall of 82% and a precision of 79%.

Recent advancements in transformers exploited computer vision problems which results in state-of-the-art models. Transformer-based models in various sequence prediction tasks such as language translation, sentiment classification, and caption generation have shown remarkable performance. Auto report generation scenarios in medical imaging through caption generation models is one of the applied scenarios for language models and have strong social impact. In these models, convolution neural networks have been used as encoder to gain spatial information and recurrent neural networks are used as decoder to generate caption or medical report. However, using transformer architecture as encoder and decoder in caption or report writing task is still unexplored. In this research, we explored the effect of losing spatial biasness information in encoder by using pre-trained vanilla image transformer architecture and combine it with different pre-trained language transformers as decoder. In order to evaluate the proposed methodology, the Indiana University Chest X-Rays dataset is used where ablation study is also conducted with respect to different evaluations. The comparative analysis shows that the proposed methodology has represented remarkable performance when compared with existing techniques in terms of different performance parameters.