The integration of AI, IoT, and edge–cloud computing is accelerating smart industrial system improvements, particularly in healthcare and finance. This paper presents TrustFed, a secure and privacy-preserving federated AI platform, to address IIoT data privacy, security, and scalability issues. TrustFed uses Intel SGX–based trusted execution, Federated Deep Learning (FDL), Differential Privacy (DP), PCA-driven feature reduction, and encryption-based secure aggregation for decentralised model training confidentiality and robustness. Two privacy-aware face recognition and brain tumour classification use cases verify the system, showing better accuracy, reduced communication overhead, and robustness to inference and poisoning assaults. TrustFed improves data privacy and performance, adding scientific value to secure AI adoption in large-scale smart industrial environments.

Reducing the influence of significant noise signal components on the obtained raw ECG signal is essential for precise identification of cardiac arrhythmias (CA), which frequently present as irregularities in heart rate or rhythm. Preprocessing is used to remove noise signals and baseline drift from the ECG wave that is recorded using the internet of things (IoT). After that, the denoised signal is subjected to dimensionality reduction and feature extraction. In order to determine whether classification method is more effective in detecting cardiac arrhythmias, this study compares two methods: an adaptive neuro-fuzzy inference system and artificial feed-forward neural networks trained with the back-propagation learning algorithm. An Adaptive Neuro Fuzzy Inference System analyses ICA features obtained by non-parametric power spectral estimates, and an Artificial Neural Network (ANN) classifier uses the ECG signal's morphological and statistical aspects to identify patterns. The creation of artificial feed-forward neural networks provides a rich framework for studying the Back Propagation Algorithm. Sensitivity, specificity, accuracy, and positive predictiveivity are some of the performance characteristics that are thoroughly examined. An overall accuracy of 97.79%, sensitivity of 99.82%, specificity of 99.68%, and positive predictivity of 98.58% were seen in the results of the Artificial Neural Feed Forward Network (ANFFN). The Adaptive Neuro Fuzzy Inference System (ANFIS) outperforms these metrics with an astounding overall accuracy of 99.62%, specificity of 98.63%, and positive predictivity of 99.46%. With a classification accuracy of 99.82%, ANFIS demonstrates to be the most effective classifier for identifying cardiac arrhythmias.

Bipolar disorder is quite a challenging mental illness which encounters substantial degree of challenges in confirmed diagnosis irrespective of modernized increasing pace of development in medical science. With the evolving standards of automation in healthcare section integrated with advanced technology, it is imperative to anticipate a reliable on-line diagnosis of mental illness for a given scenario of internet of things (IoT). Review of existing methodologies showcases a wide gap between enormous research work towards identification of bipolar disorder and only few studies towards on-line diagnosis considering patients residing in smart city. Therefore, the proposed scheme introduces a novel computational framework of an underlying architecture of an IoT that not only facilities an effective and simplified transmission of multimodal data autonomously from the patient forwarded to clinical analytical unit but also perform a multitier classification using deep neural network. The study outcome exhibits proposed scheme to offer better data transmission with higher accuracy performance in contrast to existing prevalent schemes.

American scientific publishing group

Content management systems and digital content management systems such as CMS and DCMS are used to maintain an organization’s database. Overall content maintenance is managed throughout the data lifecycle. The process of creating, storing, updating, publishing, maintaining and disposing of content is managed by DCMS software. Data can be classified as static data and dynamic data. Static data does not change. Dynamic data changes frequently. not always. An organization can contain static and dynamic content. Examples of static content are pdf files, text documents, excel sheets, etc. An example of dynamic content is a web page. However, protecting and preventing storage systems from computer crimes is one of the primary concerns of organizations. No one except the employees of the organization can access the warehouse. Cache content should prevent hardening of single-user security. Blockchain technology is growing rapidly in many industries such as software industry, medical industry and education. The purpose of the the research work is to propose how blockchain technology can be used in CMS to prevent data breach crimes. A multi-level security model is proposed where the first level of security is provided by cryptography and the second level is provided by blockchain. Storing content on the blockchain offers the highest security and once the content is stored on the blockchain, it cannot be changed. An editing system is essential software that stores all of an organization’s content and maintains it over the years. Since the application of blockchain technology is limited to static content, the research work suggests how to apply blockchain technology to store an organization’s static content in a CMS. This is to increase the security of the fixed content store. Blockchain can be used for static content in CMS storage systems to prevent unauthorized users from accessing data changes. Therefore, the goal is to prevent digital data from being stored in the CMS. Accurate data cannot be stored on the blockchain because storing a large amount of data requires a large investment. Therefore, only the unique identifier of the file is stored in the blockchain. The scheme uses the Ethereum blockchain to generate a unique identifier for each file and uses the Interplanetary File System (IPFS) to back up content files. This method provides the highest security for storing static content in your CMS, as only unique file IDs are stored on the blockchain. Therefore, theft and falsification of information can be prevented.