Introduction: The future wireless sensor network (WSN) has to be able to autonomously handle a large number of IoT gadgets in actual time, in extremely dynamic circumstances and offer extremely reliable, minimal latency connectivity. In order for wireless sensor networks to behave intelligently and become adaptable to changes in a range of operating environments, artificial intelligence competency must be included. Numerous difficulties arise from the features of WSNs, including a huge number of detector nodes, dense dispersion, dynamic topological structure, storage capacity, and communication proficiency.

Methodology: The use of artificial network approaches to advance wireless sensor networks' adaptation and smart computation capabilities will increase those networks' functioning and persistence rate. In business applications including production automation and health services, wireless sensor networks are becoming increasingly important. In sensor networks, virtualization may offer scalability, economical solutions, and increased management. This article showcases a broad range of cutting-edge virtual sensor network projects. Through the proposed framework, which leverages tiered architecture and distributed agent systems to facilitate cognitive ability, it is feasible to contrive an outcome that allows a sensor network to function as an distributed agent system.

Results: The suggested model highlights how WSN functions and how to make it clever. In situations like smart home automation, medical monitoring, combat surveillance, rock falls, and animal crossings in hilly terrain, a virtual environment in sensor networks may be possible.

Conclusions: An architecture for a multi-source sensor network might be set up to make effective use of the physical organization of sensors. The virtual infrastructure of sensor networks may provide a new business model by enabling a variety of wireless sensor network topologies to coexist on the same hardware substrate. In order to do this, we are developing a virtual machine that will allow for the real virtual environment of WSNs.

Features Extraction (FE) plays a crucial role in image classification by reducing the dimensionality of the raw hyperspectral Remote Sensing (RS) data while retaining discriminative information. This technique helps to simplify complex hyperspectral data, which contain hundreds of spectral bands, to make them more manageable by identifying the most important information for classification. Reducing the number of dimensions, this helps to overcome the problem of the "curse of dimensionality", improves classification accuracy, and speeds up data processing. This study proposed an innovative approach to improve the accuracy of water body extraction from hyperspectral RS data by combining FE and Convolutional Extreme Learning Machine (CELM) with evolutionary algorithms. This method integrates several advanced techniques to optimize water surface extraction. FE allows us to select the most relevant information from hyperspectral data, reducing complexity while preserving essential details. The addition of evolutionary algorithms allows us to automatically optimize the model parameters, improving its performance. CELM is trained in a supervised manner directly on raw data to learn discriminative features for classification steps. Then, these extracted features are used for the final classification using the CELM with the hybridization of evolutionary algorithms (EAs) such as Genetic Algorithms (GAs). This hybrid approach aims to overcome the challenges related to the spectral variability of water bodies and the presence of mixed pixels, thus offering a more robust and accurate solution for water resource mapping from hyperspectral images. In order to validate the effectiveness of our approach, we conducted experiments on hyperspectral data acquired by the RISMA (PRecursore IperSpettrale della Missione Applicativa) satellite. The obtained results were then compared with the existing methods documented in the scientific literature using recognized evaluation metrics such as precision, accuracy, recall, Intersection Over Union (IOU), and F1 score.

Facial expression recognition for identifying customer satisfaction with products is one of the most powerful and challenging research tasks in social communication. AI-based emotion recognition harnesses the collective strength of machine learning, deep learning, and computer vision to decipher the subtleties of human emotions. By intricately analyzing facial expression, including the nuanced movements of the mouth, eyes, and eyebrows. Recent innovations have driven notable progress in face detection and recognition, which enhance performance and reliability. This study focuses on leveraging AI-based facial expression recognition to identify customer satisfaction with products. The objective of this research is to develop a robust and accurate facial expression recognition system capable of analyzing customer emotions and determining their satisfaction levels based on their facial expressions. The proposed study used a hybrid CNN-GRU deep learning model to extract meaningful features from facial images and classify them into different emotional states. The trained model is evaluated using a separate test dataset to measure its performance in accurately recognizing customer emotions and assessing satisfaction levels. The evaluation metrics include accuracy, precision, recall, and F1-score. Experimental results demonstrate the effectiveness of the proposed AI-based facial expression recognition system in identifying customer satisfaction with products. The proposed experiment achieved excellent results with a real-time image-based dataset.

Accurate and efficient prediction of house prices is a critical challenge in the real estate market. This research aims to develop a robust machine learning model capable of estimating property values. By systematically analyzing key determinants of house prices, including location, square footage, and number of bedrooms, this study seeks to contribute to the advancement of property valuation methodologies. Our research investigated the complex interplay between house features and their corresponding prices. The study involved the meticulous examination of a comprehensive dataset, allowing for a thorough understanding of market trends and patterns. Various machine learning algorithms were rigorously tested and compared to identify the most effective model for predicting house prices. The findings of this research demonstrated that linear regression emerges as the superior algorithm for estimating property values within the given dataset. Furthermore, the study highlights the significant influence of specific features, such as bathroom and bedroom numbers, on predicted prices. These insights underscore the importance of considering a holistic range of factors when evaluating property values. The developed model holds the potential to revolutionize the real estate industry by providing stakeholders with a reliable tool for informed decision-making. By accurately predicting house prices, this research contributes to enhancing market efficiency, optimizing investment strategies, and supporting equitable property valuations.

Corrugated board is widely used as an eco-friendly and robust material in the packaging sector. Ensuring the proper mechanical properties of such composite materials is crucial. Therefore, designing packaging made of corrugated board often involves various numerical techniques to analyze the mechanical behavior of the structure under specified loads. To expedite the process of creating digital models of corrugated board, this study introduces an algorithm that leverages image processing techniques.

The proposed algorithm consists of two stages. The first stage utilizes basic image processing methods to extract geometrical parameters of the corrugated board, including layer and overall board thickness, as well as flute height. It also determines the locations of the center lines of each layer. In the second stage, it is assumed that the flutes can be modeled as a sinusoidal function. An objective function is defined based on the sum of the distances between the points of the potential sinusoidal function and the corresponding points on the binary image obtained in the first stage.

This study compares the effectiveness of four metaheuristics—genetic algorithms, particle swarm optimization, simulated annealing, and surrogate optimization—in refining the sinusoidal model of the flutes. The algorithm was successfully applied to three- and five-layered corrugated boards, demonstrating its capability to accurately model the geometric structure and support the design of packaging with optimized mechanical properties.

Abstract - This article is devoted to the identification of an arctangent hysteresis model, using the particle swarm optimization method. Results obtained from simulated and measured curves are compared and analyzed.

Introduction

Swarm intelligence-based algorithms are widely used to solve difficult optimization problems. Scientists and researchers are particularly interested in the PSO approach, as it needs few parameters, it is adapted to nonlinear functions, and it is easy to implement.

Describing mathematical hysteresis loops is one of the most challenging aspects of ferromagnetism. Mathematical models are characterized by their simplicity of implementation.

This paper suggests the use of PSO method in order to identify the parameters of the arctangent hysteresis model that will be presented in the coming section.

Methodology

For a given magnetic field H, the magnetic induction B in the arctangent model hysteresis curve is represented by the following equations.

For the upward curve:

B=arctan(b(H-d)cH (1)

For the downward curve:

B=arctan(b(H+d)cH (2)

Generally, the parameters a, b, c, and d are calculated from analytical expressions. The particle swarm optimization method is used to identify them too. This method is based on the definition of a search space, which includes a set number of particles and the function to be optimized. Each particle is identified by its present location, speed, and best position.

Results

It is obvious that the hysteresis curve generated by the PSO method leads to a better fit of the measured loop than the one obtained using the analytical approach. The convergence of the PSO method is very fast and can be reached in a few iterations.

Conclusion

From the obtained results, it is evident that the identification of the set of parameters (a, b, c, and d) using the PSO method gives a better approximation of the measured curve than those obtained when they are analytically identified.

An inventive use of technology in agriculture is an artificial intelligence-supported intuitive irrigation system that makes use of Arduino and Zigbee in a wireless sensor network. This system makes use of wireless connection, microcontrollers, sensors, and AI. An open-source microcontroller framework serves as the system's brain, gathering information from detectors and managing irrigation equipment. A variety of sensors are positioned across the field to measure various parameters, including relative humidity and air temperature. One of the most crucial issues that needs to be taken into consideration while creating wireless sensor networks is energy conservation. The goal of this research is to figure out how to automate irrigation. This system creates a smart and fully-automated watering arrangement. In order to establish the ideal watering needs of plants, this system first uses artificial intelligence to evaluate a range of environmental characteristics, including soil moisture, the temperature, and the weather. This makes it possible to precisely and strategically water plants, lowering the possibility of stress on plants and production losses brought on by either exceeding or under-watering. Second, using microcontrollers such as Arduino offers a flexible and robust environment for processing, controlling, and gathering data. Thirdly, the system's numerous components, such as detectors, Arduino circuits, and actuators, can communicate with one another more efficiently through the Zigbee wireless sensor network. Zigbee is perfect for large-scale installations because to its low power consumption and strong mesh networking capabilities, which makes it easier to create a decentralized and networked irrigation system.

The influence of the incorporation of oregano powder (1.5 and 3% of flour) on the chemical, microbiological and sensorial quality of bun-bread were investigated. Oregano powder, known for its antioxidant and antimicrobial properties, was added to bun-bread at varying concentrations to assess its effectiveness in enhancing bread quality. The chemical composition, microbiological, and sensory analysis of the supplemented bun-bread were measured. Sensory evaluation involved a panel of trained judges who assessed attributes such as flavor, texture, aroma, and overall acceptability. Results showed that the lowest amount of oregano powder (1.5%) revealed the best value of sensorial scores, in terms of its color and nature of crust, crumb color, texture, aroma, and taste. The results revealed that 1.5% of oregano powder can be involved in bun-bread preparation without modifying dough processing and bun-bread overall features, where this ratio approximates chemical compositions, microbiological stability, and shelf-life of bun-bread. Among the explored samples, bun-bread with 1.5% of oregano powder could be utilized industrially with acceptable properties and shelf-life stability. This study suggests that oregano powder is a valuable natural additive for improving the nutritional quality, safety, and sensory attributes of bun-bread, making it a viable option for consumers seeking functional and preservative-free baked goods. The findings highlight the potential of incorporating oregano powder in bread production to deliver health benefits and extend shelf life, aligning with growing consumer demands for healthier and more sustainable food options.

Introduction:Schizophrenia Spectrum Disorders are complex mental health conditions that significantly impact cognitive function and quality of life. While pharmacological and psychotherapeutic interventions are available, their effectiveness remains limited, particularly for negative symptoms and cognitive impairments. These limitations, alongside drug side effects and adherence difficulties, highlight the need for new treatments. Cognitive remediation strategies like EEG-biofeedback show promise by harnessing neuroplasticity. This systematic review aims to evaluate the neurocognitive and humoral changes induced by EEG-biofeedback and its therapeutic effects in patients with schizophrenia spectrum disorders.

Methods: Our review was conducted following PRISMA guidelines. Databases including EMBASE, ScienceDirect, Scopus, PsycINFO, and MEDLINE were searched for relevant studies: 15 studies, 10 RCTs and 5 Clinical trials were selected. Inclusion criteria encompassed studies involving patients with schizophrenia spectrum disorders, EEG-biofeedback interventions, and outcomes related to neurocognitive and humoral changes. The Cochrane Risk-of-Bias Tool for randomized trials (RoB 2) was used to assess the quality of included studies.

Results: The reviewed studies suggest that EEG-neurofeedback shows promise in addressing various aspects of schizophrenia spectrum disorders. Improvements were observed in processing speed, social functioning, working memory, and emotional regulation. Several studies reported successful modulation of brain activity in regions associated with auditory hallucinations. Neurofeedback training also led to increased functional connectivity between language networks and the default mode network. Some studies found improvements in brain-derived neurotrophic factor (BDNF) levels, self-efficacy, and clinical symptoms in schizophrenia patients.

Conclusions: Future research should focus on personalizing neurofeedback approaches and exploring their mechanisms of action in the context of schizophrenia pathophysiology.

Introduction

The identification of inflammatory and immunological diseases, which affect millions of people, requires accurate and early diagnosis to optimize treatment. However, these diagnoses often rely heavily on visual analysis by expert clinical pathologists, delaying timely intervention.

Neutrophils, the most important immune cells, are critical in defending against infections and regulating the inflammatory response. While conventional morphological analysis systems can identify normal neutrophils, they have difficulty detecting specific alterations, such as those seen in bacterial infections, severe inflammation, and autoimmune disorders. This limitation poses a significant challenge to timely and accurate diagnosis.

Objective

This work aims to develop an automated deep-learning-based system to differentiate normal neutrophils from those with abnormalities characteristic of various pathologies, including bacterial infections, severe inflammation, and autoimmune disorders.

Methodology

The images were obtained at the Core Laboratory of the Hospital Clínic de Barcelona using the Cellavision DM96 morphological analysis system. Pathologists validated 5,492 images: normal neutrophils (4,595), hypogranulated neutrophils (494), and neutrophils with inclusions (Döhle bodies: 139, cryoglobulins: 191, bacteria: 73).

To address imbalance, the Pareto rule was applied, starting with the smallest group (bacteria), generating 138 training images and oversampling to 276. This value balanced each neutrophil class in training and proportionally divided the dataset into training (828), validation (216), and test (4,622) sets. Data Augmentations (rotation, zoom, mirroring) were applied. Two ResNet152-based models A and B classify general categories and inclusions.

Results

The deep learning system showed high accuracy: 99% in Model A and 85% in Model B for classifying normal neutrophils and those with inclusions. It effectively identified normal, hypogranulated neutrophils, and those containing bacteria, cryoglobulins, and Döhle bodies, demonstrating its clinical value.

Conclusion

The proposed system effectively identifies normal neutrophils and those linked to bacterial infections, severe inflammation, and autoimmune disorders, showing potential for enhancing hematological disease diagnosis.