Explore the vast range of titles available.

Aquaculture plays a crucial role in meeting the growing global demand for seafood, but it faces challenges in terms of fish growth and health monitoring. The advancement of artificial intelligence (AI) techniques offers promising solutions for optimizing fish farming practices and ensuring sustainable aquaculture. This abstract provides an overview of the role of AI in fish growth and health status monitoring, emphasizing its significance in promoting a sustainable aquaculture industry. AI technologies, such as machine learning and computer vision, have shown immense potential in analyzing large volumes of data collected from fish farms. By leveraging AI algorithms, fish farmers can gain valuable insights into fish growth patterns, feeding behavior, and environmental factors affecting fish health. These algorithms can detect and predict anomalies, diseases, and stress indicators, enabling proactive interventions to mitigate health issues and reduce losses. One of the key applications of AI in aquaculture is the development of smart monitoring systems. These systems employ various sensors, cameras, and data analytics tools to continuously collect real-time data on water quality, temperature, oxygen levels, and fish behavior. AI algorithms analyze this data to identify deviations from optimal conditions and provide timely alerts to farmers, allowing them to take appropriate actions such as adjusting feeding schedules, modifying water parameters, or administering treatments as needed. Furthermore, AI-based models can assist in optimizing feed management and reducing wastage. By analyzing historical data on fish growth and feed consumption, machine learning algorithms can determine the most efficient feed formulation and feeding regimes, leading to improved growth rates and minimized environmental impact. Another significant aspect of AI in fish farming is disease detection and prevention. Through image analysis and pattern recognition, AI algorithms can identify early signs of diseases, parasites, or abnormalities in fish appearance and behavior. This enables prompt disease diagnosis and targeted treatment, reducing the need for excessive use of antibiotics and chemicals while improving fish welfare. In summary, the integration of AI techniques in fish growth and health status monitoring holds great promise for the sustainability of aquaculture. By leveraging AI's capabilities in data analysis, pattern recognition, and predictive modeling, fish farmers can optimize their practices, enhance productivity, reduce environmental impact, and ensure the welfare of farmed fish. However, continued research, data sharing, and collaboration between scientists, industry stakeholders, and policymakers are essential for harnessing the full potential of AI in achieving a sustainable aquaculture industry.

We evaluated the effectiveness of the growth monitoring and promotion (GMP) program in Zambia. A 3-mo prospective study of growth outcomes was undertaken at randomly selected health facilities and community posts within the Lusaka district. Children <2 y old ( n = 698) were purposively sampled from three health facilities ( n = 459) and four community posts ( n = 77) where health workers had undergone training in GMP and three health facilities where staff had not received training ( n = 162). Qualitative data on knowledge, attitudes, and practices of GMP were collected from health facility managers ( n = 6), health workers ( n = 35), and mothers whose children attended all follow-up visits ( n = 27). Anthropometric status of children in all groups deteriorated, with children at community posts having the worst outcomes (change in weight-for-age Z-score −0.8 ± 0.7), followed by trained (−0.5 ± 0.6) and untrained (–0.3 ± 0.47; P < 0.05) health facilities. A similar trend was seen for weight for length. The overall dropout rate was 74.1%. Weight-for-age Z-scores were higher at 1- and 2-mo follow-up visits for children who did not complete the study at trained health facilities and community posts compared with those who remained in the study. Mothers/caregivers identified GMP as important in attending the under-five clinic, associated their child's weight with overall health status, and expressed a willingness to comply with health workers' advice. However, health care providers were poorly motivated, inadequately supervised, and demonstrated poor practices. The GMP program in Lusaka is functioning suboptimally, even in facilities with trained staff.

Growth indices can quantify crop productivity and establish optimal environmental, nutritional, and irrigation control strategies. A convolutional neural network (CNN)-based model is presented for estimating various growth indices (i.e., fresh weight, dry weight, height, leaf area, and diameter) of four varieties of greenhouse lettuce using red, green, blue, and depth (RGB-D) data obtained using a stereo camera. Data from an online autonomous greenhouse challenge (Wageningen University, June 2021) were employed in this study. The data were collected using an Intel RealSense D415 camera. The developed model has a two-stage CNN architecture based on ResNet50V2 layers. The developed model provided coefficients of determination from 0.88 to 0.95, with normalized root mean square errors of 6.09%, 6.30%, 7.65%, 7.92%, and 5.62% for fresh weight, dry weight, height, diameter, and leaf area, respectively, on unknown lettuce images. Using red, green, blue (RGB) and depth data employed in the CNN improved the determination accuracy for all five lettuce growth indices due to the ability of the stereo camera to extract height information on lettuce. The average time for processing each lettuce image using the developed CNN model run on a Jetson SUB mini-PC with a Jetson Xavier NX was 0.83 s, indicating the potential for the model in fast real-time sensing of lettuce growth indices.

Flexible strain sensors capable of conformal integration with living organisms are essential for advanced wearable electronics, human–machine interaction, and plant health. However, many existing sensors require complex fabrication or rely on non-breathable elastomer substrates that interfere with the physiological microenvironment of skin or plant tissues. Here, we present a low-cost, breathable, and highly stretchable strain sensor constructed from biomedical materials, in which a double-layer medical elastic bandage serves as the porous substrate and an intermediate conductive medical elastic tape impregnated with carbon nanotubes (CNTs) ink acts as the sensing layer. Owing to the hierarchical textile porosity and the deformable CNTs percolation network, the sensor achieves a wide strain range of 100%, a gauge factor of up to 2.72, and excellent nonlinear second-order fitting (R2 = 0.997). The bandage substrate provides superior air permeability, allowing long-term attachment without obstructing moisture and gas exchange, which is particularly important for maintaining skin comfort and preventing disturbances to plant epidermal physiology. Demonstrations in human joint-motion monitoring and real-time plant growth detection highlight the device’s versatility and biological compatibility. This work offers a simple, low-cost yet effective alternative to sophisticated strain sensors designed for human monitoring and plant growth monitoring, providing a scalable route toward multifunctional wearable sensing platforms.

Image segmentation is a crucial task in computer vision, which divides a digital image into multiple segments and objects. In agriculture, image segmentation is extensively used for crop and soil monitoring, predicting the best times to sow, fertilize, and harvest, estimating crop yield, and detecting plant diseases. However, image segmentation faces difficulties in agriculture, such as the challenges of disease staging recognition, labeling inconsistency, and changes in plant morphology with the environment. Consequently, we have conducted a comprehensive review of image segmentation techniques based on deep learning, exploring the development and prospects of image segmentation in agriculture. Deep learning-based image segmentation solutions widely used in agriculture are categorized into eight main groups: encoder-decoder structures, multi-scale and pyramid-based methods, dilated convolutional networks, visual attention models, generative adversarial networks, graph neural networks, instance segmentation networks, and transformer-based models. In addition, the applications of image segmentation methods in agriculture are presented, such as plant disease detection, weed identification, crop growth monitoring, crop yield estimation, and counting. Furthermore, a collection of publicly available plant image segmentation datasets has been reviewed, and the evaluation and comparison of performance for image segmentation algorithms have been conducted on benchmark datasets. Finally, there is a discussion of the challenges and future prospects of image segmentation in agriculture.

The canopy characteristics of crops are essential aspects for assessing crop growth status and conducting phenotype analysis. As one of the key indicators to measure crop growth situation, accurate canopy coverage assessment can provide a strong foundation for crop growth and yield monitoring. Considering plant growth differences, this study investigated the statistical method for assessing canopy coverage using visual technology, focusing on lettuce as the research subject. Firstly, a multi-variety and multi-growth stage hydroponic lettuce image dataset was constructed, which lays a data foundation for the construction of a semantic segmentation model. Secondly, in order to ensure the precision of semantic segmentation, this study proposed a Channel-Axial-Spatial attention mechanism module from the perspective of feature enhancement. To satisfy the lightweight demands of practical model deployment, this study replaced the original backbone network of PSPNet with MobileNetv3, greatly reduced model complexity while minimizing model performance degradation. Finally, we developed a group lettuce canopy coverage acquisition system by employing Python in conjunction with PyQt5 and embedded the pre-trained models CAS-PSPNet and MobileNetv3-PSPNet into the system for effectiveness verification. By integrating the proposed attention mechanism module with PSPNet, the integrated model outperformed FCN, Unet, SegNet, Deeplabv3+, GCN, ExFusion, ENet, BiseNet, FusionNet, LinkNet, RefineNet, LWRefineNet, and PSPNet in semantic segmentation of lettuce plant groups, achieving a Mean Intersection over Union of 0.9832. The Mean Intersection over Union of PSPNet based on lightweight improvement is 0.9717, and the model size is 9.3M. The results show that the proposed semantic segmentation method can accurately capture the crop canopy coverage, offering a feasible solution for real-time crop growth monitoring.

Plants are primary resources for oxygen and foods whose production is fundamental for our life. However, diseases and pests may interfere with plant growth and cause a significant reduction of both the quality and quantity of agriculture products. Increasing agricultural productivity is crucial for poverty reduction and food security improvements. For this reason, the 2030 Agenda for Sustainable Development gives a central role to agriculture by promoting a strong technological innovation for advancing sustainable practices at the plant level. To accomplish this aim, recently, wearable sensors and flexible electronics have been extended from humans to plants for measuring elongation, microclimate, and stressing factors that may affect the plant’s healthy growth. Unexpectedly, fiber Bragg gratings (FBGs), which are very popular in health monitoring applications ranging from civil infrastructures to the human body, are still overlooked for the agriculture sector. In this work, for the first time, plant wearables based on FBG technology are proposed for the continuous and simultaneous monitoring of plant growth and environmental parameters (i.e., temperature and humidity) in real settings. The promising results demonstrated the feasibility of FBG-based sensors to work in real situations by holding the promise to advance continuous and accurate plant health growth monitoring techniques.

Flexible strain sensor as a measurement tool plays a significant role in agricultural development by long-term stable monitoring of the dynamic progress of plant growth. However, existing strain sensors still suffer from severe drawbacks, such as large hysteresis, insufficient fatigue resistance, and inferior stability, limiting their broad applications in the long-term monitoring of plant growth. Herein, we fabricate a novel conductive hydrogel strain sensor which is achieved through uniformly dispersing the conductive activated charcoal (AC) in high-viscosity polyvinyl alcohol (PVA) solution forming a continuous conductive network and simple preparation by freezing-thawing. The as-prepared strain sensor demonstrates low hysteresis (<1.5%), fatigue resistance (fatigue threshold of 40.87 J m−2), and long-term sensing stability upon mechanical cycling. We further exhibit the integration and application of PVA-AC strain sensor to monitor the growth of plants for 14 days. This work may offer an effective strategy for monitoring plant growth with conductive hydrogel strain sensor, facilitating the advancement of agriculture.

To quantify the prevalence and trends of stunting among children using the WHO growth standards. Five hundred and seventy-six nationally representative surveys, including anthropometric data, were analysed. Stunting was defined as the proportion of children below -2sd from the WHO length- or height-for-age standards median. Linear mixed-effects modelling was used to estimate rates and numbers of affected children from 1990 to 2010, and projections to 2020. One hundred and forty-eight developed and developing countries. Boys and girls from birth to 60 months. In 2010, it is estimated that 171 million children (167 million in developing countries) were stunted. Globally, childhood stunting decreased from 39·7 (95 % CI 38·1, 41·4) % in 1990 to 26·7 (95 % CI 24·8, 28·7) % in 2010. This trend is expected to reach 21·8 (95 % CI 19·8, 23·8) %, or 142 million, in 2020. While in Africa stunting has stagnated since 1990 at about 40 % and little improvement is anticipated, Asia showed a dramatic decrease from 49 % in 1990 to 28 % in 2010, nearly halving the number of stunted children from 190 million to 100 million. It is anticipated that this trend will continue and that in 2020 Asia and Africa will have similar numbers of stunted children (68 million and 64 million, respectively). Rates are much lower (14 % or 7 million in 2010) in Latin America. Despite an overall decrease in developing countries, stunting remains a major public health problem in many of them. The data summarize progress achieved in the last two decades and help identify regions needing effective interventions.

Growth monitoring and promotion (GMP) programmes have been implemented for decades in almost all countries. Despite this long history of implementation, GMP has been criticised for being ineffective, calling for a rethink of the programme. With a view of contributing evidence towards the redesign of GMP, we conducted a qualitative evaluation of the programme in various contexts of Ethiopia. We conducted focus‐group discussions (FGDs; n  = 28) and key informant interviews (KIIs; n  = 193) with programme managers, service providers and caregivers beneficiaries. Supply‐side, service delivery, and barriers hindering effective coverage were identified. Lack of functional weighing scales, budget constraints, limited transportation facilities, overlap of interventions, and the low motivation and performance of health workers were identified as main barriers affecting the quality‐of‐service delivery. The benefits of participating in GMP were not always clear to beneficiaries. Competing priorities like household chores, long travel distances to health centres, and in some contexts culturally insensitive practices deterred participation. Although GMP can serve as an entry point for mainstreaming nutrition into universal health coverage (UHC), the programme would need to be redesigned and supported by adequate supply, resources (financial and human), planning, and quality service delivery that is contextual and culturally sensitive. Supply and resource constraints along with the work overload and the low motivation and performance of health workers affect the quality of growth monitoring and promotion (GMP) service delivery. Caregivers did not always see the benefit of GMP. GMP sessions were avoided by child caregivers due to competing priorities like household chores, the long travel distances to health centres, and the fear of being judged by others. Malnutrition screening is undermined by a systemic failure to ensure diagnosed children receive the subsequent services and support they desperately need. GMP programme should be redesigned and be supported by adequate supply, resources (financial and human), planning, and quality service delivery that is contextual and culturally sensitive.