Innovative Monitoring Research Articles

Addressing Shortages with Storage: From Old Grain Pits to New Solutions for Underground Storage Systems

In every era, climate variability and frequent food shortages have made it necessary to store harvested grains for more than one season. Underground grain storage has been used since ancient times throughout the world. Italy (Cerignola) and Malta (Valletta and Floriana) have preserved rare examples of more recent (from the 16th century onward) large concentrations of grain pits, capable of accumulating substantial reserves to cope with famine or siege. No longer in operation, they represent an important part of the cultural heritage of the agricultural economy. The purpose of this narrative review was, after a geographical framing of grain pits in the Eurasian and African macro-areas, to take the Italian and Maltese grain pits as historical case studies to draw attention to the reevaluation of underground grain storage in the context of climate change and food insecurity. Today, as in the past, grain reserves play a significant role in food security in developing countries and, due to climate change and geopolitical events that can cause disruptions in grain supplies, are also increasingly important for developed countries. A comparison of traditional and modern underground storage systems reveals the great flexibility of this technology, ranging from basic pits of different sizes to large underground granaries equipped with a support structure. The advantages of underground storage, such as environmental sustainability due to thermal insulation of the soil and airtight conditions that make high energy inputs for grain cooling and pesticide use unnecessary, are still useful today, perhaps more so than in the past. Prospects for development include technical solutions involving the application of innovative information technology-based monitoring systems and the use of modern materials to ensure the performance of waterproofing, seepage control, and static safety, all tools for further evolution of this ancient storage system.

Immune responses in rodent whole eye transplantation: elucidation and preliminary investigations into rejection diagnosis and monitoring

BackgroundWhole Eye Transplantation (WET) offers potential for vision restoration but is hindered by the complex challenge of immune rejection. Understanding and closely monitoring these immunological responses is crucial for advancing WET. This study delves into the timeline and nature of immune responses in a rodent model of WET without immunosuppression, aiming to elucidate a detailed picture of the immune landscape post-transplantation and establish innovative diagnostic and monitoring methods.MethodsWe employed a multi-faceted approach to analyze immune responses post-WET, including assessments of gross changes in corneal transparency, thickness, and skin condition. Histopathological examinations of both ocular and surrounding skin tissues provided insights into cellular changes, complemented by ocular RT-qPCR for molecular analysis. Serological analysis was employed to quantify cytokines, chemokines, and donor-specific antibodies, aiming to identify potential biomarkers correlating with WET rejection and to validate the presence of antibody-mediated rejection. These methodologies collectively contribute to the development of non-invasive diagnostic and monitoring strategies for WET.ResultsOur study revealed a rapid and acute immune response following WET, characterized by an early innate immune response dominated by complement involvement, and infiltration of neutrophils and monocytes by post-operative day (POD) 2. This was succeeded by an acute T-cell-mediated immune reaction, predominantly involving T helper 1 (Th1) cells and cytotoxic T lymphocytes (CTLs). The presence of donor specific antibody (DSA) and indications of pyroptosis in the early phases of rejection were observed. Notably, the early elevation of serum CXCL10 by POD4, coupled with ocular CD3+ cell infiltration, emerged as a potential early biomarker for WET rejection. Additionally, corneal transparency grading proved effective as a non-invasive monitoring tool.ConclusionThis study offers a first-time comprehensive exploration of immune responses in WET, unveiling rapid and complex rejection mechanisms. The identification of early biomarkers and the development of non-invasive monitoring techniques significantly advance our understanding of WET rejection. Additionally, these findings establish an essential baseline for future research in this evolving field.

Autonomous, Multisensory Soil Monitoring System

The research investigates the advantages of real-time soil quality monitoring for various land management applications. We emphasize the crucial role of soil modeling and mapping by visualizing and understanding aridity trends across different regions. The primary objective is to develop an innovative soil monitoring system utilizing Internet of Things (IoT) technology. This system, equipped with intelligent sensors, will operate autonomously, collecting real-time data to identify key trends in soil conditions. Our system employs smart soil sensors to measure macronutrient values up to a depth of 80 cm. These sensors will transmit data wirelessly. Laboratory research involved a two-month evaluation of the system’s performance across three distinct soil types collected from diverse geographical locations. Analysis of the three soil types yielded a model accuracy estimate of 0.01. A strong positive linear correlation (0.92) between moisture and macronutrients has been observed in two out of the three soil types. The results, particularly related to soil moisture, were averaged over the testing period. While precipitation values were not directly integrated into the modeling framework, they were calculated in l/m2 to ensure accurate real-time estimates. The need for such advanced monitoring systems is critical for optimizing key soil macronutrients and enabling spatiotemporal mapping. This information is essential for developing effective strategies to mitigate soil aridification and prevent desertification.

Development and Application of an Innovative Planning and Monitoring Tool to Optimize Construction Projects

This research develops and applies a tool that allows the breakdown of time objectives to the same level of detail traditionally applied to cost, while also providing a favorable production scheme to ensure the project quality. This tool introduces an innovative approach to planning and execution monitoring through cascading dashboards, representing production packages and activities across designated project zones. This approach reinterprets the Last Planner System for jobs on-site in conjunction with the Location-Based Management System. The primary dashboard facilitates the management of complex work structures—typically involving hundreds of rows in Gantt chart representations or numerous lines in Line of Balance diagrams—while enabling the easy identification of activity cycles and gaps between activities in each zone. The tool offers a four-dimensional planning visualization—what, where, when, and who—enhancing the understanding of activity sequences and workflows across project zones, while also contributing to product quality improvement. Furthermore, it has been demonstrated through its application that the tool provides reliable, real-time information that supports decision-making, optimizes resource allocation, and improves overall project competitiveness.

Cloud-based adolescent physical health research incorporating cell molecular biomechanics insights into predictive modeling and biometric algorithms

The physical health of adolescents is critical to their future development and quality of life. However, there is still much room for improvement in monitoring and intervention of adolescent physical health in colleges and universities. Based on the National Standard for Student Physical Fitness and Health, this study proposes a physical health management framework for adolescents that combines a cloud platform and real-time data analysis. Through an innovative health monitoring and early warning system and feedback mechanism, the effectiveness of health intervention was significantly improved. Body mass index is related to the balance between energy intake and expenditure at the cellular level. Excessive calorie intake can lead to an increase in adipose cells, which secrete molecules that can affect overall metabolism and biomechanical stress on tissues. Lung capacity is linked to the elasticity and strength of the alveolar cells and the connective tissue in the lungs. he proper functioning of these cells, regulated by intracellular signaling pathways and molecular interactions, determines the efficiency of gas exchange. The 50-meter run, seated forward bending, standing long jump, pull-ups/sit-ups, and 800-meter/1000-meter run all involve muscle contractions. Muscle cells contain actin and myosin filaments, and the sliding of these filaments, regulated by calcium ions and other molecular signals, generates the force required for movement. The graded early warning parameters established by the system can thus be seen as indicators of potential disruptions in these cell molecular biomechanical processes. The innovative health monitoring and early warning system and feedback mechanism not only help students recognize the weaknesses in their physical functions from a macroscopic level but also potentially identify areas where cell molecular biomechanical imbalances may exist. This enables physical education teachers to formulate personalized training plans that can target and correct these imbalances, as experimentally validated by the system's ability to accurately identify health risks and enhance the overall health of students.

Acoustical modeling and analysis of proton-exchange membrane fuel cell stack anode exhaust gas from the perspective of ultrasound testing

Abstract Proton-exchange membrane fuel cells are widely utilized in transportation and stationary power generation applications due to their high energy conversion efficiency, substantial power density, and zero emissions. To address the requirements for internal status monitoring and hydrogen purge management in the hydrogen supply subsystem of automotive fuel cell systems, this paper proposes an innovative online monitoring scheme for real-time measurement of the anode exhaust mixture concentration from the fuel cell stack, utilizing an ultrasonic flowmeter. This scheme offers high measurement accuracy, short sampling intervals, simple configuration, and low cost. An acoustic analysis model of the anode exhaust gas was developed to systematically evaluate the influence of environmental parameters such as temperature, pressure, and humidity on the ultrasonic flowmeter’s measurement. Additionally, an ultrasonic flowmeter prototype was constructed based on this acoustic model, and the accuracy of its flow rate and concentration measurements was validated using standard gases. The results indicate that, without a humidity sensor, the absolute error in hydrogen concentration can reach 7 vol%, while the absolute error in nitrogen concentration can exceed 11 vol%. Therefore, integrating additional sensors is essential for improving the accuracy of concentration calculations for the anode exhaust gas components. The relative error in flow measurement with the ultrasonic flowmeter prototype is consistently below 5%, and the absolute error in concentration measurements is less than 1%, reflecting the effectiveness and feasibility of the proposed method. Furthermore, this paper outlines a calculation method for converting sensor feedback into the mass flow rates of individual gas components in the mixture. This work offers a novel theoretical and practical framework for enhancing real-time internal status monitoring and hydrogen purge management in fuel cell systems, which is expected to significantly improve the reliability, stability, and fuel economy of automotive fuel cell systems in the future.

Innovative Grouting Process Monitoring: Design and Implementation of a Measurement Device with Datalogger function

Innovative Grouting Process Monitoring: Design and Implementation of a Measurement Device with Datalogger function

Bibliometric Analysis of the Effects of Prolonged Preoperative Fasting on Patients

ABSTRACT Preoperative fasting is a common practice in the surgical field, which aims to minimize complications and ensure patient safety. Understanding its impact and optimizing protocols are essential in clinical practice. This study analyzed the bibliometric and network overview of publications on the effects of extended preoperative fasting on patients, using VOSViewer. This bibliometric analysis explores the research landscape on the effects of extended preoperative fasting duration on patients. Using VOSViewer, this study identified key contributors and clusters in the literature, highlighting significant research gaps. Bibliometric methods were used to analyze publications regarding the effects of extended preoperative fasting. Using VOSViewer, this study identified key contributors and groups in the literature, which highlighted significant research gaps. Bibliometric methods were used to analyze publications regarding the effects of extended preoperative fasting. Data were aggregated and visualized using VOSViewer to map the publication network and identify thematic clusters. China and the UK emerged as the main contributors with 7 articles each, followed by Brazil and India. Three main clusters were identified: a red cluster focusing on fasting duration, side effects, dehydration risk, and intraoperative management; a blue cluster exploring the effects of fasting on surgical outcomes, hunger, and procedural aspects; and a green cluster addressing guideline development, elective surgery, and preoperative preparation. These findings underscore the importance of extended preoperative fasting in clinical practice and highlight significant research opportunities. Future research could focus on personalized fasting protocols, long-term effects, psychological impact, and innovative monitoring technologies to improve the quality of patient care. Keywords: Preoperative Fasting, Effects Of Prolonged Fasting, Bibliometric Analysis, Vosviewer, Surgical Outcomes, Patient Care

Real-Time Identification of Yarn Irregularities on DTY Machine Through Vibration Monitoring

This paper presents an innovative real-time monitoring system for detecting yarn irregularities during the draw texturing process in DTY machine. The system uses advanced sensors to continuously measure vibration signals, which are then analyzed for anomalies. The system incorporates advanced sensors, controllers, and embedded software for monitoring the vibrations produced during the draw texturing process. Fast Fourier Transform (FFT) in LabVIEW converts these vibration signals into their frequency-domain representation. This helps identify anomalies that could indicate potential yarn irregularities. The results from the sensor data clearly indicate that amplitude values serve as a reliable measure for detecting yarn irregularities. For normal spindles, the amplitude ranges from 10.9 to 12.2 m/s², while abnormal spindles show significantly higher values, between 31.9 and 44.3 m/s². This distinction facilitates real-time classification of yarn quality. The system's ability to identify these amplitude variations promptly can significantly reduce waste and enhance quality control. Future developments will focus on integrating an intelligent early warning system that alerts operators immediately upon detecting irregularities, enabling quicker interventions and minimizing downtime.

Scalable and Secure IoT-Driven Vibration Monitoring: Advancing Predictive Maintenance in Industrial Systems

The rapid evolution of Industry 4.0 has positioned Internet of Things (IoT) technologies as key enablers for smarter industrial operations, particularly in predictive maintenance and machine monitoring. This research proposes an innovative IoT-driven vibration monitoring system that addresses limitations in traditional approaches such as high costs, limited scalability, and insufficient real-time capabilities. Employing low-cost sensors, edge computing, and LoRaWAN-based communication, the framework enables efficient fault detection and operational analysis. Data from industrial machinery was collected over two months and analyzed using advanced signal processing and machine learning techniques to extract meaningful insights. The system demonstrated an accuracy rate of 92%, a detection latency of 150 milliseconds, and extended sensor life to 12 months, marking significant improvements over conventional methods. Furthermore, scalability tests showed stable performance across setups involving up to 500 sensors, even in challenging industrial conditions. This study also highlights cost reductions of 30% and a 25% decline in machine downtime, reinforcing its practical value for industrial applications. By delivering an adaptable, energy-efficient, and secure solution, this research advances the integration of IoT into industrial systems. It lays the groundwork for future enhancements, including real-world testing and multimodal data integration

Advances in Bioprocess Engineering for Optimising Chlorella vulgaris Fermentation: Biotechnological Innovations and Applications.

Chlorella vulgaris, a unicellular green microalga, has obtained significant attention due to its high protein content, abundance of bioactive compounds, and broad biotechnological potential. Used in nutraceuticals, pharmaceuticals, and functional foods, it is now gaining traction in cosmetics, biopharmaceuticals, and environmental applications. Recent advancements in fermentation technology, such as the development of high-density fermentation strategies, adaptive evolution of strains, and real-time monitoring systems, have greatly improved the efficiency, scalability, and sustainability of C. vulgaris production, enhancing bioavailability and product quality. This review explores developments in C. vulgaris fermentation, highlighting advancements in strain improvement through genetic engineering, metabolic optimization, mutagenesis, and adaptive evolution, alongside bioprocess engineering and the optimization of fermentation parameters. Key considerations include bioreactor design, downstream processing, and innovative monitoring technologies aimed at maximizing biomass yield and bioactive compound production. Emerging applications of fermented C. vulgaris across industries are also highlighted, along with future perspectives on scaling up production, addressing regulatory challenges, and ensuring biosafety. These insights provide a comprehensive outlook on the future of C. vulgaris fermentation in biotechnological applications.

AIHEMAF-P: An Innovative Healthcare Model for Atrial Fibrillation Patients.

Atrial fibrillation (AF) is one of the most common cardiac arrhythmias of clinical relevance and a major cause of cardiovascular morbidity and mortality. Following a diagnosis of AF, patients are directed towards therapy with anticoagulant drugs to reduce the thromboembolic risk and antiarrhythmics to control their cardiac rhythm, with periodic follow-up checks. Despite the great ease of handling these drugs, we soon realized the need for follow-up models that would allow the appropriateness and safety of these pharmacological treatments to be monitored over time. This pilot study was conducted at a rural pharmacy. The study comprised 47 patients (average age 71.22 years) with nonvalvular atrial fibrillation (68% being paroxysmal) on NOACs. Twenty percent of the enrolled subjects lived alone and fifty-four percent of the participants stated that they were not independent in managing their treatment. The primary aim was to describe the implementation and the outcomes of an innovative smart clinic model in which a local trained pharmacist is a case manager, and the patient carries out the required checks via telemedicine and point-of-care testing systems (POCT) under the service pharmacy regime; the results of the checks could be shared in real time with the attending general practitioner and the relevant specialist. The secondary aims of this study were to evaluate adherence to the planned controls, the prescriptive appropriateness of the dosages and drugs and adherence to the prescribed therapy, the occurrence of pharmacological problems linked to drug type interactions, the occurrence of hemorrhagic and/or thromboembolic complications, the acceptance by the general practitioners and/or the specialists of the reports made by the pharmacist on the subsequent actions undertaken, the economic and social impact of this model on the National Health Service and on the patient, and the impact on the quality perceived by the patients involved in this innovative monitoring process. Compliance with the planned checks was 93%. The dosage of the anticoagulant drug during enrollment was found to be inappropriate, without apparent clinical reasons, in 11% of the sample. Adherence to the anticoagulant therapy was found to be 98%. In total, 214 drug-drug interactions of varying clinical relevance were detected. No embolic events were detected; however, 13% of the sample reported a major hemorrhagic event, which came to light thanks to the close monitoring of hemoglobinemia. A total of 109 reports were made to the patients' referring doctors in relation to the summarized anomalies, and 84% were accepted by the referring clinicians. Therefore, community pharmacists and pharmacy services represent ideal actors and contexts that, when integrated into the care network, can really favor individual care plan adherence and achieve daily morbidity reductions and cost savings through proper disease control and the early diagnosis of complications.

Exploring Pharmacological and Non-Pharmacological Approaches to Managing Hypertension During Pregnancy: A Systematic Review.

This systematic review aimed to explore the efficacy of both pharmacological and non-pharmacological interventions in managing hypertension during pregnancy. It analyzed high-quality randomized controlled trials (RCTs), focusing on outcomes related to maternal and fetal health. The findings demonstrated that antihypertensive medications, particularly labetalol and nifedipine, effectively reduced the risks of severe preeclampsia (PE), preterm birth, and other complications. Remote monitoring of blood pressure (BP) showed promise in improving postpartum care and addressing health disparities. While dietary interventions such as the Dietary Approaches to Stop Hypertension (DASH) diet offered metabolic benefits, their impact on preventing PE was inconclusive. The review highlights the need for a comprehensive approach to hypertension management, integrating medication, lifestyle interventions, and innovative monitoring strategies. It also emphasizes the importance of further research to refine non-pharmacological interventions and assess their long-term effectiveness. We believe these insights will help guide clinical practice, enhance maternal and fetal outcomes, and inform future research directions.

Innovations in Limnospira platensis Fermentation: From Process Enhancements to Biotechnological Applications

The cyanobacterium Limnospira platensis, vulgarly Spirulina, has gained significant attention due to its high protein content, rich bioactive compounds, and health benefits, making it a valuable resource in biotechnology, nutraceuticals, food supplements, biopharmaceuticals, and cosmetics. Recent advancements in fermentation technology have considerably improved the efficiency, scalability, and cost-effectiveness of L. platensis production while addressing environmental sustainability and enhancing product quality. Based on well-recognized databases (Google Scholar, PubMed, Scopus, Web of Science), this review explores the latest developments in L. platensis fermentation, emphasizing strain improvement, bioprocess engineering, and optimization of fermentation parameters. It also examines key factors such as bioreactor design, downstream processing, and innovative monitoring technologies aimed at maximizing biomass yield and bioactive compound production. Additionally, emerging applications of fermented L. platensis in various industries and future perspectives, including large-scale production, regulatory barriers, and biosafety considerations, are discussed. These insights provide a comprehensive outlook on the future of L. platensis fermentation in biotechnological applications.

Postimplementation Evaluation in Assisted Living Facilities of an eHealth Medical Device Developed to Predict and Avoid Unplanned Hospitalizations: Pragmatic Trial.

The proportion of very old adults in the population is increasing, representing a significant challenge. Due to their vulnerability, there is a higher frequency of unplanned hospitalizations in this population, leading to adverse events. Digital tools based on artificial intelligence (AI) can help to identify early signs of vulnerability and unfavorable health events and can contribute to earlier and optimized management. This study aims to report the implementation in assisted living facilities of an innovative monitoring system (Presage Care) for predicting the short-term risk of emergency hospitalization. We describe its use and assess its performance. An uncontrolled multicenter intervention study was conducted between March and August 2022 in 7 assisted living facilities in France that house very old and vulnerable adults. The monitoring system was set up to provide alerts in cases of a high risk of emergency hospitalization. Nurse assistants (NAs) at the assisted living facilities used a smartphone app to complete a questionnaire on the functional status of the patients, comprising electronic patient-reported outcome measures (ePROMs); these were analyzed in real time by a previously designed machine learning algorithm. This remote monitoring of patients using ePROMs allowed notification of a coordinating nurse or a coordinating NA who subsequently informed the patient's nurses or physician. The primary outcomes were the acceptability and feasibility of the monitoring system in the context and confirmation of the effectiveness and efficiency of AI in risk prevention and detection in practical, real-life scenarios. The secondary outcome was the hospitalization rate after alert-triggered interventions. In this study, 118 of 194 (61%) eligible patients were included who had at least 1 follow-up visit. A total of 38 emergency hospitalizations were documented. The system generated 92 alerts for 47 of the 118 (40%) patients. Of these 92 alerts, 46 (50%) led to 46 health care interventions for 14 of the 118 (12%) patients and resulted in 4 hospitalizations. The other 46 of the 92 (50%) alerts did not trigger a health care intervention and resulted in 25 hospitalizations (P<.001). Almost all hospitalizations were associated with a lack of alert-triggered interventions (P<.001). System performance to predict hospitalization had a high specificity (96%) and negative predictive value (99.4%). The Presage Care system has been implemented with success in assisted living facilities. It was well accepted by coordinating nurses and performed well in predicting emergency hospitalizations. However, its use by NAs was less than expected. Overall, the system performed well in terms of performance and clinical impact in this setting. Nevertheless, further work is needed to improve the moderate use rate by NAs. ClinicalTrials.gov NCT05221697; https://clinicaltrials.gov/study/NCT05221697.

AI-boosted and motion-corrected, wireless near-infrared sensing system for continuously monitoring laryngeal muscles

Neuromuscular diseases pose significant health and economic challenges, necessitating innovative monitoring technologies for personalizable treatment. Existing devices detect muscular motions either indirectly from mechanoacoustic signatures on skin surface or via ultrasound waves that demand specialized skin adhesion. Here, we report a wireless wearable system, Laryngeal Health Monitor (LaHMo), designed to be conformally placed on the neck for continuously measuring movements of underlying muscles. The system uses near-infrared (NIR) light that features deep-tissue penetration and strong interaction with myoglobin to capture muscular locomotion. The incorporated inertial measurement unit sensor further decouples the superposition of signals from NIR recordings. Integrating a multimodal AI-boosted algorithm based on recurrent neural network, the system accurately classifies activities of physiological events. An adaptive model enables fast individualization without enormous data sources from the target user, facilitating its broad applicability. Long-term tests and simulations suggest the potential efficacy of the LaHMo platform for real-world applications, such as monitoring disease progression in neuromuscular disorders, evaluating treatment efficacy, and providing biofeedback for rehabilitation exercises. The LaHMo platform may serve as a general noninvasive, user-friendly solution for assessing neuromuscular function beyond the anterior neck, potentially improving diagnostics and treatment of various neuromuscular disorders.

Editorial: Innovative process, monitoring and control in the wire arc additive manufacturing

Editorial: Innovative process, monitoring and control in the wire arc additive manufacturing

OPTIMIZATION OF MEDIAN STERNOTOMY AND STERNORRHAPHY IN DISEASES OF THE THORACIC ORGANS IN CHILDREN

This review article explores the optimization of median sternotomy and sternorraphy in pediatric patients with thoracic organ diseases. The discussion includes contemporary approaches to surgical techniques, materials used in suturing, and postoperative care that aim to improve surgical outcomes and reduce complications. Key advancements, such as minimally invasive methods, the introduction of advanced suture materials, and innovative postoperative monitoring techniques, are examined. By integrating a multidisciplinary approach and emphasizing individualized patient care, the article highlights the importance of these optimizations in enhancing recovery and overall treatment success for children undergoing thoracic surgery.

Safety Dynamic Monitoring and Rapid Warning Methods for Mechanical Shaft

In the context of urban space constraints, subway and underground projects have become crucial strategies to alleviate urban congestion and enhance residents’ quality of life. However, pit engineering, a frequent accident area in geotechnical engineering, urgently requires innovative safety monitoring technologies. Traditional monitoring methods face challenges such as high labor costs, lengthy monitoring cycles, high-risk working environments, and over-reliance on human judgment. To address these issues, this paper introduces an innovative monitoring system integrating Fiber Bragg Grating (FBG) sensing technology based on a subway pit project in Guangzhou. This system not only achieves fully automated data acquisition but also includes an intelligent monitoring cloud platform, providing unprecedented automated and intelligent monitoring solutions for support structures and the surrounding environment during mechanical shaft construction. The key findings of this paper include the following: (1) The breakthrough application of distributed optical fiber monitoring technology, including successfully deploying this advanced technology in complex pit engineering environments, enabling the precise and continuous monitoring of support structures and surrounding changes, and demonstrating its high effectiveness and intelligence in practical engineering. (2) The innovative design of an intelligent safety monitoring system. By integrating sensors and wireless communication technology, an efficient data networking architecture is constructed, supporting remote configuration and flexible adjustment of monitoring equipment, significantly enhancing data collection‘s real-time performance and continuity while greatly reducing safety risks for field staff, achieving an intelligent upgrade of monitoring work. (3) Comprehensive and accurate empirical analysis. During shaft excavation, the monitoring data collected by the system were stable and reliable, with all indicators maintained within reasonable ranges and closely matching expected changes caused by construction activities, validating the system’s practical application effectiveness in complex construction environments and providing a scientific basis for pit engineering safety management.

Application of AMIS-optimized vision transformer in identifying disease in Nile Tilapia

Efficient health monitoring in Nile tilapia aquaculture is critical due to the substantial economic losses from diseases, underlining the necessity for innovative monitoring solutions. This study introduces an advanced, automated health monitoring system known as the “Automated System for Identifying Disease in Nile Tilapia (AS-ID-NT),” which incorporates a heterogeneous ensemble deep learning model using the Artificial Multiple Intelligence System (AMIS) as the decision fusion strategy (HE-DLM-AMIS). This system enhances the accuracy and efficiency of disease detection in Nile tilapia. The research utilized two specially curated video datasets, NT-1 and NT-2, each consisting of short videos lasting between 3–10 s, showcasing various behaviors of Nile tilapia in controlled environments. These datasets were critical for training and validating the ensemble model. Comparative analysis reveals that the HE-DLM-AMIS embedded in AS-ID-NT achieves superior performance, with an accuracy of 92.48% in detecting health issues in tilapia. This system outperforms both single model configurations, such as the 3D Convolutional Neural Network and Vision Transformer (ViT-large), which recorded accuracies of 84.64% and 85.7% respectively, and homogeneous ensemble models like ViT-large-Ho and ConvLSTM-Ho, which achieved accuracies of 88.49% and 86.84% respectively. AS-ID-NT provides a non-invasive, continuous, and automated solution for timely intervention, successfully identifying both healthy and unhealthy (infected and environmentally stressed) fish. This system not only demonstrates the potential of advanced AI and machine learning techniques in enhancing aquaculture management but also promotes sustainable practices and food security by maintaining healthier fish populations and supporting the economic viability of tilapia farms.