Search

As the demand for edge computing applications continues to rise, the need for efficient training of resource-constrained devices becomes paramount. This letter proposes message queuing telemetry transport (MQTT)-based implementation of distributed estimation strategies in the context of the Internet of Things (IoT), namely incremental, consensus, and diffusion strategies. The use of Raspberry Pi Pico W in the emulation environment is motivated by its advanced capability, while the MQTT data protocol is employed to address the constraints associated with conventional HTTP/HTTPs protocols. Synchronization in an IoT network is achieved by the integration of a novel methodology that entails the use of the wait-for-slowest (WFS) protocol and the MQTT protocol. Furthermore, the development of a graphical user interface supported by the Django application allows for adjusting parameters in distributed strategies through the HTTP REST API, along with SQLite. The results acquired from hardware experiments exhibit a strong correlation between the mean-square performance achieved from simulation studies. The distributed estimation strategy is compared with state-of-the art centralized and noncooperation estimation strategies, demonstrating its superior performance. In addition, a study is conducted on the resilience of these IoT networks in the face of several network threats, such as node failure and model poisoning attacks. A theoretical analysis is provided to explain the relationship between the number of iterations and node failure. [ABSTRACT FROM AUTHOR]

Neural network (NN), also known as artificial neural network (ANN), provides efficient results in every computation, whether it is pattern recognition, forecasting, customer research, data validation, risk management, data mining, etc. In each computation, NN requires a specific dataset, and according to the datasets, a new NN structure is used to compute the results. Thus, these NN structures mostly depend upon the type of datasets. The current study presents a method that comprises a dedicated architecture known as neuromorphic neural network (NNN), which is made up of optical waveguides that enable high communication and data processing speed at the same time. We have also proposed three algorithms for configuring and building distinct ANN structures from the same architecture. These dedicated structures are not dependent on the datasets and employ the necessary processing element (PE) nodes to function as neurons in the hidden layer. Because specialized resources will be employed to perform operations in the hidden layer, these designs may produce more efficient outcomes than the present logical NN. Furthermore, we assessed our proposed architecture in terms of communication latency, deadlock prevention, energy consumption, and power usage. The simulation results show that deadlocks are avoided to the greatest extent possible, power consumption is reduced by up to 95%, and communicational latency is accomplished in the order of femtoseconds while conversing among PE nodes. The proposed architecture and simulation results promise an alternative for logical NN as well as improved results in terms of speed and efficiency. [ABSTRACT FROM AUTHOR]

The design and development of a rear-mounted power assist system specifically made for manual wheelchairs are the main objectives of this project. This invention's main goal is to reduce physical strain on people who have restricted upper body strength or movement, improving their independent mobility and general quality of life. The power assist wheels are designed to make maneuvering through difficult environments such as inclines and uneven surfaces easier. These types of terrain provide challenges for traditional manual wheelchairs. The goal of using this technology is to provide a solution that enhances the mobility of the disabled while simultaneously fostering exclusivity and accessibility, which benefits society as a whole.

Aquaculture, a rapidly expanding sector, meets the global surging demand for aquatic food. Pangasius, a highly valued freshwater species, has seen a significant increase in demand due to its adaptability and potential for high yields, making it a promising candidate for aquaculture in India. This study investigates the gut microbiome composition of Pangasius pangasius fish cultured in three different systems (biofloc, cage, and pond). Metagenomic DNA extraction and 16S rRNA gene-targeted sequencing were performed. Outcomes revealed distinct microbial compositions across culture types, with significant differences in species richness and diversity, specifically in the biofloc system, compared to cages and ponds. Taxonomic analysis identified prevalent phyla such as Firmicutes and Fusobacteriota, with varying abundances among culture systems. The genus-level analysis highlighted dominant genera such as Cetobacterium and WWE3. Functional profiling indicated differences in enzymatic activity and metabolic pathways, emphasizing each culture sample type's unique microbial community structures. Notably, the microbiota from BF samples exhibited significant differences and unique metabolic pathways compared to the microbiota from C and P samples, which showed greater similarity and shared several common metabolic pathways. These findings highlight substantial differences in microbial diversity across the culturing systems, reflecting the microbiota's ability to adapt to specific environments and their potential role in promoting fish growth within those environments. Overall, this study provides insights into the gut microbiome diversity and functionality in Pangasius pangasius across different aquaculture environments, contributing to a better understanding of host-microbe interactions and aquaculture management strategies. [ABSTRACT FROM AUTHOR]