Search Results (7,303)

Neural networks (NNs) have proven their ability to deal with many computer vision tasks, including image-based remote sensing such as the identification and segmentation of hyperspectral images captured by satellites. Often, NNs run on a ground system upon receiving the data from the satellite. On the one hand, this approach introduces a considerable latency due to the time needed to transmit the satellite-borne images to the ground station. On the other hand, it allows the employment of computationally intensive NNs to analyze the received data. Low-budget missions, e.g., CubeSat missions, have computation capability and power consumption requirements that may prevent the deployment of complex NNs onboard satellites. These factors represent a limitation for applications that may benefit from a low-latency response, e.g., wildfire detection, oil spill identification, etc. To address this problem, in the last few years, some missions have started adopting NN accelerators to reduce the power consumption and the inference time of NNs deployed onboard satellites. Additionally, the harsh space environment, including radiation, poses significant challenges to the reliability and longevity of onboard hardware. In this review, we will show which hardware accelerators, both from industry and academia, have been found suitable for onboard NN acceleration and the main software techniques aimed at reducing the computational requirements of NNs when addressing low-power scenarios. Full article

Global food demand is rising, leading to increased food waste, which contains underutilized bioactive compounds. The Pressurized Liquid Extraction (PLE) method employs high temperature and pressure to maintain the solvent in a liquid state above its boiling point, thereby minimizing extraction time and solvent usage. Ginger waste is known to contain bioactive compounds with significant antioxidant activity. We aimed to assess the effect of temperature, time, and particle size on the total phenolic content (TPC) and antioxidant activity (AA) of ginger (Zingiber officinale R.) waste aqueous extract using the PLE method. A Box–Behnken design with 16 runs was employed. Each extraction utilized 40 g of the sample and was conducted at a constant pressure of 20 bar with a solvent ratio of 27:1 mL/g. Data analysis was performed with Minitab^® 19.1 (64-bit). TPC ranged from 10.42 to 14.1 mg GAE/g, and AA ranged from 72.9 to 111.9 μmol TE/g. The model explained 81.07% of AA’s total variability. Positive correlation was found between TPC and AA (Pearson’s ρ = 0.58, p < 0.05). The optimized extraction conditions were a temperature of 126 °C, an extraction time of 38 min, and a particle size between 355 and 500 μm. Temperature significantly influenced AA (p < 0.05), while time and particle size were not significant factors. To enhance future research, conducting nutritional and functional studies on the extracted compounds would provide valuable insights. Lastly, evaluating the economic feasibility of using PLE for ginger waste valorization should be considered to support its commercial application. Full article

At present, raising caged chickens is a common farming method in China. However, monitoring the status of caged chickens is still done by human labor, which is time-consuming and laborious. This paper proposed a posture detection method for caged chickens based on computer vision, which can automatically identify the standing and lying posture of chickens in a cage. For this aim, an image correction method was used to rotate the image and make the feeding trough horizontal in the image. The variance method and the speeded-up robust features method were proposed to identify the feeding trough and indirectly obtain the key area through the feeding trough position. In this paper, a depth camera was used to generate three-dimensional information so that it could extract the chickens from the image of the key area. After some constraint conditions, the chickens’ postures were screened. The experimental results show that the algorithm can achieve 97.80% precision and 80.18% recall (IoU > 0.5) for white chickens and can achieve 79.52% precision and 81.07% recall (IoU > 0.5) for jute chickens (yellow and black feathers). It runs at ten frames per second on an i5-8500 CPU. Overall, the results indicated that this study provides a non-invasive method for the analysis of posture in caged chickens, which may be helpful for future research on poultry. Full article

This study investigated the impact of six high-intensity interval training (HIIT) running sessions on 1% or 10% slopes on various physiological and performance parameters in 25 men. The participants underwent assessments of VO_2max, time to exhaustion on 1% slope (TLim1%), and time to exhaustion on 10% slope (TLim10%) in the initial three visits. They were then randomly assigned to control (CON), HIIT on 1% slope (GT1%), or HIIT on 10% slope (GT10%) groups. Over three weeks, participants performed six HIIT sessions with equalized workload based on their individual maximal oxygen uptake (vVO_2max). The sessions comprised 50% of TLim, with a 1:1 ratio of exercise to recovery at 50% vVO_2max. The results indicated significant improvements in VO_2max and peak velocity (VPeak) after HIIT on both slopes. Heart rate (HR) differed between sessions for GT1%, while no significant differences were observed for GT10%. Ratings of perceived exertion (RPE) were significantly reduced for GT1% after the third session, with a similar trend for GT10%. In summary, six HIIT sessions on a 1% or 10% slope effectively enhanced VO_2max and VPeak, but there was no improvement in TLim performance, suggesting no adaptive transfer between training groups. Full article

In dynamic scenarios, the status of a Radio Frequency Identification (RFID) system fluctuates with environmental changes. The key to improving system efficiency lies in the real-time monitoring and evaluation of the system status, along with adaptive adjustments to the system parameters and read algorithms. This paper focuses on the status changes in RFID systems in dynamic scenarios, aiming to enhance system robustness and reading performance, ensuring high link quality, reasonable resource scheduling, and real-time status evaluation under varying conditions. This paper comprehensively considers the system parameter settings in dynamic scenarios, integrating the interaction model between readers and tags. The system’s real-time status is evaluated from both the physical layer and the Medium Access Control (MAC) layer perspectives. For the physical layer, a link quality evaluation model based on Uniform Manifold Approximation and Projection (UMAP) and K-Means clustering is proposed from the link quality. For the MAC layer, a multi-criteria decision-making evaluation model based on combined weighting and the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) is proposed, which comprehensively considers both subjective and objective factors, utilizing the TOPSIS algorithm for an accurate evaluation of the MAC layer system status. For the RFID system, this paper proposes a real-time status evaluation model based on the Classification and Regression Tree (CART), which synthesizes the evaluation results of the physical layer and MAC layer. Finally, engineering tests and verification were conducted on the RFID robot system in mobile scenarios. The results showed that the clustering average silhouette coefficient of the physical layer link quality evaluation model based on K-Means was 0.70184, indicating a relatively good clustering effect. The system status evaluation model of the MAC layer, based on the combined weighting-TOPSIS method, demonstrated good flexibility and generalization. The real-time status evaluation model of the RFID system, based on CART, achieved a classification accuracy of 98.3%, with an algorithm runtime of 0.003 s. Compared with other algorithms, it had a higher classification accuracy and shorter runtime, making it well suited for the real-time evaluation of the RFID robot system’s status in dynamic scenarios. Full article

The poor timeliness of routing has always been an urgent problem in practical operator networks, especially in situations with large-scale networks and multiple network domains. In this article, a pruning idea of routing integrated with Dijkstra’s shortest path searching is utilized to accelerate the process of routing in large-scale multi-domain elastic optical networks (EONs). The layered-graph approach is adopted in the spectrum allocation stage. To this end, an efficient heuristic algorithm is proposed, called “Branch-and-Bound based Routing and Layered Graph based Spectrum Allocation algorithm (BBR-LGSA)”, which is an integrated RSA algorithm. Notably, the significant reduction in algorithm time complexity is not only reflected in the pruning method used in the routing stage but also in the construction of auxiliary graphs during the spectrum allocation stage utilizing the Branch-and-Bound method. Simulation results show that the proposed BBR-LGSA significantly reduces the average running time by nearly 78% with higher spectrum utilization in large-scale multi-domain EONs, compared with benchmark algorithms. In addition, the impact of key parameters on performance comparisons of different algorithms is evaluated. Full article

Despite the strong interest concerning the responsive façades, today there are still few built examples and few tools to assess their benefits due to the complex description of the phenomenon. Energy simulations should consider the interactions between a time-varying environment and an environment-dependent envelope, increasing the intricacy of the problem; moreover, these strong environment–envelope interlinkages increase the importance of the location and climate scenarios considered. The aim of this study is to provide a tool to easily model these phenomena in different geographical and climate contexts. For this purpose, an innovative interactive computational platform (ICP) was developed based on EnergyPlus as a simulation engine, Python as a simulation manager, and Grasshopper as a user interface. Thanks to a single user-friendly environment, the users can simply select the climate scenario, the location, the responsive technology, and its main properties to set and run the dynamic energy simulation. After an overview of the current state of the art, this study provides a description of the structure and workflow adopted for developing this platform and details regarding its functioning and input management. Finally, the platform was tested to run an evolutionary optimization of an electrochromic window control strategy in different climate scenarios. Full article

This study examines the relationship between CO₂ emissions, labor force participation, foreign direct investment (FDI), and trade openness on the Consumer Price Index (CPI) in Saudi Arabia, within the context of Vision 2030’s economic reforms. Vision 2030 aims to diversify the economy, reduce oil dependency, and promote sustainable growth, making it crucial to understand the factors influencing inflation and economic stability. Using annual data from 2001 to 2022 and the nonlinear Autoregressive Distributed Lag (NARDL) bounds testing approach, the study analyzes both short- and long-term effects. The findings reveal that higher CO₂ emissions have a deflationary effect, reducing the CPI in both the short and long term, while FDI shows an inflationary impact with a delayed effect. Labor force expansion contributes to lowering the CPI, reflecting its deflationary pressure, especially over the long term. Trade openness is also examined for its dual effects on CPI, In the short run, both positive and negative trade openness reduce consumer prices, while in the long run, positive trade openness increases inflation, and negative trade openness lowers prices. This shows the differing inflationary impacts of trade openness over time. These findings contribute to the policy discourse on balancing economic growth, environmental sustainability, and inflation management, offering strategic insights for policymakers in alignment with Saudi Arabia’s Vision 2030 objectives. Full article

This study introduces a novel, robust, and efficient method for the simultaneous quantitative determination of three sunscreen filters, namely, 4-methylbenzylidene camphor, octyl methoxycinnamate, and avobenzone, in a moisturizing sunscreen cream specifically designed for acne-prone skin. The method employs high-performance liquid chromatography with photodiode-array detection, providing a reliable separation of the analytes. Chromatographic separation was achieved using a Fortis Phenyl analytical column (150.0 × 2.1 mm, 5 μm), with isocratic elution at a flow rate of 0.4 mL/min. The mobile phase was composed of a 57/43 (v/v) mixture of acetonitrile/45 mM aqueous ammonium formate solution, ensuring sufficient resolution and peak symmetry for the target compounds. The method was validated comprehensively for critical performance parameters, including linearity, precision, accuracy, and robustness. Linearity was established across a suitable range for all three analytes, with high correlation coefficients. Precision was confirmed with intra-run and total precision coefficients of variation of ≤4.6%, while accuracy assessments yielded a percent recovery between 98.6 and 100.4, for all quality control levels. Additionally, the method was able to effectively separate the sunscreen filters from other cosmetic ingredients, such as [β-(1.3), (1.6)-D-glucan], low molecular weight (LMW) hyaluronic acid and plant extracts ensuring specificity in complex formulations. This straightforward and time efficient sample preparation process, involving methanol extraction followed by serial dilution, makes the method suitable for routine quality control in cosmetic laboratories. The method was successfully applied to the analysis of two different lots of a commercial sunscreen cream, achieving excellent recovery for all filters, ranging between 94.6% and 99.8%, thus demonstrating its reliability and applicability for the quality control of cosmetics. Full article

Airtime is crucial for high-rotation tricks in snowboard halfpipe performance, significantly impacting trick difficulty, the primary judging criterion. This study aims to enhance the detection of take-off and landing events using inertial measurement unit (IMU) data in conjunction with machine learning algorithms since manual video-based methods are too time-consuming. Eight elite German National Team snowboarders performed 626 halfpipe tricks, recorded by two IMUs at the lateral lower legs and a video camera. The IMU data, synchronized with video, were labeled manually and segmented for analysis. Utilizing a 1D U-Net convolutional neural network (CNN), we achieved superior performance in all of our experiments, establishing new benchmarks for this binary segmentation task. In our extensive experiments, we achieved an $80.34$% lower mean Hausdorff distance for unseen runs compared with the threshold approach when placed solely on the left lower leg. Using both left and right IMUs further improved performance ($83.37$% lower mean Hausdorff). For data from an algorithm-unknown athlete (Zero-Shot segmentation), the U-Net outperformed the threshold algorithm by $67.58$%, and fine-tuning on athlete-specific (Few-Shot segmentation) runs improved the lower mean Hausdorff to $78.68$%. The fine-tuned model detected takeoffs with median deviations of $0.008$ s (IQR $0.030$ s), landing deviations of $0.005$ s (IQR 0.020 s), and airtime deviations of $0.000$ s (IQR $0.027$ s). These advancements facilitate real-time feedback and detailed biomechanical analysis, enhancing performance and trick execution, particularly during critical events, such as take-off and landing, where precise time-domain localization is crucial for providing accurate feedback to coaches and athletes. Full article

Since the implementation of unconventional monetary policies (UMPs) by the US in response to the global financial crisis (GFC) and the COVID-19 pandemic, there have been increasing concerns that these forward guidance and quantitative easing programmes have had spillover effects on global equity markets. We specifically question whether the implementation of these UMPs have had spillovers to African equities, which have been previously speculated to be decoupled from global markets and shocks. Time-varying-parameter (TVP) frequency connectedness and wavelet coherency methods were used to examine the dynamic time-frequency spillovers between daily time series of the US shadow short rate and African equities returns/volatility between 1 January 2007 and 31 March 2023. On one hand, the TVP frequency connectedness analysis reveals robust long-run spillovers from US monetary policy to African equity markets during specific periods: 2009, 2013, 2020, and 2021. These coincide with instances when the Federal Reserve announced their transition from conventional to unconventional monetary practices and vice versa. On the other hand, the wavelet analysis provides insights into the ‘sign’ of the spillovers, indicating mixed phase dynamics during UMPs responding to the GFC. In contrast, anti-phase or negative co-movements characterize UMPs implemented during the COVID-19 pandemic, implying that these policies increased both returns and volatilities to African equities. Altogether, we conclude that US UMP has increasing deteriorated market efficiency and amplified portfolio risk in African equities whilst during ‘normalization’ periods US monetary policy has little transmission effect. Full article

Production efficiency is used to determine the best conditions for manufacturing goods at the lowest possible unit cost. When achieved, production efficiency leads to increased revenues for the manufacturer, enhanced employee safety, and a satisfied customer base. Production efficiency not only measures the amount of resources that are needed for production but also considers the productivity levels and the state of the production lines. In this context, online anomaly detection (AD) is an important tool for maintaining the reliability of the production ecosystem. With advancements in artificial intelligence and the growing significance of identifying and mitigating anomalies across different fields, approaches based on artificial neural networks facilitate the recognition of intricate types of anomalies by taking into account both temporal and contextual attributes. In this paper, a lightweight framework based on the Echo State Network (ESN) model running at the edge is introduced for online AD. Compared to other AD methods, such as Long Short-Term Memory (LSTM), it achieves superior precision, accuracy, and recall metrics while reducing training time, CO₂ emissions, and the need for high computational resources. The preliminary evaluation of the proposed solution was conducted using a low-resource computing device at the edge of the real production machine through an Industrial Internet of Things (IIoT) smart meter module. The machine used to test the proposed solution was provided by the Italian company SIFIM Srl, which manufactures filter mats for industrial kitchens. Experimental results demonstrate the feasibility of developing an AD method that achieves high accuracy, with the ESN-based framework reaching $85\%$ compared to $80.88\%$ for the LSTM-based model. Furthermore, this method requires minimal hardware resources, with a training time of $9.5$ s compared to $2.100$ s for the other model. Full article

As deep learning has produced dramatic breakthroughs in many areas, it has motivated emerging studies on the combination between neural networks and cache replacement algorithms. However, deep learning is a poor fit for performing cache replacement in hardware implementation because its neural network models are impractically large and slow. Many studies have tried to use the guidance of the Belady algorithm to speed up the prediction of cache replacement. But it is still impractical to accurately predict the characteristics of future access addresses, introducing inaccuracy in the discrimination of complex access patterns. Therefore, this paper presents the LSTM-CRP algorithm as well as its efficient hardware implementation, which employs the long short-term memory (LSTM) for access pattern identification at run-time to guide cache replacement algorithm. LSTM-CRP first converts the address into a novel key according to the frequency of the access address and a virtual capacity of the cache, which has the advantages of low information redundancy and high timeliness. Using the key as the inputs of four offline-trained LSTM network-based predictors, LSTM-CRP can accurately classify different access patterns and identify current cache characteristics in a timely manner via an online set dueling mechanism on sampling caches. For efficient implementation, heterogeneous lightweight LSTM networks are dedicatedly constructed in LSTM-CRP to lower hardware overhead and inference delay. The experimental results show that LSTM-CRP was able to averagely improve the cache hit rate by 20.10%, 15.35%, 12.11% and 8.49% compared with LRU, RRIP, Hawkeye and Glider, respectively. Implemented on Xilinx XCVU9P FPGA at the cost of 15,973 LUTs and 1610 FF registers, LSTM-CRP was running at a 200 MHz frequency with 2.74 W power consumption. Full article

Background/Objectives: The impact of physical activity (PA) and sedentary time (ST) during preschool years on the physical fitness (PF) levels of school-aged children remains unaddressed. This study aimed to investigate the associations of objectively measured vigorous physical activity (VPA), moderate-to-vigorous physical activity (MVPA), total physical activity (TPA), and ST in the last year of preschool (age of 6–7 years; n = 77; 51% boys) with cardiorespiratory fitness (CRF) and muscular fitness (MF) in the first grade of school among Estonian children. Methods: We assessed PA (accelerometers), CRF (20 m shuttle run), and MF (z-score of relative upper- and lower-limb muscular strength). Results: In the unadjusted analysis, higher VPA, MVPA, and TPA in preschool were associated with a higher MF in school among boys, while a higher VPA in preschool was related to a higher CRF in school among girls. However, VPA, MVPA, TPA, and ST in preschool were unrelated to CRF and MF among boys and girls after adjustment for baseline age, accelerometer wear time, the corresponding PF item, and parent’s education. In addition, a higher PF level in preschool was frequently related to a higher corresponding PF item in school among both genders. Conclusions: Moderate-to-vigorous and vigorous type of activities during final year of preschool, as well the amount of TPA that preschoolers are involved in, are not sufficient to affect their CRF and MF longitudinally. In addition, ST in preschool did not impact the CRF and MF of boys and girls in the first grade. Full article

Recently, various emerging technologies have been introduced to host IoT applications. Edge computing, utilizing volunteer devices, could be a feasible solution due to the significant and underutilized resources at the edge. However, cloud providers are still reluctant to offer it as an edge infrastructure service because of the unpredictable nature of volunteer resources. Volunteer edge computing introduces challenges such as reliability, trust, and availability. Testing this infrastructure is prohibitively expensive and not feasible in real-world scenarios. This emerging technology will not be fully realized until dedicated research and development efforts have substantiated its potential for running reliable services. Therefore, this paper proposes VonEdgeSim, a simulation of volunteer edge computing. To the best of our knowledge, it is the first and only simulation capable of mimicking volunteer behavior at the edge. Researchers and developers can utilize this simulation to test and develop resource management models. We conduct experiments with various IoT applications, including Augmented Reality, Infotainment, and Health Monitoring. Our results show that incorporating volunteer devices at the edge can significantly enhance system performance by reducing total task delay, and improving task execution time. This emphasizes the potential of volunteers to provide reliable services in an edge computing environment. The simulation code is publicly available for further development and testing. Full article