Search Results (5,961)

Natural language understanding (NLU) includes temporal text understanding, which can be complex and encompasses temporal common sense understanding. There are many challenges in comprehending common sense within a text. Currently, there is a limited number of datasets containing temporal common sense in English and there is an absence of such datasets specifically for the Arabic language. In this study, an Arabic dataset was constructed based on an available English dataset. This dataset is considered a valuable resource for the Arabic community. Consequently, different multilingual pre-trained language models (PLMs) were applied to both the English and new Arabic datasets. Based on this, the effectiveness of these models in Arabic and English is compared and discussed. After analyzing the errors, a new categorization of errors was proposed. Finally, the ability of the PLMs to understand the input text and predict temporal features was evaluated. Through this detailed categorization of errors and classification of temporal elements, this study establishes a comprehensive framework aimed at clarifying the specific challenges encountered by PLMs in temporal common sense understanding (TCU). This methodology underscores the urgent need for further research on PLMs’ capabilities for TCU tasks. Full article

Blockchain and artificial intelligence are two of the most prominent technologies in computer science today and have attracted considerable attention from various research communities. Recently, several initiatives have been launched to explore the combination of these two pioneering technologies. The main goal is to combine the data integrity, privacy, and decentralization properties of blockchain with the ability of artificial intelligence to process, analyze, predict, and refine massive data sets. The combination of blockchain and AI technologies is expected to address key challenges in the digital realm, such as data security, transparency, and streamlined decision-making. However, there is a problem that many studies have focused on the advancement of a single technology as the main perspective. To overcome these recent research limitations, we provide a broad view of the combination of blockchain and artificial intelligence and analyze the limitations of existing research and their causes. Furthermore, we identify challenges and attempts to be addressed through this analysis. The analysis in this paper is organized into a comprehensive section dedicated to the application of artificial intelligence in blockchain and vice versa. Based on our analysis, we identify existing challenges and propose a novel framework for researchers to overcome these limitations, thus expanding new research opportunities. Full article

In the big data era, data are created in huge volume. This leads to the development of storage devices. Many technologies are proposed for the next generation of storage fields. However, among them, holographic data storage (HDS) has attracted much attention and has been introduced as the promising candidate to meet the increasing demand for capacity and speed. For signal processing, HDS faces two major challenges: inter-page interference (IPI) and two-dimensional (2D) interference. To access the IPI problem, we can use balanced coding, which converts user data into an intensity level with uniformly distributed values for each page. For 2D interference, we can use the equalizer and detection to mitigate the 2D interference. However, the often-used equalizer and detection are methods in wireless communication and only handle the one-dimensional (1D) signal. Thus, we can combine the equalizer, detection, and estimator to reduce 2D interference into 1D interference. In this paper, we proposed a combined model using serial maximum a posteriori (MAP) detection and estimator to improve the detection of HDS systems. In our proposed model, instead of using an estimator with the Viterbi algorithm to predict the upper–lower interference (UPI) or left–right interference (LRI) and converting the received signal into 1D ISI, we used the estimator to predict the extrinsic information for serial MAP detection. This preserves the 2D information in the received signal in serial MAP detection and improves the detection of serial MAP detection by extrinsic information. The simulation results demonstrate that our proposed model significantly improves the bit-error rate (BER) performance compared to previous studies. Full article

Soil is a complex and dynamic ecosystem containing a diverse array of microorganisms, and plays a crucial and multifaceted role in various functions of the ecosystem. Substantial fluctuations in the environmental conditions arise from diverse global changes. The microbial shifts in the soil in concordance with the changing environmental factors, or a combination of these factors, are of high significance. Exploring the contribution of global change drivers to the microbial community to improve the predictions of the response of the microbial community to the functioning of the ecosystem is of prime importance. Promoting the health of soil microorganisms maintains the overall health and fertility of the soil, which in turn supports the health of terrestrial ecosystems and agricultural systems. The current review aims to assemble different abiotic factors or stressors that exist in the environment that affect the microbial community. More focus will be given to one of the stressors—antibiotics, a recent emerging pollutant. The effects on the soil microbial community and the future of soil health due to the presence of antibiotics will be addressed. The scope of the interaction of antibiotics with other pollutants like plastics and heavy metals (HMs) will be examined. Full article

IoT (Internet of Things) networks are vulnerable to network viruses and botnets, while facing serious network security issues. The prediction of payload states in IoT networks can detect network attacks and achieve early warning and rapid response to prevent potential threats. Due to the instability and packet loss of communications between victim network nodes, the constructed protocol state machines of existing state prediction schemes are inaccurate. In this paper, we propose a network payload predictor called IoTGuard, which can predict the payload states in IoT networks based on real-time IoT network traffic. The steps of IoTGuard are briefly as follows: Firstly, the application-layer payloads between different nodes are extracted through a module of network payload separation. Secondly, the classification of payload state within network flows is obtained via a payload extraction module. Finally, the predictor of payload state in a network is trained on a payload set, and these payloads have state labels. Experimental results on the Mozi botnet dataset show that IoTGuard can predict the state of payloads in IoT networks more accurately while ensuring execution efficiency. IoTGuard achieves an accuracy of 86% in network payload prediction, which is 8% higher than the state-of-the-art method NetZob, and the training time is reduced by 52.8%. Full article

As farming practices evolve and climate conditions shift, achieving sustainable food production for a growing global population requires innovative strategies to optimize environmentally friendly practices and minimize ecological impacts. Agroecosystems, which integrate agricultural practices with the surrounding environment, play a vital role in maintaining ecological balance and ensuring food security. Rhizosphere management has emerged as a pivotal approach to enhancing crop yields, reducing reliance on synthetic fertilizers, and supporting sustainable agriculture. The rhizosphere, a dynamic zone surrounding plant roots, hosts intense microbial activity fueled by root exudates. These exudates, along with practices such as green manure application and intercropping, significantly influence the soil’s microbial community structure. Beneficial plant-associated microbes, including Trichoderma spp., Penicillium spp., Aspergillus spp., and Bacillus spp., play a crucial role in improving nutrient cycling and promoting plant health, yet their interactions within the rhizosphere remain inadequately understood. This review explores how integrating beneficial microbes, green manures, and intercropping enhances rhizosphere processes to rebuild microbial communities, sequester carbon, and reduce greenhouse gas emissions. These practices not only contribute to maintaining soil health but also foster positive plant–microbe–rhizosphere interactions that benefit entire ecosystems. By implementing such strategies alongside sound policy measures, sustainable cropping systems can be developed to address predicted climate challenges. Strengthening agroecosystem resilience through improved rhizosphere processes is essential for ensuring food security and environmental sustainability in the future. In conclusion, using these rhizosphere-driven processes, we could develop more sustainable and resilient agricultural systems that ensure food security and environmental preservation amidst changing climate situations. Full article

Lung cancer is the leading cause of cancer-related deaths worldwide, and delayed detection contributes to poor outcomes. Primary care plays a crucial role in early diagnosis, but detecting lung cancer early remains challenging for general practitioners (GPs). Therefore, the aim of this scoping review was to identify optimal strategies and pathways for lung cancer screening (LCS) in primary care settings globally. We conducted a scoping review by searching PubMed, Scopus, and the Cochrane Library for relevant studies published in the past 10 years. Our keywords included “lung cancer”, “primary care”, “early detection”, “screening”, “best practices”, and “pathways”. We included randomized controlled trials, cross-sectional studies, and cohort studies focused on lung cancer screening in primary care. We extracted data on study characteristics, screening pathways, and key findings. We identified 18 studies that met our inclusion criteria. Important strategies for LCS included the use of shared decision-making tools, electronic health record (HER) prompts, risk prediction models, community outreach, and integration with smoking cessation programs. Barriers to implementation included the lack of provider familiarity with guidelines, time constraints, and patient factors. Healthcare professionals and policy makers in primary care settings can leverage this information to integrate the most effective screening strategies into their care, thus enhancing early detection rates and subsequently reducing global lung cancer morbidity and mortality. Full article

Background/Objectives: Health and social care systems around the globe are currently undergoing a transformation towards personalized, preventive, predictive, participative precision medicine (5PM), considering the individual health status, conditions, genetic and genomic dispositions, etc., in personal, social, occupational, environmental, and behavioral contexts. This transformation is strongly supported by technologies such as micro- and nanotechnologies, advanced computing, artificial intelligence, edge computing, etc. Methods: To enable communication and cooperation between actors from different domains using different methodologies, languages, and ontologies based on different education, experiences, etc., we have to understand the transformed health ecosystem and all its components in terms of structure, function and relationships in the necessary detail, ranging from elementary particles up to the universe. In this way, we advance design and management of the complex and highly dynamic ecosystem from data to knowledge level. The challenge is the consistent, correct, and formalized representation of the transformed health ecosystem from the perspectives of all domains involved, representing and managing them based on related ontologies. The resulting business viewpoint of the real-world ecosystem must be interrelated using the ISO/IEC 21838 Top Level Ontologies standard. Thereafter, the outcome can be transformed into implementable solutions using the ISO/IEC 10746 Open Distributed Processing Reference Model. Results: The model and framework for this system-oriented, architecture-centric, ontology-based, policy-driven approach have been developed by the first author and meanwhile standardized as ISO 23903 Interoperability and Integration Reference Architecture. The formal representation of any ecosystem and its development process including examples of practical deployment of the approach, are presented in detail. This includes correct systems and standards integration and interoperability solutions. A special issue newly addressed in the paper is the correct and consistent formal representation Conclusions: of all components in the development process, enabling interoperability between and integration of any existing representational artifacts such as models, work products, as well as used terminologies and ontologies. The provided solution is meanwhile mandatory at ISOTC215, CEN/TC251 and many other standards developing organization in health informatics for all projects covering more than just one domain. Full article

The widespread propagation of wireless communication devices, from smartphones and tablets to Internet of Things (IoT) systems, has become an integral part of modern life. However, the expansion of wireless technology has also raised public concern about the potential health risks associated with prolonged exposure to electromagnetic fields. Our objective is to determine the optimal machine learning model for constructing electric field strength maps across urban areas, enhancing the field of environmental monitoring with the aid of sensor-based data collection. Our machine learning models consist of a novel and comprehensive dataset collected from a network of strategically placed sensors, capturing not only electromagnetic field readings but also additional urban features, including population density, levels of urbanization, and specific building characteristics. This sensor-driven approach, coupled with explainable AI, enables us to identify key factors influencing electromagnetic exposure more accurately. The integration of IoT sensor data with machine learning opens the potential for creating highly detailed and dynamic electromagnetic pollution maps. These maps are not merely static snapshots; they offer researchers the ability to track trends over time, assess the effectiveness of mitigation efforts, and gain a deeper understanding of electromagnetic field distribution in urban environments. Through the extensive dataset, our models can yield highly accurate and dynamic electric field strength maps. For this study, we performed a comprehensive analysis involving 566 machine learning models across eight French cities: Lyon, Saint-Étienne, Clermont-Ferrand, Dijon, Nantes, Rouen, Lille, and Paris. The analysis incorporated six core approaches: k-Nearest Neighbors, XGBoost, Random Forest, Neural Networks, Decision Trees, and Linear Regression. The findings underscore the superior predictive capabilities of ensemble methods such as Random Forests and XGBoost, which outperform individual models. Simpler approaches like Decision Trees and k-NN offer effective yet slightly less precise alternatives. Neural Networks, despite their complexity, highlight the potential for further refinement in this application. In addition, our results show that the machine learning models significantly outperform the linear regression baseline, demonstrating the added value of more complex techniques in this domain. Our SHAP analysis reveals that the feature importance rankings in tree-based machine learning models differ significantly from those in k-NN, neural network, and linear regression models. Full article

Abstract: To improve the silage quality of Lotus corniculatus L. and expedite the promotion of cultivated varieties, this study investigates the impact of Lactiplantibacillus plantarum on the fermentation characteristics, bacterial community, and functional aspects of silage. The experiment included a control (CK) and a Lactiplantibacillus plantarum (LP) treatment, with sampling conducted at 3, 7, 15, and 45 days of fermentation to monitor nutritional value and fermentation quality, as well as changes in the bacterial community at 3 and 45 days. The results indicated that compared to the CK, the addition of LP significantly increased the lactic acid, dry matter, and crude protein content (p < 0.05) while substantially decreasing the water-soluble carbohydrates, pH, NH₃-N, and acetic acid levels (p < 0.05). And the effect of adding LP was the most significant after 45 days of fermentation. LP promoted the growth of beneficial bacteria and inhibited harmful bacteria, with LP becoming the predominant genus and species after 45 days of fermentation. The metabolic pathway analysis revealed that the addition of LP enhanced carbohydrate metabolism and improved the replication and repair, translation, transcription, and membrane transport functions of the bacterial community. In summary, the addition of LP significantly enhances the silage quality of L. corniculatus and may serve as an effective method for promoting the application of L. corniculatus in karst regions. Full article

This study aimed to investigate the effects of different storage times of the mixed inoculum on in vitro rumen fermentation characteristics, microbial diversity, and community composition. The experiment was divided into five groups, with mixed inoculum composed of fresh rumen fluid and culture medium being stored at 39 °C for 0 h (H0), 12 h (H12), 24 h (H24), 36 h (H36), and 48 h (H48). After 48 h of in vitro fermentation, the fermentation fluid was collected to assess rumen fermentation characteristics and microbial community composition. The H24 group showed higher total gas production, ammoniacal nitrogen levels, and total volatile fatty acids, as well as higher concentrations of individual volatile fatty acids except propionate, compared to the H0 and H48 groups (p < 0.05). The Shannon and Simpson evenness indices were significantly higher in the H0, H12, and H24 groups than in the H48 group (p < 0.05). A total of nine phyla and sixteen genera involved in starch and fiber degradation were found to be more abundant in the H24 or H48 groups (p < 0.05). Moreover, nine predicted metabolic pathways were observed to be significantly enriched in either the H24 or H48 group (p < 0.05). Both principal coordinates analysis (PCoA) and non-metric multidimensional scaling (NMDS) analysis revealed distinct clustering patterns among the H0, H12, H24, H36, and H48 groups, and analysis of similarities (ANOSIM) confirmed these significant differences (R = 1.00, p < 0.05). This study demonstrates that the storage time of mixed inoculum influences rumen fermentation characteristics and microbial community composition in a time-dependent manner. It is recommended to use a mixed inoculum that has been stored within 24 h in an anaerobic environment at 39 °C for in vitro rumen fermentation tests. This study offers valuable microbial insights into the storage strategies for mixed inoculum, thereby improving the methodologies for variable control in in vitro rumen fermentation techniques. Full article

There is an increasing number of studies concerned with the study of children with autism spectrum disorder (ASD). At the same time, there is a lack of interest in studies on their families, especially on mothers who represent the first breadwinner for a child who suffers from a deficit in social communication with others, reflected in their well-being (PWB). This study aimed to reveal the possibility of predicting the PWB of autistic spectrum children’s mothers through the variables of coping strategies and psychological capital (PsyCap). The study used a predictive, descriptive research method to reveal the ability of the variables—coping strategies (problem-solving, avoidance, support, re-evaluation, remorse) and PsyCap (self-efficacy, optimism, hope, and resilience)—in predicting the PWB of autistic spectrum children’s mothers. The study sample consisted of (248) mothers, to whom coping strategies, PsyCap, and PWB measures were applied. The results showed that there were statistically significant differences between working and housewife mothers of autistic spectrum children in solving problems (t = 3.162, p < 0.002), avoidance (t = 1.973, p < 0.05), positive coping (t = 2.307, p < 0.022), self-efficacy (t = 3.667, p < 0.000), resilience (t = 3.338, p < 0.001), PsyCap (t = 2.866, p < 0.005), and PWB (t = 2.549, p < 0.011). Meanwhile, there were no statistically significant differences in social support, problem reassessment, remorse, negative coping, optimism, and hope. Also, there were no statistically significant differences due to the number of children in coping strategies, PsyCap, and PWB. The results also showed that there were statistically significant differences at the level of significance (0.05) between mothers whose age was less than 40 years and those 40 years and older in solving problems (t = 2.093, p < 0.037) in favor of mothers of the age group 40 years and older (M = 22.00, SD = 1.22), and avoidance (t = 1.987, p < 0.048) in favor of mothers under 40 years of age (M = 6.228, SD = 0.464). However, there were no statistically significant differences in social support, problem reassessment, remorse, positive coping, negative coping, self-efficacy, optimism, hope, resilience, the total degree of PsyCap, and well-being due to the variable of the mother’s age. The regression analysis results showed that optimism and problem-solving contributed to (39.90%) of the total change in PWB for mothers of children with autism spectrum. The study’s findings indicate the need to develop the ability of autistic spectrum children’s mothers to solve problems and their PsyCap, which is represented in self-efficacy, optimism, hope, and resilience, to enhance their PWB, which may have a positive impact on their autistic spectrum child. Full article

Unmanned aerial vehicle (UAV)-enabled vehicular communications in the sixth generation (6G) are characterized by line-of-sight (LoS) and dynamically varying channel conditions. However, the presence of obstacles in the LoS path leads to shadowed fading environments. In UAV-assisted cellular vehicle-to-everything (C-V2X) communication, vehicle and UAV mobility and shadowing adversely impact latency and throughput. Moreover, 6G vehicular communications comprise data-intensive applications such as augmented reality, mixed reality, virtual reality, intelligent transportation, and autonomous vehicles. Since vehicles’ sensors generate immense amount of data, the latency in processing these applications also increases, particularly when the data are not independently identically distributed (non-i.i.d.). Furthermore, when the sensors’ data are heterogeneous in size and distribution, the incoming packets demand substantial computing resources, energy efficiency at the UAV servers and intelligent mechanisms to queue the incoming packets. Due to the limited battery power and coverage range of UAV, the quality of service (QoS) requirements such as coverage rate, UAV flying time, and fairness of vehicle selection are adversely impacted. Controlling the UAV trajectory so that it serves a maximum number of vehicles while maximizing battery power usage is a potential solution to enhance QoS. This paper investigates the system performance and communication disruption between vehicles and UAV due to Doppler effect in the orthogonal time–frequency space (OTFS) modulated channel. Moreover, a low-complexity UAV trajectory prediction and vehicle selection method is proposed using federated learning, which exploits related information from past trajectories. The weighted total energy consumption of a UAV is minimized by jointly optimizing the transmission window ($L_w$), transmit power and UAV trajectory considering Doppler spread. The simulation results reveal that the weighted total energy consumption of the OTFS-based system decreases up to 10% when combined with federated learning to locally process the sensor data at the vehicles and communicate the processed local models to the UAV. The weighted total energy consumption of the proposed federated learning algorithm decreases by 10–15% compared with convex optimization, heuristic, and meta-heuristic algorithms. Full article

The Internet of Things (IoT) is transforming industries by integrating sensors and connectivity into everyday objects, enabling enhanced monitoring, management, and automation through Machine-to-Machine (M2M) communication. Despite these advancements, the IoT faces limitations in accurately predicting environmental conditions and power consumption. This study proposes an advanced IoT platform that combines real-time data collection with secure transmission and forecasting using a hybrid Long Short-Term Memory (LSTM)–Gated Recurrent Unit (GRU) model. The hybrid architecture addresses the computational inefficiencies of LSTM and the short-term dependency challenges of GRU, achieving improved accuracy and efficiency in time-series forecasting. For all prediction use cases, the model achieves a Maximum Mean Absolute Error (MAE) of 3.78%, Root Mean Square Error (RMSE) of 8.15%, and a minimum $R^2$ score of 82.04%, the showing proposed model’s superiority for real-life use cases. Furthermore, a comparative analysis also shows the performance of the proposed model outperforms standalone LSTM and GRU models, enhancing the IoT’s reliability in real-time environmental and power forecasting. Full article

Background: Soil microbes play a vital role in the ecosystem as they are able to carry out a number of vital tasks. Additionally, metagenomic studies offer valuable insights into the composition and functional potential of soil microbial communities. Furthermore, analyzing the obtained data can improve agricultural restoration practices and aid in developing more effective environmental management strategies. Methodology: In November 2023, sandy soil samples were collected from ten sites of different geographical areas surrounding natural lakes and artificial water points in the Tubaiq conservation area of King Salman Bin Abdulaziz Royal Natural Reserve (KSRNR), Saudi Arabia. In addition, genomic DNA was extracted from the collected soil samples, and 16S rRNA sequencing was conducted using high-throughput Illumina technology. Several computational analysis tools were used for gene prediction and taxonomic classification of the microbial groups. Results: In this study, sandy soil samples from the surroundings of natural and artificial water resources of two distinct natures were used. Based on 16S rRNA sequencing, a total of 24,563 OTUs were detected. The metagenomic information was then categorized into 446 orders, 1036 families, 4102 genera, 213 classes, and 181 phyla. Moreover, the phylum Pseudomonadota was the most dominant microbial community across all samples, representing an average relative abundance of 34%. In addition, Actinomycetes was the most abundant class (26%). The analysis of clustered proteins assigned to COG categories provides a detailed understanding of the functional capabilities and adaptation of microbial communities in soil samples. Amino acid metabolism and transport were the most abundant categories in the soil environment. Conclusions: Metagenome analysis of sandy soils surrounding natural lakes and artificial water points in the Tubaiq conservation area of KSRNR (Saudi Arabia) has unveils rich microbial activity, highlighting the complex interactions and ecological roles of microbial communities in these environments. Full article