Search Results (7,271)

Recurrent neural networks (RNNs) have produced significant results in many fields, such as natural language processing and speech recognition. Owing to their computational complexity and sequence dependencies, RNNs need to be deployed on customized hardware accelerators to satisfy performance and energy-efficiency constraints. However, designing hardware accelerators for RNNs is challenged by the vast design space and the reliance on ineffective optimization. An efficient automated design space exploration (DSE) strategy that can balance conflicting objectives is wanted. To address the low efficiency and insufficient universality of the resource allocation process employed for hardware accelerators, we propose an automated two-stage design space exploration (DSE) strategy for customized RNN accelerators. The strategy combines a genetic algorithm (GA) and a reinforcement learning (RL) algorithm, and it utilizes symmetrical exploration and exploitation to find the optimal solutions. In the first stage, the area of the hardware accelerator is taken as the optimization objective, and the GA is used for partial exploration purposes to narrow the design space while maintaining diversity. Then, the latency and power of the hardware accelerator are taken as the optimization objectives, and the RL algorithm is used in the second stage to find the corresponding Pareto solutions. To verify the effectiveness of the developed strategy, it is compared with other algorithms. We use three different network models as benchmarks: a vanilla RNN, LSTM, and a GRU. The results demonstrate that the strategy proposed in this paper can provide better solutions and can achieve latency, power, and area reductions of 9.35%, 5.34%, and 11.95%, respectively. The HV of GRMD is reduced by averages of 6.33%, 6.32%, and 0.67%, and the runtime is reduced by averages of 18.11%, 14.94%, and 10.28%, respectively. Additionally, given different weights, it can make reasonable trade-offs between multiple objectives. Full article

The particle size distribution (PSD) is a crucial parameter used to characterize the material composition of debris-flow deposits which determines their hydraulic permeability, affecting the mobility of debris flows and, hence, the sustainable development of debris-flow fans. Three types of graded bedding structures—normal, reverse, and mixed graded bedding structures—are characterized by discontinuous gradation within a specific deposit thickness. A series of permeability tests were conducted to study the effects of bed sediment composition, particularly coarse grain sizes and fine particle contents, on the permeability and migration of fine particles in discontinuous debris-flow deposits. An increase in fine particles within the discontinuously graded bed sediment led to a power-law decrease in the average permeability coefficient. With fine particle contents of 10% and 15% in the bed sediments, the final permeability coefficient consistently exceeded the initial value. However, this trend reversed when the fine particle contents were increased to 20%, 25%, and 30%. Lower fine particle contents indicated enhanced permeability efficiency due to more interconnected voids within the coarse particle skeleton. Conversely, an increase in fine particle content reduced the permeability efficiency, as fine particles tended to aggregate at the lower section of the seepage channel. An increase in coarse particle size decreased the formation of flow channels at the coarse–fine particle interface, causing fine particles to move slowly along adjacent or clustered slow flow channels formed by fine particles, resulting in decreased permeability efficiency. Three formulae are proposed to calculate the permeability coefficients of discontinuously graded bed sediments, which may aid in understanding the initiation mechanism of channel deposits. Based on experimental studies and field investigations, it is proposed that achieving sustainable development of debris-flow fans requires a practical approach that integrates three key components: spatial land-use planning, in situ monitoring of debris flows and the environment, and land-use adjustment and management. This comprehensive and integrated approach is essential for effectively managing and mitigating the risks associated with debris flows, ensuring sustainable development in vulnerable areas. Full article

This research investigates the energy consumption of buildings managed by traditional Building Management Systems (BMSs) and proposes the integration of Internet of Things (IoT) technology to enhance energy efficiency. Conventional BMSs often suffer from significant energy wastage and safety hazards due to sensor failures or malfunctions. These issues arise when building systems continue to operate under unknown conditions while the BMS is offline, leading to increased energy consumption and operational risks. The study demonstrates that integrating IoT systems with existing BMSs can substantially improve energy efficiency in smart buildings. The research involved designing a system architecture prototype, performing MATLAB simulations, and a real-life case study which revealed that IoT devices are effective in reducing energy waste, particularly in Heating, Ventilation, and Air Conditioning (HVAC) systems and lighting. Additionally, an auxiliary bypass system was incorporated in parallel with the IoT system to enhance reliability in the event of IoT system failures. Preliminary findings indicate that the integration of IoT systems with traditional BMSs significantly boosts energy efficiency and safety in smart buildings. Simulation results reveal an hourly average power savings of 36.8 kw with the integrated failsafe model for all scenarios. This integration offers a promising solution for advancing energy management practices and policies, thereby improving both operational performance and sustainability in building management. Full article

The selection of the optimal 35 kV network structure is crucial for modern distribution networks. To address the problem of balancing investment costs and reliability benefits, as well as to establish the target network structure, firstly, the investment cost of the distribution network is calculated based on the determined number of network structure units. Secondly, reliability benefits are measured by combining the comprehensive function of user outage losses with the System Average Interruption Duration Index (SAIDI). Then, a multi-objective planning model of the network structure is established, and the weighted coefficient transformation method is used to convert reliability benefits and investment costs into the total cost of power supply per unit load. Finally, by using the influencing factors of the network structure as the initial population and setting the minimum total cost of the unit load as the fitness function, the DE algorithm is employed to obtain the optimal grid structure under continuous load density intervals. Case studies demonstrate that different load densities correspond to different optimal network structures. For load densities ranging from 0 to 30, the selected optimal network structures from low to high are as follows: overhead single radial, overhead three-section with two ties, cable single ring network, and cable dual ring network. Full article

Load-side peak shaving is an effective measure to alleviate power supply–demand imbalance. As a key link between a vast array of small- and medium-sized adjustable resources and the bulk power system, load aggregators (LAs) typically allocate peak shaving budgets using fixed pricing methods based on peak shaving demand forecasts. However, due to the randomness of supply and demand, fluctuations in peak shaving demand occur, making it a significant technical challenge to meet peak shaving needs under limited budget allocations. To address this issue, this paper first conducts a clustering analysis of various adjustable load characteristics to derive typical electricity consumption curves, and then proposes a differentiated calculation method for the value of multi-time-segment peak shaving. Subsequently, an optimization model for LA scheduling and compensation pricing is established based on the limited peak shaving budget and time-segment peak shaving value. While ensuring the economic benefits of LAs, the model also analyzes the impact of different peak shaving budget allocations on the scale of peak shaving that can be achieved. Finally, case studies demonstrate that, compared to traditional fixed compensation pricing, the proposed pricing method reduces scheduling costs by an average of 16.5%, while significantly improving the overall satisfaction of adjustable users. Full article

This study investigates the impact of rotor structure, material selection, and cooling methods on ultra-high-speed motor performance, revealing performance variation laws under multi-physical field coupling. Considering mechanical boundary constraints, we propose an optimization design method based on a multi-physical field coupling model. Using a MaxPro experimental design, initial samples are obtained and fitted using a Kriging surrogate model. The NSGA-2 algorithm is then applied for optimization, with Relative Maximum Absolute Error (RMAE) and Relative Average Absolute Error (RAAE) employed for accuracy evaluation. The Kriging model is iteratively updated based on evaluation results until the optimal design is achieved. This method enhances motor performance, ensures mechanical boundary conditions, and reduces computational load. Experimental results show significant improvements in efficiency and power density. This study provides theoretical support and technical guidance for ultra-high-speed motor design and offers new ideas for related motor research and development. Future work will explore more efficient and intelligent optimization algorithms to continuously advance ultra-high-speed motor technology. Full article

This paper aims to examine the physical layer security (PLS) performance of a reconfigurable intelligent surface (RIS)-aided wiretap multiple-input single-output (MISO) system over generalized fading conditions by assuming inherent phase shift errors at the RIS. Specifically, the procedures (i.e., the method) to conduct this research is based on learning-based approaches to model the magnitude of the end-to-end RIS channel, i.e., employing an unsupervised expectation-maximization (EM) approach via a finite mixture of Nakagami-m distributions. This general framework allows us to accurately approximate key practical factors in RIS’s channel modeling, such as generalized fading conditions, spatial correlation, discrete phase shift, beamforming, and the presence of direct and indirect links. For the numerical results, the secrecy outage probability, the average secrecy rate, and the average secrecy loss under different setups of RIS-aided wireless systems are assessed by varying the fading parameters of the N-wave with a diffuse power fading channel model. The results show that the correlation between RIS elements and unfavorable channel conditions (e.g., Rayleigh) affect secrecy performance. Likewise, it was confirmed that the use of a RIS is not essential when there is a solid line-of-sight link between the transmitter and the legitimate receiver. Full article

Leak detection in oil and gas pipeline networks is a climacteric and frequent issue in the oil and gas field. Many establishments have long depended on stationary hardware or traditional assessments to monitor and detect abnormalities. Rapid technological progress; innovation in engineering; and advanced technologies providing cost-effective, rapidly executed, and easy to implement solutions lead to building an efficient oil pipeline leak detection and real-time monitoring system. In this area, wireless sensor networks (WSNs) are increasingly required to enhance the reliability of checkups and improve the accuracy of real-time oil pipeline monitoring systems with limited hardware resources. The real-time transient model (RTTM) is a leak detection method integrated with LoRaWAN technology, which is proposed in this study to implement a wireless oil pipeline network for long distances. This study will focus on enhancing the LoRa network parameters, e.g., node power consumption, average packet loss, and delay, by applying several machine learning techniques in order to optimize the durability of individual nodes’ lifetimes and enhance total system performance. The proposed system is implemented in an OMNeT++ network simulator with several frameworks, such as Flora and Inet, to cover the LoRa network, which is used as the system’s network infrastructure. In order to implement artificial intelligence over the FLoRa network, the LoRa network was integrated with several programming tools and libraries, such as Python script and the TensorFlow libraries. Several machine learning algorithms have been applied, such as the random forest (RF) algorithm and the deep extreme learning machine (DELM) technique, to develop the proposed model and improve the LoRa network’s performance. They improved the LoRa network’s output performance, e.g., its power consumption, packet loss, and packet delay, with different enhancement ratios. Finally, a hybrid deep extreme learning machine model was built and selected as the proposed model due to its ability to improve the LoRa network’s performance, with perfect prediction accuracy, a mean square error of 0.75, and an exceptional enhancement ratio of 39% for LoRa node power consumption. Full article

Agricultural greenhouses (AGs) are an effective solution to address the growing demand for vegetables despite limited cropland, yet significant soil quality problems often accompany them, particularly in high-altitude regions. However, the effects of natural factors and production management on soil quality are not well understood in such fragile environments. This study analyzed soil quality differences between AGs and adjacent open cropland (OCs) in the Lhasa River Valley, Tibetan Plateau, based on 592 soil samples and 12 key soil physicochemical indicators. GeoDetector was used to identify the dominant factors and their interactions with these differences. The results showed that AG soils had significantly lower pH, with an average decrease of 20%, indicating acidification, while nutrient levels and total salinity were significantly higher compared to OC soils. Specifically, available phosphorus, available potassium, the soil fertility quality index, and total soluble salt increased by 281%, 102%, 38%, and 184%, respectively. Planting, topographic, and fertilizer factors were identified as the dominant factors contributing to these differences. Interaction analysis showed that the interaction of these factors increased the explanatory power by 20.2% to 41.32% compared to individual factors. The interaction between planting year and fertilizer type had the highest explanatory power for nutrient increases and pH decline, while fertilizer amount and slope aspect contributed to salinity accumulation. These findings provide valuable insights and practical guidance for optimizing AG management and ensuring sustainable agricultural development in high-altitude regions. Full article

The aim of this article is to analyse the global environmental impact of wind farms, i.e., the effects on human health and the local ecosystem. Compared to conventional energy sources, wind turbines emit significantly fewer greenhouse gases, which helps to mitigate global warming. During the life cycle of a wind farm, 86% of CO₂ emissions are generated by the extraction of raw materials and the manufacture of wind turbine components. The water consumption of wind farms is extremely low. In the operational phase, it is 4 L/MWh, and in the life cycle, one water footprint is only 670 L/MWh. However, wind farms occupy a relatively large total area of 0.345 ± 0.224 km²/MW of installed capacity on average. For this reason, wind farms will occupy more than 10% of the land area in some EU countries by 2030. The impact of wind farms on human health is mainly reflected in noise and shadow flicker, which can cause insomnia, headaches and various other problems. Ice flying off the rotor blades is not mentioned as a problem. On a positive note, the use of wind turbines instead of conventionally operated power plants helps to reduce the emission of particulate matter 2.5 microns or less in diameter (PM 2.5), which are a major problem for human health. In addition, the non-carcinogenic toxicity potential of wind turbines for humans over the entire life cycle is one of the lowest for energy plants. Wind farms can have a relatively large impact on the ecological system and biodiversity. The destruction of animal migration routes and habitats, the death of birds and bats in collisions with wind farms and the negative effects of wind farm noise on wildlife are examples of these impacts. The installation of a wind turbine at sea generates a lot of noise, which can have a significant impact on some marine animals. For this reason, planners should include noise mitigation measures when selecting the site for the future wind farm. The end of a wind turbine’s service life is not a major environmental issue. Most components of a wind turbine can be easily recycled and the biggest challenge is the rotor blades due to the composite materials used. Full article

Despite its flexibility, unmanned aerial vehicle (UAV) communications are susceptible to eavesdropping due to the open nature of wireless channels and the broadcasting nature of wireless signals. This paper studies secure UAV communications and proposes a method to optimize the minimum secrecy rate of the system by using interference technology to enhance it. To this end, the system not only deploys multiple UAV base stations (BSs) to provide services to legitimate users but also assigns dedicated UAV jammers to send interference signals to active or potential eavesdroppers to disrupt their eavesdropping effectiveness. Based on this configuration, we formulate the optimization process of parameters such as the user association variables, UAV trajectory, and output power as a sequential decision-making problem and use the single-agent soft actor-critic (SAC) algorithm and twin delayed deep deterministic policy gradient (TD3) algorithm to achieve joint optimization of the core parameters. In addition, for specific scenarios, we also use the multi-agent soft actor-critic (MASAC) algorithm to solve the joint optimization problem mentioned above. The numerical results show that the normalized average secrecy rate of the MASAC algorithm increased by more than 6.6% and 14.2% compared with that of the SAC and TD3 algorithms, respectively. Full article

Objectives: The PROtein-enriched MEDiterranean diet to combat undernutrition and promote healthy neuroCOGnitive ageing in older adults (PROMED-COG) is a European project that investigates the role of nutritional status on neurocognitive ageing. This methodological paper describes the harmonization process of dietary data from four Italian observational studies (Pro.V.A., ILSA, BEST-FU, and NutBrain). Methods: Portion sizes and food frequency consumption within different food frequency questionnaires were retrospectively harmonized across the datasets on daily food frequency, initially analyzing raw data using the original codebook and establishing a uniform food categorization system. Individual foods were then aggregated into 27 common food groups. Results: The pooled cohort consisted of 9326 individuals (40–101 years, 52.4% female). BEST-FU recruited younger participants who were more often smokers and less physically active than those of the other studies. Dietary instruments varied across the studies differing in the number of items and time intervals assessed, but all collected dietary intake through face-to-face interviews with a common subset of items. The average daily intakes of the 27 food groups across studies varied, with BEST-FU participants generally consuming more fruits, vegetables, red meat, and fish than the other studies. Conclusions: Harmonization of dietary data presents challenges but allows for the integration of information from diverse studies, leading to a more robust and statistically powerful dataset. The study highlights the feasibility and benefits of data harmonization, despite inherent limitations, and sets the stage for future research into the effects of diet on cognitive health and aging. Full article

Hydroelectric power is one of the most important renewable energy sources in the world. It currently generates more electricity than all other renewable technologies combined and, according to the International Energy Agency, it is expected to remain the world’s largest source of renewable electricity generation into the 2030s. Thus, despite the increasing focus on more recent energy technologies, such as solar and wind power, it will continue to play a critical role in energy transition. The management of hydropower plants and future planning should be ensured through careful planning based on the suitable forecasting of the future of this energy source. Starting from these considerations, in this paper, we examine the evolution of hydropower with a forecasting analysis for a selected group of countries. We analyze the time-series data of hydropower generation from 1965 to 2023 and apply Innovation Diffusion Models, as well as other models such as Prophet and ARIMA, for comparison. The models are evaluated for different geographical regions, namely the North, South, and Central American countries, the European countries, and the Middle East with Asian countries, to determine their effectiveness in predicting trends in hydropower generation. The models’ accuracy is assessed using Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and Mean Absolute Percentage Error (MAPE). Through this analysis, we find that, on average, the GGM outperforms the Prophet and ARIMA models, and is more accurate than the Bass model. This study underscores the critical role of precise forecasting in energy planning and suggests further research to validate these results and explore other factors influencing the future of hydroelectric generation. Full article

Recruitment poses significant challenges for narrow endemic plant species inhabiting extreme environments like vertical cliffs. Investigating seed traits in these plants is crucial for understanding the adaptive properties of chasmophytes. Focusing on the Iberian endemic genus Petrocoptis A. Braun ex Endl., a strophiole-bearing Caryophyllaceae, this study explored the relationships between seed traits and climatic variables, aiming to shed light on the strophiole’s biological role and assess its classificatory power. We analysed 2773 seeds (557 individuals) from 84 populations spanning the genus’ entire distribution range. Employing cluster and machine learning algorithms, we delineated well-defined morphogroups based on seed traits and evaluated their recognizability. Linear mixed-effects models were utilized to investigate the relationship between climate predictors and strophiole area, seed area and the ratio between both. The combination of seed morphometric traits allows the division of the genus into three well-defined morphogroups. The subsequent validation of the algorithm allowed 87% of the seeds to be correctly classified. Part of the intra- and interpopulation variability found in strophiole raw and relative size could be explained by average annual rainfall and average annual maximum temperature. Strophiole size in Petrocoptis could have been potentially driven by adaptation to local climates through the investment of more resources in the production of bigger strophioles to increase the hydration ability of the seed in dry and warm climates. This reinforces the idea of the strophiole being involved in seed water uptake and germination regulation in Petrocoptis. Similar relationships have not been previously reported for strophioles or other analogous structures in Angiosperms. Full article

Background and Objectives: Soccer is a sport characterized by various unpredictable situations in which physical abilities are associated with athletic performance. There are several capabilities that young soccer players must develop to adapt to the needs of the competition. This study analyzes the physical characteristics, tactical knowledge, emotional intelligence, and mood states of youth soccer players at different competitive levels. Materials and Methods: The sample consisted of 36 male soccer players with an average age of 12.65 ± 0.48 years, weight of 44.92 ± 7.49 kg, and height of 157.2 ± 0.08 cm. A cross-sectional correlational study design was selected. Inferential analysis was conducted via the RV coefficient to assess relationships between groups. Two-sample tests (Student’s t test or the Mann–Whitney U test) were used to assess the distribution of the samples. Standardized mean differences (i.e., Cohen’s d) were calculated as effect sizes. Results: For the yo-yo intermittent endurance test level 1, the Premier category showed higher speed (p = 0.01, d = 0.40) and superior estimated VO_2max (p = 0.01, d = −0.91). The statistically significant variables included the hamstring strength exercise of the hamstrings for the angle of rupture (p = 0.04, d = −0.04, d = −0.72), the COD-Timer 5-0-5 for contact time—5-0-5 (ms) (p = 0.04, d = 0.69) and 10 m—5-0-5 (s) (p = 0.02, d = 0.79), tactical knowledge of in-game performance (p = 0.01, d = −1.19), support level (p = 0.01, d = −1.27), decision-making ability (p = 0.01, d = 0.59), melancholy (p = 0.01, d = 0.59), confusion (p = 0.01, d = 0.56), and emotional intelligence (p = 0.04, d = 0.77). The Premier category presented slightly higher averages than did category A. In the assessment of running-based anaerobic sprint test power (p < 0.05, d = 0.83) and mood states (p < 0.05, d = 0.59), players in category A presented higher results. Conclusions: The performance capacity of youth soccer players encompasses a multidimensional complexity that includes physical, tactical, emotional, and psychological aspects, which vary among players of the same age. Full article