Explore the vast range of titles available.

Machine learning (ML) has been remarkably successful in transforming numerous scientific and technological fields in recent years including computer vision, natural language processing, speech recognition, bioinformatics, etc. Naturally, it has long been considered as a promising mechanism to fundamentally revolutionize the existing archaic optical networks into next-generation smart and autonomous entities. However, despite its promise and extensive research conducted over the last decade, the ML paradigm has so far not been triumphant in achieving widespread adoption in commercial optical networks. In our perspective, this is primarily due to non-addressal of a number of critical non-technological issues surrounding ML-based solutions’ development and use in real-world optical networks. The vision of intelligent and autonomous fiber-optic networks, powered by ML, will always remain a distant dream until these so far neglected factors are openly confronted by all relevant stakeholders and categorically resolved. The author sheds light on critical non-technological barriers that significantly limit the broad utilization of machine learning in optical networks and presents several prospective solutions. Various pathways are discussed for the evolving machine learning potential for its desired penetration, credibility, and impact in real-world optical networks.

Artificial intelligence (AI) development across the health sector has recently been the most crucial. Early medical information, identification, diagnosis, classification, then analysis, along with viable remedies, are always beneficial developments. Precise and consistent image classification has critical in diagnosing and tactical decisions for healthcare. The core issue with image classification has become the semantic gap. Conventional machine learning algorithms for classification rely mainly on low-level but rather high-level characteristics, employ some handmade features to close the gap, but force intense feature extraction as well as classification approaches. Deep learning is a powerful tool with considerable advances in recent years, with deep convolution neural networks (CNNs) succeeding in image classification. The main goal is to bridge the semantic gap and enhance the classification performance of multi-modal medical images based on the deep learning-based model ResNet50. The data set included 28378 multi-modal medical images to train and validate the model. Overall accuracy, precision, recall, and F1-score evaluation parameters have been calculated. The proposed model classifies medical images more accurately than other state-of-the-art methods. The intended research experiment attained an accuracy level of 98.61%. The suggested study directly benefits the health service.

Magnesium deficiency is a frequently occurring limiting factor for crop production due to low levels of exchangeable Mg (ex-Mg) in acidic soil, which negatively affects sustainability of agriculture development. How Mg fertilization affects crop yield and subsequent physiological outcomes in different crop species, as well as agronomic efficiencies of Mg fertilizers, under varying soil conditions remain particular interesting questions to be addressed. A meta-analysis was performed with 570 paired observations retrieved from 99 field research articles to compare effects of Mg fertilization on crop production and corresponding agronomic efficiencies in different production systems under varying soil conditions. The mean value of yield increase and agronomic efficiency derived from Mg application was 8.5% and 34.4 kg kg respectively, when combining all yield measurements together, regardless of the crop type, soil condition, and other factors. Under severe Mg deficiency (ex-Mg < 60 mg kg ), yield increased up to 9.4%, nearly two folds of yield gain (4.9%) in the soil containing more than 120 mg kg ex-Mg. The effects of Mg fertilization on yield was 11.3% when soil pH was lower than 6.5. The agronomic efficiency of Mg fertilizers was negatively correlated with application levels of Mg, with 38.3 kg kg at lower MgO levels (0-50 kg ha ) and 32.6 kg kg at higher MgO levels (50-100 kg ha ). Clear interactions existed between soil ex-Mg, pH, and types and amount of Mg fertilizers in terms of crop yield increase. With Mg supplementation, Mg accumulation in the leaf tissues increased by 34.3% on average; and concentrations of sugar in edible organs were 5.5% higher compared to non-Mg supplemented treatments. Our analysis corroborated that Mg fertilization enhances crop performance by improving yield or resulting in favorable physiological outcomes, providing great potentials for integrated Mg management for higher crop yield and quality.

Pakistan has an agriculture-dependent economy vulnerable to climate impacts. Within Pakistan, Punjab province is a leading regional producer of food and cash crops, and an exporter of agricultural commodities of significance in South Asia. Punjab agriculture provides livelihoods for agriculture-dependent communities living in one of the most populous countries of the world and these will be disrupted under incremental climate changes (e.g. rising temperatures) and the impacts of extreme climate events (such as droughts and floods). Climate impact assessments and mapping are widely accepted initial approaches to address climate change as they have the potential to facilitate bottom-up adaptation. However, to date, policy responses in Pakistan have tended to be top-down, driven by national adaptation planning processes. This paper assesses agricultural vulnerability to impacts of climate events at the district scale for Punjab province by developing maps of the individual components of vulnerability, i.e. exposure, sensitivity and adaptive capacity. An indicator-based approach using a composite index method was adopted for the assessment. The mapping separated and categorised districts in Punjab based on their vulnerability to climate change and revealed spatial patterns and factors influencing district-level vulnerability. These geospatial variations in vulnerability illustrate the need for a nuanced policy on adaptation that recognises the importance of local biophysical and socio-economic context to build adaptive capacity for vulnerable regions rather than the current concentration on broad-scale top-down action embedded in National Adaptation Plans.

Globally, agriculture holds significant importance for human food, economic activities, and employment opportunities. Wheat stands out as the most cultivated crop in the farming sector; however, its annual production faces considerable challenges from various diseases. Timely and accurate identification of these wheat plant diseases is crucial to mitigate damage and enhance overall yield. Pakistan stands among the leading crop producers due to favorable weather and rich soil for production. However, traditional agricultural practices persist, and there is insufficient emphasis on leveraging technology. A significant challenge faced by the agriculture sector, particularly in countries like Pakistan, is the untimely and inefficient diagnosis of crop diseases. Existing methods for disease identification often result in inaccuracies and inefficiencies, leading to reduced productivity. This study proposes an efficient application for wheat crop disease diagnosis, adaptable for both mobile devices and computer systems as the primary decision-making engine. The application utilizes sophisticated machine learning techniques, including Decision Tree (DT), Random Forest (RF), Support Vector Machine (SVM), and AdaBoost, combined with feature extraction methods such as Count Vectorization (CV) and Term Frequency-Inverse Document Frequency (TF-IDF). These advanced methods collectively achieve up to 99% accuracy in diagnosing 14 key wheat diseases, representing a significant improvement over traditional approaches. The application provides a practical decision-making tool for farmers and agricultural experts in Pakistan, offering precise disease diagnostics and management recommendations. By integrating these cutting-edge techniques, the system advances agricultural technology, enhancing disease detection and supporting increased wheat production, thus contributing valuable innovations to both the field of machine learning and agricultural practices.

Redundancy analysis (RDA) showed that plant 13C (P-Atom13C) abundance and plant 15N (P-Con15N) abundance were pivotal factors that benefited the soil bacterial community composition under low temperature. [...]N nutrition can alleviate the low temperature stress in the soil through betterments of soil bacterial community compositions for the uptakes of carbon and nitrogen in Malus sieversii plants. The offset of the negative effects of salt stress on alfalfa growth and N fixation through improvements in N nutrition status suggested the importance of optimal N fertilization in salt-affected soils. During the growing season, it also proved to improve soil moisture and, subsequently, increased fruit yield in the virgin location as well. [...]the incorporation of food waste compost at a 2x rate can replace synthetic fertilizers and potentially increase peach growth, at least during orchard establishment. (2021).Cover crop management and water conservation in vineyard and olive orchards.Soil Tillage.

Amongst various environmental constraints, abiotic stresses are increasing the risk of food insecurity worldwide by limiting crop production and disturbing the geographical distribution of food crops. Millets are known to possess unique features of resilience to adverse environments, especially infertile soil conditions, although the underlying mechanisms are yet to be determined. The small diploid genome, short stature, excellent seed production, C photosynthesis, and short life cycle of foxtail millet make it a very promising model crop for studying nutrient stress responses. Known to be a drought-tolerant crop, it responds to low nitrogen and low phosphate by respective reduction and enhancement of its root system. This special response is quite different from that shown by maize and some other cereals. In contrast to having a smaller root system under low nitrogen, foxtail millet enhances biomass accumulation, facilitating root thickening, presumably for nutrient translocation. The low phosphate response of foxtail millet links to the internal nitrogen status, which tends to act as a signal regulating the expression of nitrogen transporters and hence indicates its inherent connection with nitrogen nutrition. Altogether, the low nitrogen and low phosphate responses of foxtail millet can act as a basis to further determine the underlying molecular mechanisms. Here, we will highlight the abiotic stress responses of foxtail millet with a key note on its low nitrogen and low phosphate adaptive responses in comparison to other crops.

International civil society and non-government organisations (NGOs) play a role in implementing agricultural projects, which contribute to the mitigation, adaptation, and food security dimensions of climate-smart agriculture (CSA). Despite the growth of CSA, it remains unclear how CSA is designed, conceptualised, and embedded into agricultural development projects led and implemented by NGOs, creating a lack of clarity as to the direction of future of agricultural development interventions. This paper examines the extent to which development programmes from the NGO sector actively incorporate CSA principles to benefit smallholder farmers under the major pillars of CSA. Drawing from six projects’ documentation since 2009, we conducted a thematic analysis to reveal the alignment of projects with the pillars of CSA and discuss the extent to which CSA allows for localised adaptability given the diverse agricultural contexts in which civil society and NGOs work. We find that despite a lack of clarity in CSA definition and focus, the agricultural practices in the six projects make heterogenous contributions to the adoption of CSA principles. We illustrate the diversity of ways in which CSA is ‘done’ by a global NGO across six areas: greening and forests, practices and knowledge exchange, markets, policy and institutions, nutrition, carbon and climate, and gender. We discuss the need for balance in contextual adaptability across the three pillars of CSA with explicit consideration of trade-offs to reduce unintended outcomes from CSA initiatives. We conclude with reflections on the role of civil society and NGOs as boundary agents in the agricultural development sector.

Real-time security surveillance and identity matching using face detection and recognition are central research areas within computer vision. The classical facial detection techniques include Haar-like, MTCNN, AdaBoost, and others. These techniques employ template matching and geometric facial features for detecting faces, striving for a balance between detection time and accuracy. To address this issue, the current research presents an enhanced FaceNet network. The RetinaFace is employed to perform expeditious face detection and alignment. Subsequently, FaceNet, with an improved loss function is used to achieve face verification and recognition with high accuracy. The presented work involves a comparative evaluation of the proposed network framework against both traditional and deep learning techniques in terms of face detection and recognition performance. The experimental findings demonstrate that an enhanced FaceNet can successfully meet the real-time facial recognition requirements, and the accuracy of face recognition is 99.86% which fulfills the actual requirement. Consequently, the proposed solution holds significant potential for applications in face detection and recognition within the education sector for real-time security surveillance.

Underwater visible light communication (UVLC) is a method that uses visible light as a carrier to transmit information through an underwater channel and offers the key advantages of fast speed, low cost and large capacity. The main challenges faced by UVLC systems include the power constraints of underwater terminals and signal distortions due to light attenuation in complex and changing underwater environments. In order to improve the efficiency and robustness of image transmission process in UVLC systems, we propose a novel image compression and reconstruction solution that jointly optimizes coding complexity and image reconstruction quality using neural architecture search (NAS) mechanism. Experimental validations on an UVLC system demonstrate that the proposed scheme achieves increased transmission efficiency with reduced algorithmic complexity and offers robustness to errors caused by the underwater channel distortions. For bit error rate (BER) values as high as 1.58 × 10 − 2 , the peak signal-to-noise ratio (PSNR) remains above 20 dB while structure similarity index measure (SSIM) value is above 0.67, for a compression ratio (CR) of 0.33.