۱.
Early cancer detection is crucial for improving patient survival rates, as timely intervention greatly enhances treatment efficacy. One promising method for early detection is identifying cancerous cells through the detection of protein-level modifications, which serve as early indicators of malignancy. These protein modifications often result from complex biochemical processes that occurs before visible cellular abnormalities, making them critical targets for diagnostic technologies. In recent years, wireless biomedical sensors have advanced significantly, enabling precisely detecting these protein-level changes. These sensors have the potential to detect cancer at its earliest stages by monitoring the subtle alterations in protein structures and functions that distinguish healthy cells from cancerous ones. As the costs of genetic analysis continue to decrease, the development of Medical Internet of Things (MIoT) devices has become increasingly feasible. These devices are designed to perform real-time analyses of biological specimens—such as blood and urine—by detecting protein-level changes indicative of cancer. In this paper, a new machine learning method based on Extreme Randomized Trees (ERT) is developed to increase the speed of classification of cancerous cells based on single-cell Assay for Transposase-Accessible Chromatin using sequencing (ATAC-seq). The proposed method enhances the classification speed of the limited and noisy ATAC-seq data as it requires less computation to determine the best splits at each node of the decision trees. This method can significantly improve near real-time cancer risk assessment using samples collected by MIoT. Our proposed method achieves classification accuracy comparable to state of the art single-cell ATAC-seq data analysis techniques while reducing processing time by 259%, challenged by various low-data scenarios. This approach presents an efficient solution for rapid cancer monitoring within the MIoT framework.
۲.
Multilevel thresholding is recognized as a fast and effective technique for image segmentation. Although exhaustive search provides a comprehensive solution, its computational complexity increases with the number of threshold levels. This paper introduces a novel meta-heuristic search algorithm called Ensemble Searching (ES), designed to tackle complex nonlinear optimization problems. The focus is on applying ES to image multilevel thresholding. Initially, the population is divided into predefined groups, each guided by an evolutionary algorithm that independently searches for better positions within the search space. If an algorithm encounters a local optimum, a diversity-maintaining mechanism is activated to relocate the group. Throughout the iterative process, all algorithms share the best global solution (Gbest). The proposed structure’s effectiveness is evaluated using ten test images and the energy curve method. Kapur’s entropy, a well-established measure, is used to assess the algorithm’s performance. A comparative analysis with eight different search algorithms demonstrates the proposed framework’s rapid convergence, confirming its efficiency and effectiveness.
۳.
Today, the Internet of Things is a widely recognized phenomenon that generates a significant amount of data and connects many devices. Many products are incorporating electronic components to facilitate their integration and interaction with the Internet. Scalable and efficient trust management systems are required to maintain network reliability, considering the increasing number of IoT devices and generated data. In order to enable scalable trust management in social IoT, this paper presents a sharding-based scalable trust management approach that combines social interactions with smart contract functionality. Through the division of transaction state into smaller segments and the enhancement of trust value propagation among connected devices, sharding techniques in blockchain can offer scalable trust management protocols. When implementing the model on the Hyperledger Fabric platform, we carried out a thorough evaluation. The model calculates trust in terms of trust convergence and success rate efficiently. We have conducted several tests to evaluate the scalability of the model. To boost it, we have also implemented the state sharding. We also conducted a study to highlight the advantages of the sharding strategy on the scalability of the model. The results demonstrate that using shards significantly improves trust management capacity on the blockchain. The proposed method demonstrates the potential application of sharding in blockchain-based Trust Management (TM) for scalable trust management in SIoT.
۴.
This paper explores the usability of Augmented Reality (AR) applications specifically designed for visually impaired individuals, focusing on how these technologies can enhance their accessibility and daily living. AR offers potential benefits in areas such as navigation, object recognition, environmental awareness, education, social interaction, and entertainment. However, visually impaired users face significant challenges, including complex interfaces, reliance on visual cues, and limited access to assistive technologies. This paper identifies key usability guidelines to address these challenges, such as ensuring compatibility with assistive technologies like screen readers, maintaining consistency in design, providing clear and accessible user interfaces, and integrating alternative sensory cues like audio and haptic feedback. Furthermore, customization options, collision detection, contextual information, and user-centered design principles are emphasized to enhance the AR experience. The study concludes that incorporating these usability guidelines is crucial for creating AR applications that are intuitive, effective, and tailored to the unique needs of visually impaired users. Continuous user testing and feedback are also vital to further refine these technologies and ensure their accessibility.
۵.
The Internet of Things (IoT) is a transformative technology that enhances various aspects of human life, significantly impacting fields such as healthcare, industry, transportation, agriculture, education, and commercial applications. In particular, IoT's role in smart healthcare systems has attracted considerable research attention due to its potential to improve patient monitoring, optimize treatments, and reduce costs. Therefore, a systematic assessment of the scientific output in this domain is essential for understanding current trends and future directions. Bibliometric approaches can describe, explain, and predict the scientific contributions of researchers, institutions, journals, and countries on an international scale while identifying emerging research areas. This analysis quantifies scientific output and evaluates its impact through concepts such as co-occurrence networks, collaboration networks, and co-citation networks, revealing trends within specific fields. Given the increasing significance of IoT in healthcare, this study examines trends in IoT applications in medicine using a bibliometric approach. The research analyzes 7,205 articles indexed in the Web of Science (WoS) database, covering the period from 2013 to August 2024. Data visualization was conducted using VOSviewer software. The findings indicate a likely future focus on integrating automated disease detection methods with IoT technologies. China, India, and the United States lead in scientific output, with Asian countries demonstrating a strong interest in healthcare applications. Additionally, security and privacy concerns remain significant challenges in the field.
۶.
Cancer is a complex and dangerous disease in which cells uncontrollably begin to grow. Some cells, with mutated genes, cause abnormalities in the cell. These abnormalities are transferred to other genes through specific interactions between genes, leading to disruptions in the normal function of cells. The result of these cell abnormalities will be the occurrence of cancer. In cancer, modules are considered as clusters of genes and regulatory molecules that play a role in the processes of cancer initiation and progression. These modules usually have a specific gene sequence as a central unit that is important in controlling and regulating cellular processes related to cancer.In this study, a novel network-based method called mdGRN is proposed for identifying modules effective in lung cancer occurrence in the gene regulatory network. In this method, first, using gene expression data and regulatory interactions, a lung cancer regulatory network is constructed. Then, using a greedy modularity optimization approach, communities related to lung cancer are identified. Subsequently, the obtained communities are ranked using influence diffusion metrics in the network. Finally, the top-ranked communities are introduced as effective modules.To assess the efficacy of the proposed method, the standard Cancer Genome Atlas (TCGA) database and four classifiers including a decision tree, k-nearest neighbors, support vector machine, and random forest were utilized. The results obtained demonstrated that the proposed mdGRN method outperforms other methods in identifying cancer modules in terms of the average harmonic mean metric with the support vector machine classifier. Additionally, in terms of the AUC metric, the proposed method achieved a value of 0.997 using the random forest classifier, indicating better performance compared to other previous methods in identifying cancer modules. Furthermore, the number of genes identified by the top module is compared with other previous computational and network methods. The results show that the top-ranked module, besides containing a considerable number of driver genes, contains unique genes that have not been identified by other methods.
