Obstructive sleep apnea/hypopnea syndrome (OSAHS) is a condition linked to severe cardiovascular and neuropsychological consequences, characterized by recurrent episodes of partial or complete upper airway obstruction during sleep, leading to compromised ventilation, hypoxemia, and micro-arousals. Polysomnography (PSG) serves as the gold standard for confirming OSAHS, yet its extended duration, high cost, and limited availability pose significant challenges. In this paper, we employ a range of machine learning techniques, including Neural Networks, Decision Trees, Random Forests, and Extra Trees, for OSAHS diagnosis. This approach aims to achieve a diagnostic process that is not only more accessible but also more efficient. The dataset utilized in this study consists of records from 601 adults assessed between 2014 and 2016 at a specialized sleep medical center in Colombia. This research underscores the efficacy of ensemble methods, specifically Random Forests and Extra Trees, achieving an area under the Receiver Operating Characteristic (ROC) curve of 89.2% and 89.6%, respectively. Additionally, a web application has been devised, integrating the optimal model, empowering qualified medical practitioners to make informed decisions through patient registration, an input of 18 variables, and the utilization of the Random Forests model for OSAHS screening. Full article

Cowpea is one of the most popular dry-land legumes cultivated for food and forage in arid and semi-arid areas. Genetic diversity for global germplasm can be organized into core collections providing optimum resources to serve breeding requirements. Here, we present diversity analysis and genome-wide association study (GWAS) results for part of the cowpea core collection of the United States Department of Agriculture (USDA) along with breeding line controls. Included in the analysis were a total of 373 accessions analyzed with 6880 Single Nucleotide Polymorphism (SNP) markers from Genotyping by Sequencing (GBS). Population structure differentiated accessions into two groups irrespective of geographical origin and formed three clusters based on taxa upon phylogenetic analysis. A total of 56 SNPs were significantly associated to nine traits including pod length (25 Quantitative Trait Nucleotides, QTNs), seed anti-oxidant content (7 QTNs), dry pod color (7 QTNs), plant maturity (5 QTNs), flower color (5 QTNs), seed weight (4 QTNs), tolerance to low phosphate (1 QTN), growth habit (1 QTN), and response to rock phosphate (1 QTN) using Bayesian-information, Linkage-disequilibrium Iteratively Nested Keyway (BLINK), and Fixed and random model Circulating Probability Unification (FarmCPU) association models. Key genes related to all significant SNPs were identified based on annotations of the cowpea reference genome, including a flavonoid gene controlling flower color (Vigun08g040200.1), a root nodulation regulator for tolerance to low phosphate (Vigun11g168000.1), and numerous genes involved in signaling, biosynthesis, metabolite transport, and abiotic stress. Our results highlight the importance of maintaining public phenotyping databases at USDA and strengthening collaborations for data collection in cowpea to maximize research impacts. Full article

Logistics land is the spatial carrier for the development of logistics enterprises. Its evolution mode and driving mechanism determine the level of high-quality development of the logistics industry, and serve as an important basis for urban planning and territorial spatial planning. This study introduced a Boston consulting group (BCG) matrix and geographically weighted regression (GWR) spatial econometric models to carry out empirical research on the Yangtze River Delta (YRD), in an effort to provide scientific information for evidence-based decision-making by governments and enterprises. The scale and ratio of logistics land (LLS and LLR) in the YRD showed significant spatial heterogeneity and autocorrelation, cities with large logistics land use converging from clusters to belts from 2000 to 2020, and agglomerations with high logistics land ratio (LLR) migrating from inland to coastal areas. Diversified models of logistics land evolution also emerged, such as high scale–high speed cities, low scale–low speed cities, high scale–low speed cities, and low scale–high speed cities. In addition, the driving mechanism of LLS and LLR was very complex, with a great difference in the intensity, nature and spatial effects of the influence of different factors. The inspiration from empirical case studies is urgent to revise the planning norms and clarify the LLS and LLR control standards for logistics land use. Meanwhile, the synergistic development target of the logistics industry in the new era is changing from the manufacturing industry to the commerce and trade industry; the establishment of planning zoning and the designing of differentiated management policies significantly improve the planning applicability. Full article

Document-oriented databases, a type of Not Only SQL (NoSQL) database, are gaining popularity owing to their flexibility in data handling and performance for large-scale data. MongoDB, a typical document-oriented database, is a database that stores data in the JSON format, where the upper field involves lower fields and fields with the same related parent. One feature of this
document-oriented database is that data are dynamically stored in an arbitrary location without explicitly defining a schema in advance. This flexibility violates the above property and causes difficulties for application program readability and database maintenance. To address these issues, we propose a reconstruction support method for document structures in MongoDB. The method uses the strength of the Has-A relationship between the parent and child fields, as well as the similarity of field names in the MongoDB documents in natural language processing, to reconstruct the data structure in MongoDB. As a result, the method transforms the parent and child fields into more
coherent data structures. We evaluated our methods using real-world data and demonstrated their MongoDBeffectiveness. Full article

The excessive discharge of phosphorus-containing wastewater contributes to eutrophication, posing a serious threat to aquatic ecosystems. Therefore, methods such as electrocoagulation should be utilized to remove phosphorus from wastewater prior to discharging it into a water body. In this study, we aimed to determine the effectiveness of electrocoagulation in treating simulated phosphorus-containing wastewater under different parameters, including anode material (aluminum, iron, and magnesium), electrode distance (ED) (1, 2.5, and 4.5 cm), pH (3, 6, and 9), and current density (CD) (3, 6, and 9 mA/cm²). Additionally, three models of phosphate removal, the pseudo-first-order (PFO), pseudo-second-order (PSO), and Behnajady–Modirshahla–Ghanbery (BMG) models, were used to simulate the relationship between phosphate concentration and time in the electrocoagulation process using the three metals for phosphate removal. The experimental results showed that the aluminum system had the highest removal efficiency (90%) when energized for 20 min under a CD of 3 mA/cm², followed by those of the iron (80%) and magnesium (35%) systems. Furthermore, a life cycle assessment (LCA) showed that the aluminum electrode system had a smaller environmental impact than the iron and magnesium electrode systems. Therefore, the aluminum electrode system is suitable for phosphorus removal from wastewater. Full article

The rapid advancement of communication technologies underscores the urgent need for robust and adaptable emergency communication systems (ECSs), particularly crucial during crises and natural disasters. Although network-based ECSs have been extensively studied, integrating open-source technologies, such as software-defined wide area networks (SD-WAN) with private long-term evolution (LTE) base stations, is a relatively unexplored domain. This study endeavors to fill this gap by introducing an experimental ECS platform that utilizes a hybrid network, incorporating a VoIP network to enhance open-source and on-premises communications in targeted areas. Our hypothesis posits that a hybrid network architecture, combining SD-WAN and private LTE, can substantially improve the reliability and efficiency of ECSs. Our findings, supported by the open-source OMNeT++ simulator, illuminate the enhanced communication reliability of the network. Moreover, the proposed platform, characterized by autonomous wireless 4G/LTE base stations and an Asterisk VoIP server, demonstrates improved quality of service (QoS) and quality of experience (QoE), with minimal data loss. This research not only has immediate practical applications but also bears significant implications for the development of cost-effective, open-source communication networks, optimized for emergencies, critical infrastructure, and remote areas. Full article

Though we spend a significant amount of time in indoor and built environments as general occupants of residential or commercial spaces, we do not necessarily know how the heating, cooling, and ventilation services work in our occupied spaces. As the mechanical systems of buildings become more complex for energy saving and better indoor air quality, it is beneficial for occupants to learn more their built environment so that they can cooperate effectively for the building’s performance. In this context, the purpose of this research is to develop and evaluate how virtual reality (VR) technology can support occupants in understanding their built environment. An educational building on campus was selected for the development as it provides familiar spaces for potential participants in this research. This research was carried out in two stages. In Stage One, we, as researchers in mechanical engineering, explored the workflow for VR development and developed VR tours for four spaces: a classroom, an auditorium, a conference room, and a mechanical room. In Stage Two, we conducted a survey study to examine the VR experience from the perspective of users. In this survey study, we recruited 34 participants from engineering students/graduates, industry participants, and a sustainability group. The participants generally indicated a positive experience with the VR tours, although the quiz scores on the VR content were weak. From our reflection, we consider that positive and effective VR experiences for the education of the built environment require collaboration from three domains: (1) mechanical systems of buildings, (2) VR technology, and (3) pedagogy. Full article

Acrodermatitis chronica atrophicans (ACA) is not an infrequent condition in Europe. However, the characteristic skin lesions are often confused by non-dermatologists with other conditions. We report three unusual cases in which we made a definitive diagnosis of ACA complicated by cutaneous marginal zone lymphoma, juxta-articular fibrotic nodules, or bilateral sensory polyneuropathy. In all cases, correct diagnosis and adequate treatment was delayed over a period of at least 12 months. We initiated systemic antibiotics resulting in full recovery in these patients. The present case reports underscore that ACA may be associated with unusual clinical presentation which potentially result in delay of correct diagnosis and treatment. Hence, ACA diagnosis may be considerably delayed leading to inappropriate therapy exposure, prolonged patients’ suffering, and causing unnecessary cost. Thus, physicians who are not familiar with skin conditions should seek a timely consultation a dermatologist. Full article

Energy production from coal combustion is responsible for nearly 40% of global CO₂ emissions including SO_x and NO_x. This study aims to produce solid biomass fuels from oil-palm residues by torrefaction, having a high heating value (HHV) equivalent to fossil coals. The experiments were designed using Design Expert version 13 software to optimize the conditions affecting the fuel characteristics of the torrefied products. The statistical analysis suggested that the optimal conditions to achieve a high HHV and fixed carbon content while retaining the mass yield of biomass mainly depended on the temperature and torrefying time, while the size played a less important role in affecting the properties. The optimal conditions were observed to be at 283 °C (120 min) for EFBs, 301 °C (111 min) for PF, and 285 °C (120 min) for PKSs. The maximum HHV of 5229, 5969, and 5265 kcal/kg were achieved for the torrefied EFBs, PF, and PKSs, respectively. The energy efficiency of torrefied biomass was increased to 1.25–1.35. Ecoefficiency analysis suggested that torrefaction should be carried out at high temperatures with a short torrefying time. This low-cost bio-circular torrefied biomass showed promising fuel characteristics that could be potentially used as an alternative to coals. Full article

We are living in an era of advanced nanoscience and nanotechnology. Numerous nanomaterials, culminating in nanorobots, have demonstrated ingenious applications in biomedicine, including breast cancer (BC) nano-theranostics. To solve the complicated problem of BC heterogeneity, non-targeted drug distribution, invasive diagnostics or surgery, resistance to classic onco-therapies and real-time monitoring of tumors, nanorobots are designed to perform multiple tasks at a small scale, even at the organelles or molecular level. Over the last few years, most nanorobots have been bioengineered as biomimetic and biocompatible nano(bio)structures, resembling different organisms and cells, such as urchin, spider, octopus, fish, spermatozoon, flagellar bacterium or helicoidal cyanobacterium. In this review, readers will be able to deepen their knowledge of the structure, behavior and role of several types of nanorobots, among other nanomaterials, in BC theranostics. We summarized here the characteristics of many functionalized nanodevices designed to counteract the main neoplastic hallmark features of BC, from sustaining proliferation and evading anti-growth signaling and resisting programmed cell death to inducing angiogenesis, activating invasion and metastasis, preventing genomic instability, avoiding immune destruction and deregulating autophagy. Most of these nanorobots function as targeted and self-propelled smart nano-carriers or nano-drug delivery systems (nano-DDSs), enhancing the efficiency and safety of chemo-, radio- or photodynamic therapy, or the current imagistic techniques used in BC diagnosis. Most of these nanorobots have been tested in vitro, using various BC cell lines, as well as in vivo, mainly based on mice models. We are still waiting for nanorobots that are low-cost, as well as for a wider transition of these favorable effects from laboratory to clinical practice. Full article

Although blood still remains the most commonly utilized medium to detect increased levels of oxidative damage induced by exercise, saliva diagnostics have gained increasing popularity due to their non-invasive nature and athlete-friendly collection process. Given that the contribution of various phases of the menstrual cycle to the levels of oxidative damage may differ, the aim of this study was to evaluate an agreement between salivary and plasmatic levels of lipid peroxidation products in female swimmers in both the follicular (F) and luteal (L) phases of the menstrual cycle at rest and following exercise. Twelve well-trained female swimmers aged 19.6 ± 1.1 years old were examined. We measured diene conjugates (DCs), triene conjugates (TCs), and Schiff bases (SBs) in lipids immediately after their extraction from both saliva and blood plasma. All female swimmers were studied two times each, in the two different phases of one menstrual cycle, before and after high-intensity interval exercise (HIIE). Salivary and plasmatic levels of DCs, TCs, and SBs significantly increased post-exercise compared to pre-exercise, in both the F and L phases. A high positive correlation was observed between the concentrations of DCs, TCs, and SBs in the saliva and blood plasma of participants in the F and L phases, both at rest and following HIIE. Ordinary least products regression analysis indicates that there was no proportional and differential bias in the data. The Bland–Altman method also declares that there was no differential bias, since the line of equality was within the 95% confidence interval of the mean difference between salivary and plasmatic levels of DCs, TCs, and SBs in female swimmers, in both the F and L phases, before and after HIIE. There was also no proportional bias in the Bland–Altman plots. Thus, this is the first study to report a high agreement between the quantifications of DCs, TCs, and SBs in the saliva and blood plasma of female swimmers in both the F and L phases, at rest and following HIIE. Full article

Cultural routes are a composite set of heritage sites that refer to historical routes of human communication. As key products of cultural tourism, they provide visitors with rich cultural experiences across regions. We systematically review reports and studies related to the tourism development of 38 cultural route cases worldwide, with a special focus on their distribution, typology, planning patterns, and tools for cultural tourism. We summarized eight tools and found some differences in how often these eight tools are used by the different types of routes and different planning patterns for route tourism. This study also developed an evaluation system based on the conservation principles of cultural routes to determine how different tourism tools affect the conservation and development of historical regions. Although tourism decision-makers have made numerous efforts to protect and develop cultural routes, there are still many problems and challenges in the process of tourism development along cultural routes. We conclude the paper by making recommendations for decision-makers and researchers concerning future route tourism planning and study. Full article

Nanofibrous materials generated through electrospinning have gained significant attention in tissue regeneration, particularly in the domain of bone reconstruction. There is high interest in designing a material resembling bone tissue, and many scientists are trying to create materials applicable to bone tissue engineering with piezoelectricity similar to bone. One of the prospective candidates is highly piezoelectric poly(vinylidene fluoride) (PVDF), which was used for fibrous scaffold formation by electrospinning. In this study, we focused on the effect of PVDF molecular weight (180,000 g/mol and 530,000 g/mol) and process parameters, such as the rotational speed of the collector, applied voltage, and solution flow rate on the properties of the final scaffold. Fourier Transform Infrared Spectroscopy allows for determining the effect of molecular weight and processing parameters on the content of the electroactive phases. It can be concluded that the higher molecular weight of the PVDF and higher collector rotational speed increase nanofibers’ diameter, electroactive phase content, and piezoelectric coefficient. Various electrospinning parameters showed changes in electroactive phase content with the maximum at the applied voltage of 22 kV and flow rate of 0.8 mL/h. Moreover, the cytocompatibility of the scaffolds was confirmed in the culture of human adipose-derived stromal cells with known potential for osteogenic differentiation. Based on the results obtained, it can be concluded that PVDF scaffolds may be taken into account as a tool in bone tissue engineering and are worth further investigation. Full article

Our previous study demonstrated that our novel herbal remedy, a mixture of Asarum sieboldii, Platycodon grandiflorum, and Cinnamomum Cassia extracts, exhibits a therapeutic effect in 1-chloro-2,4-dinitrobenzene (DNCB)-induced mice by inhibiting the Th-2 inflammatory response upon oral administration. It also ameliorated imbalances in lipid metabolism related to the skin barrier function in keratinocytes, indicating its potential as a topical agent. This study aims to further investigate the therapeutic effects and metabolic mechanisms of its topical application. The anti-atopic effect was evaluated using dermatitis scores, histopathological analysis, and immune cell factors in DNCB-induced mice. Metabolomic profiling of serum and lesional skin was conducted to elucidate the metabolic mechanisms. The topical application significantly reduced dermatitis scores, mast cell infiltration, and serum levels of immunoglobulin E (IgE), IFN-γ, interleukin (IL)-4, IL-17, and thymic stromal lymphopoietin (TSLP), demonstrating its effectiveness in treating atopic dermatitis (AD). Serum metabolomics revealed alterations in fatty acid metabolism related to the pro-inflammatory response. In lesional skin, metabolic markers associated with oxidative stress, immune regulation, and AD symptoms were restored. This study demonstrated its potential as a topical agent in suppressing Th-2 inflammatory responses and improving metabolic abnormalities related to AD symptoms, providing crucial insights for developing natural AD treatments. Full article

The European Union’s recent decision to renew the authorization for the use of glyphosate until 15 December 2033 has stimulated scientific discussion all around the world regarding its toxicity or otherwise for humans. Glyphosate is a chemical of which millions of tons have been used in the last 50 years worldwide to dry out weeds in cultivated fields and greenhouses and on roadsides. Concern has been raised in many areas about its possible presence in the food chain and its consequent adverse effects on health. Both aspects that argue in favor of toxicity and those that instead may indicate limited toxicity of glyphosate are discussed here. The widespread debate that has been generated requires further investigations and field measurements to understand glyphosate’s fate once dispersed in the environment and its concentration in the food chain. Hence, there is a need for validated analytical methods that are available to analysts in the field. In the present review, methods for the analytical determination of glyphosate and its main metabolite, AMPA, are discussed, with a specific focus on chromatographic techniques applied to cereal products. The experimental procedures are explained in detail, including the cleanup, derivatization, and instrumental conditions, to give the laboratories involved enough information to proceed with the implementation of this line of analysis. The prevalent chromatographic methods used are LC-MS/MS, GC-MS/SIM, and GC-MS/MS, but sufficient indications are also given to those laboratories that wish to use the better performing high-resolution MS or the simpler HPLC-FLD, HPLC-UV, GC-NPD, and GC-FPD techniques for screening purposes. The concentrations of glyphosate from the literature measured in wheat, corn, barley, rye, oats, soybean, and cereal-based foods are reported, together with its regulatory status in various parts of the world and its accumulation mechanism. As for its accumulation in cereals, the available data show that glyphosate tends to accumulate more in wholemeal flours than in refined ones, that its concentration in the product strictly depends on the treatment period (the closer it is to the time of harvesting, the higher the concentration), and that in cold climates, the herbicide tends to persist in the soil for a long time. Full article

Though crucial for natural bone healing, local calcium ion (Ca²⁺) and phosphate ion (P_i) concentrations can exceed the cytotoxic limit leading to mitochondrial overload, oxidative stress, and cell death. For bone tissue engineering applications, H₂S can be employed as a cytoprotective molecule to enhance mesenchymal stem cell (MSC) tolerance to cytotoxic Ca²⁺/P_i concentrations. Varied concentrations of sodium hydrogen sulfide (NaSH), a fast-releasing H₂S donor, were applied to assess the influence of H₂S on MSC proliferation. The results suggested a toxicity limit of 4 mM for NaSH and that 1 mM of NaSH could improve cell proliferation and differentiation in the presence of cytotoxic levels of Ca²⁺ (32 mM) and/or P_i (16 mM). To controllably deliver H₂S over time, a novel donor molecule (thioglutamic acid—GluSH) was synthesized and evaluated for its H₂S release profile. Excitingly, GluSH successfully maintained cytoprotective level of H₂S over 7 days. Furthermore, MSCs exposed to cytotoxic Ca²⁺/P_i concentrations in the presence of GluSH were able to thrive and differentiate into osteoblasts. These findings suggest that the incorporation of a sustained H₂S donor such as GluSH into CaP-based bone graft substitutes can facilitate considerable cytoprotection, making it an attractive option for complex bone regenerative engineering applications. Full article

This review focuses on the use of conventional gel or coil and “new” generation hydrogel used as an embolic agent in endovascular applications. In general, embolic agents have deep or multidistrict vascular penetration properties as they ensure complete occlusion of vessels by exploiting the patient’s coagulation system, which recognises them as substances foreign to the body, thus triggering the coagulation cascade. This is why they are widely used in the treatment of endovascular corrections (EV repair), arteriovenous malformations (AVM), endoleaks (E), visceral aneurysms or pseudo-aneurysms, and embolisation of pre-surgical or post-surgical (iatrogenic) lesions. Conventional gels such as Onyx or coils are now commercially available, both of which are frequently used in endovascular interventional procedures, as they are minimally invasive and have numerous advantages over conventional open repair (OR) surgery. Recently, these agents have been modified and optimised to develop new embolic substances in the form of hydrogels based on alginate, chitosan, fibroin and other polymers to ensure embolisation through phase transition phenomena. The main aim of this work was to expand on the data already known in the literature concerning the application of these devices in the endovascular field, focusing on the advantages, disadvantages and safety profiles of conventional and innovative embolic agents and also through some clinical cases reported. The clinical case series concerns the correction and exclusion of endoleak type I or type II appeared after an endovascular procedure of exclusion of aneurysmal abdominal aortic (EVAR) with a coil (coil penumbra released by a LANTERN microcatheter), the exclusion of renal arterial malformation (MAV) with a coil (penumbra coil released by a LANTERN microcatheter) and the correction of endoleak through the application of Onyx 18 in the arteries where sealing by the endoprosthesis was not guaranteed. Full article

This study introduces a novel approach for fault classification in bearing components utilizing raw accelerometer data. By employing various neural network models, including deep learning architectures, we bypass the traditional preprocessing and feature-extraction stages, streamlining the classification process. Utilizing the Case Western Reserve University (CWRU) bearing dataset, our methodology demonstrates remarkable accuracy, particularly in deep learning networks such as the three variant convolutional neural networks (CNNs), achieving above 98% accuracy across various loading levels, establishing a new benchmark in fault-detection efficiency. Notably, data exploration through principal component analysis (PCA) and t-distributed stochastic neighbor embedding (t-SNE) provided valuable insights into feature relationships and patterns, aiding in effective fault detection. This research not only proves the efficacy of neural network classifiers in handling raw data but also opens avenues for more straightforward yet effective diagnostic methods in machinery health monitoring. These findings suggest significant potential for real-world applications, offering a faster yet reliable alternative to conventional fault-classification techniques. Full article

Language barriers, specifically among refugees, pose significant challenges to delivering quality healthcare in Canada. While the COVID-19 pandemic accelerated the emergence and development of innovative alternatives such as telephone-based and video-conferencing medical interpreting services and AI tools, access remains uneven across Canada. This comprehensive analysis highlights the absence of a cohesive national strategy, reflected in diverse funding models employed across provinces and territories, with gaps and disparities in access to medical interpreting services. Advocating for medical interpreting, both as a moral imperative and a prudent investment, this article draws from human rights principles and ethical considerations, justified in national and international guidelines, charters, codes and regulations. Substantiated by a cost-benefit analysis, it emphasizes that medical interpreting enhances healthcare quality and preserves patient autonomy. Additionally, this article illuminates decision-making processes for utilizing interpreting services; recognizing the pivotal roles of clinicians, interpreters, patients and caregivers within the care circle; appreciating intersectional considerations such as gender, culture and age, underscoring the importance of a collaborative approach. Finally, it provides recommendations at provider, organizational and system levels to ensure equitable access to this right and to promote the health and well-being of refugees and other individuals facing language barriers within Canada’s healthcare system. Full article

This paper presents the development of a novel anti-violence device titled “no pAIn” (an acronym for Never Oppressed Protected by Artificial Intelligence Nonviolence system), which harnesses the power of artificial intelligence (AI). Primarily designed to combat violence against women, the device offers personal safety benefits for individuals across diverse demographics. Operating autonomously, it necessitates no user interaction post-activation. The AI engine conducts real-time speech recognition and effectively discerns genuine instances of aggression from non-violent disputes or conversations. Facilitated by its Internet connectivity, in the event of detected aggression, the device promptly issues assistance requests with real-time precise geolocation tracking to predetermined recipients for immediate assistance. Its compact size enables discreet concealment within commonplace items like candy wrappers, purpose-built casings, or wearable accessories. The device is battery-operated. The prototype was developed using a microcontroller board (Arduino Nano RP2040 Connect), incorporating an omnidirectional microphone and Wi-Fi module, all at a remarkably low cost. Subsequent functionality testing, performed in debug mode using the Arduino IDE serial monitor, yielded successful results. The AI engine exhibited exceptional accuracy in word recognition, complemented by a robust logic implementation, rendering the device highly reliable in discerning genuine instances of aggression from non-violent scenarios. Full article

Shrimp fry counting is an important task for biomass estimation in aquaculture. Accurate counting of the number of shrimp fry in tanks can not only assess the production of mature shrimp but also assess the density of shrimp fry in the tanks, which is very helpful for the subsequent growth status, transportation management, and yield assessment. However, traditional manual counting methods are often inefficient and prone to counting errors; a more efficient and accurate method for shrimp fry counting is urgently needed. In this paper, we first collected and labeled the images of shrimp fry in breeding tanks according to the constructed experimental environment and generated corresponding density maps using the Gaussian kernel function. Then, we proposed a multi-scale attention fusion-based shrimp fry counting network called the SFCNet. Experiments showed that our proposed SFCNet model reached the optimal performance in terms of shrimp fry counting compared to CNN-based baseline counting models, with MAEs and RMSEs of 3.96 and 4.682, respectively. This approach was able to effectively calculate the number of shrimp fry and provided a better solution for accurately calculating the number of shrimp fry. Full article

Accurate feeding management in aquaculture relies on assessing the average weight of aquatic animals during their growth stages. The traditional method involves using a labor-intensive approach and may impact the well-being of fish. The current research focuses on a unique way of estimating red tilapia’s weight in cage culture via a river, which employs unmanned aerial vehicle (UAV) and deep learning techniques. The described approach includes taking pictures by means of a UAV and then applying deep learning and machine learning algorithms to them, such as convolutional neural networks (CNNs), extreme gradient boosting (XGBoost), and a Hybrid CNN-XGBoost model. The results showed that the CNN model achieved its accuracy peak after 60 epochs, showing accuracy, precision, recall, and F1 score values of 0.748 ± 0.019, 0.750 ± 0.019, 0.740 ± 0.014, and 0.740 ± 0.019, respectively. The XGBoost reached its accuracy peak with 45 n_estimators, recording values of approximately 0.560 ± 0.000 for accuracy and 0.550 ± 0.000 for precision, recall, and F1. Regarding the Hybrid CNN-XGBoost model, it demonstrated its prediction accuracy using both 45 epochs and n_estimators. The accuracy value was around 0.760 ± 0.019, precision was 0.762 ± 0.019, recall was 0.754 ± 0.019, and F1 was 0.752 ± 0.019. The Hybrid CNN-XGBoost model demonstrated the highest accuracy compared to using standalone CNN and XGBoost models and could reduce the time required for weight estimation by around 11.81% compared to using the standalone CNN. Although the testing results may be lower than those from previous laboratory studies, this discrepancy is attributed to the real-world testing conditions in aquaculture settings, which involve uncontrollable factors. To enhance accuracy, we recommend increasing the sample size of images and extending the data collection period to cover one year. This approach allows for a comprehensive understanding of the seasonal effects on evaluation outcomes. Full article