Ever since its emergence, the concept internet of things (IoT) has been applied in many fields. In the area of medical sciences, a new concept “Internet of Medical Things” (IoMT) has been explored. IoMT establishes a connection between humans & machines and serves both of them. It has been expected that, by 2025, services of IoMT would reach the entire world. IoMT has covered a wide scope pertaining to health but unfortunately been facing many security challenges. Healthcare systems consist of sensitive and significant data, which is unorganized and noisy and needs additional power to be calculated for effective analysis & workable results. This data is worked upon for the purpose of making critical decisions. Therefore, it has become the main target of Cyber Criminals. The need of robust security and privacy (S&P) is gradually increasing as more and more devices are getting connected to the IoMT. The S&P of the IoMT has now become a great challenge, considering the utmost significance and vulnerability of the data in the healthcare industry. Lack of sufficient S&P in IoMT devices keeps the patients’ privacy at high stake. This research is intended to propose a Security Model to cope with these Security threats, attacks, issues and challenges. The proposed model has been developed by thoroughly investigating all the major security models through a detailed systematic literature review. The SLR has been conducted to explore all the security threats, security attacks, security issues and security challenges. Extensive meta-analysis has been performed for each of the defined category in order to prioritize these risks. After analyzing these risks, a comprehensive security model has been proposed. The interface has been developed in Python which is well structured, user friendly and easy to implement. The developed module not only identify and prioritize the risks but also automatically control different level of threats. The developed system also contain user intimation modules in case of any threat. This research is based on a very flexible and comprehensive model, which would be highly beneficial to future researchers who desire to work on existing models for the improvement as well as to those who wish to create new security models for IoMT.

Pashto is the native language of Afghanistan and one of Pakistan’s most essential and regional languages. The Pashto language has a vast number of native speakers who live in various parts of the world. The handwritten Pashto textual trajectories are hard to recognize and detect due to the cursive style and handwriting variation. The transformation behaviour, i.e., scaling, rotation, and shifting of handwritten text, are the prominent but challenging factors. A lightweight deep learning-based model construction for low and medium-resource devices in a less-constrained environment is challenging. This paper provides a practical, light deep learning-based model for predicting handwritten Pashto words. A massive Pashto-transformed invariant inverted handwritten text dataset is prepared with the help of the Pashtun community. A lightweight MobileNetV2 has been highly tuned for Pashto handwritten text classification, extracting images’ features (MoI). We inverted the dataset to make the model more accurate and restrict it to fifteen epochs. Extensive experiments have been conducted to validate the suggested model’s performance. The proposed transformed invariant lightweight Pashto deep learning (TILPDeep) technique achieves a training accuracy of 0.9839 and a validation accuracy of 0.9405 for transformed invariant Pashto handwritten inverted text using recognition matrices.

Medical image segmentation has numerous applications in diagnosing different diseases. Various types of diseases are found in white blood and Red blood cells. This paper represents the segmentation of WBCs from blood smear images. It is a complex and challenging task due to the frequent overlapping and variants in size and shape of WBCs with each other and RBCs. This overlapping is due to the rough border of the immature cells. The paper describes a new approach to WBC segmentation using UNet++, the marker watershed algorithm, and Neural Ordinary Differential Equations (ODE). This technique uses UNet++ for pre-segmentation, followed by the marker watershed method, which has been integrated using ODE to deepen the segmentation process. This novel integration enhances clinical applications in automated blood cell analysis, diagnostic imaging, and disease monitoring, improving accuracy and robustness. The ODE is used after the convolution operation to reduce the error at each step, preventing the massive propagation of error in the forward and the backpropagation. The White blood cells are segmented from the input smear images using ALL_IDB1 and ALL_IDB2 datasets, which are further used in the experiment section. UNet ++ is used to generate the pre-segmented probabilistic grayscale images. Some white blood cells are connected and make groups appearing in the grayscale images. These groups of WBCs are separated using a technique called the marker watershed, which gives us the final segmented result. The experimentation results show that the mean intersection over union (Jaccard method), the Dice similarity coefficient, and the mean pixel accuracy are 97.73%, 98.36%, and 98.97%, respectively. The structure and size of the white blood cells vary from red blood cells and platelets, which makes this work different from others. Furthermore, the combination of UNet++, marker watershed, and Neural Ordinary Differential Equation makes the proposed system unique from existing systems. This work can be further investigated to reduce computational complexity and memory space for optimizing deployment on low-resource devices, such as smart healthcare systems. Techniques like model pruning, quantization, or learned information distillation might be explored to create a lightweight version of the model without much loss in accuracy. Such developments would make possible mass uses of automated white blood cell segmentation in portable, low-cost health devices for point-of-care remote diagnostics and monitoring.

Before the 19th century, all communication and official records relied on handwritten documents, cherished as valuable artefacts by different ethnic groups. While significant efforts have been made to automate the transcription of major languages like English, French, Arabic, and Chinese, there has been less research on regional and minor languages, despite their importance from geographical and historical perspectives. This research focuses on detecting and recognizing Pashto handwritten characters and ligatures, which is essential for preserving this regional cursive language in Pakistan and its status as the national language of Afghanistan. Deep learning techniques were employed to detect and recognize Pashto characters and ligatures, utilizing a newly developed dataset specific to Pashto. A further enhancement was done on the dataset by implementing data augmentation, i.e., scaling and rotation on Pashto handwritten characters and ligatures, which gave us many variations of a single trajectory. Different morphological operations for minimizing gaps in the trajectories were also performed. The median filter was used for the removal of different noises. This dataset will be combined with the existing PHWD-V2 dataset. Various deep-learning techniques were evaluated, including VGG19, MobileNetV2, MobileNetV3, and a customized CNN. The customized CNN demonstrated the highest accuracy and minimal loss, achieving a training accuracy of 93.98%, validation accuracy of 92.08% and testing accuracy of 92.99%.

The Internet and Big Data expansion have motivated the requirement for more generous stockpiling to hold and share information. Against the current era of information, guaranteeing protection and security to individuals sending data to each other is of utmost importance. The only file type that is instantly and widely used is the image. Therefore, to secure transmission, it is necessary to develop a mechanism to safeguard user data transmission. Considering this thought, it is necessary to analyze the best file type of image for essential criteria of image steganography, such as Payload, Robustness, Imperceptibility, etc., to challenge the weakness of the current algorithms. The widely used image formats are PNG, TIFF, JPEG, BMP, and GIF, which is the cause of existing methods. However, in this case, the critical softness is the credibility of the steganography, which plays a vital role in these format images to ensure the end users communicate. In this paper, a single algorithm provides several advantages for various types of images used as cover objects. However, after the critical and comparative analysis of different perspectives and some assessment metrics, the experimental results prove the importance, significance, and promising limits for these image formats by accomplishing a 4.4450% normal higher score for PSNR correlation than the next best existing methodology. Besides, in PSNR with a variable measure of code implanted in similar pictures of similar aspects, the proposed approach accomplished a 6.33% better score. Encrypting similar code sizes in pictures of various dimensions brought about a 4.23% better score. Embedding the same message size into the same dimension of different images resulted in a 3.222% better score.

The immediate transition to a fully Software-Defined Networking (SDN)-based architecture is both costly and operationally complex. As an alternative, a hybrid SDN architecture is introduced, where SDN-enabled devices are incrementally deployed alongside legacy network devices. This coexistence, however, presents significant challenges in network management and control, particularly in the efficient implementation of Access Control List (ACL) policies. ACL policies play a crucial role in defining network security and control mechanisms, yet existing approaches assume that all subnets affected by these policies are continuously transmitting data. Given the dynamic nature of subnet behavior, such static assumptions can lead to suboptimal network performance. To address this limitation, this paper proposes a novel Q-learning-based approach for dynamically deploying ACL policies based on real-time data transmission patterns of subnets. The proposed algorithm optimally determines the placement of ACL policies, minimizing both the total number of policies and redundant transmissions in the network. Extensive evaluations using real-world network traces and topologies demonstrate that our approach outperforms existing state-of-the-art methods in terms of efficiency and network performance.