Search Results (18,972)

Multi-channel speech enhancement has become an active area of research, demonstrating excellent performance in recovering desired speech signals from noisy environments. Recent approaches have increasingly focused on leveraging spectral information from multi-channel inputs, yielding promising results. In this study, we propose a novel feature integration network that not only captures spectral information but also refines it through shifted-window-based self-attention, enhancing the quality and precision of the feature extraction. Our network consists of blocks containing a full- and sub-band LSTM module for capturing spectral information, and a global–local attention fusion module for refining this information. The full- and sub-band LSTM module integrates both full-band and sub-band information through two LSTM layers, while the global–local attention fusion module learns global and local attention in a dual-branch architecture. To further enhance the feature integration, we fuse the outputs of these branches using a spatial attention module. The model is trained to predict the complex ratio mask (CRM), thereby improving the quality of the enhanced signal. We conducted an ablation study to assess the contribution of each module, with each showing a significant impact on performance. Additionally, our model was trained on the SPA-DNS dataset using a circular microphone array and the Libri-wham dataset with a linear microphone array, achieving competitive results compared to state-of-the-art models. Full article

Utilizing the Web of Science database as a retrieval source, this study employs CiteSpace software to conduct a visualization analysis of 8380 documents related to outdoor education published from 1994 to 2023. The findings reveal a phased increase in the volume of outdoor education research, with a shift in research themes from environmental governance to environmental education, ultimately concentrating on education for sustainable development that is characterized by significant temporal features. Initially dominated by publications from Europe and North America, the geographical distribution of research has gradually expanded globally. The core research theme centres around environmental education, with experiential education, outdoor learning, and education for sustainable development evolving concurrently. The network structure of research collaboration predominantly involves higher education institutions, with a noticeable shift from limited disciplinary research to interdisciplinary integration across multiple fields. Full article

The integration of blockchain technology into supply chain management (SCM) has emerged as a revolutionary force transforming traditional business operations. This study uses bibliometric analysis on 1069 articles from the Scopus database, using text mining and Python to uncover predominant themes and research trends at the intersection of blockchain and SCM. The key findings revealed three main thematic groups: ‘blockchain to improve transparency and traceability in SCM’ (supported by 323 articles), ‘impact of blockchain on supply chain efficiency and cost reduction’ (295 articles), and ‘blockchain-enabled supply chain resilience’ (191 articles). Furthermore, text mining highlighted prominent themes such as ‘decentralized supply chain networks’ (204 articles), ‘smart contracts for automated processes in SCM’ (234 articles), and ‘blockchain for sustainable supply chain practices’ (227 articles). The inclusion of sustainability themes reflects the growing importance of environmentally conscious strategies within supply chains, driven by the capacity of blockchain to reduce waste, and promote resource efficiency. The study identifies critical literature gaps, advocating for further exploration of the socio-economic impacts of blockchain on SCM. The topic extraction suggests new directions for SCM theory, while the role of blockchain in fostering sustainable and ethical supply chains is underscored. Practically, blockchain and IoT emerge as pivotal in the advancement of SCM, with text mining offering industry foresight and emphasizing blockchain-driven resilient strategies. Limitations include reliance on a single database and the recommendation that future studies incorporate diverse sources and qualitative insights. The findings provide a roadmap for academics and practitioners, highlighting potential avenues in SCM, especially in the context of sustainable and ethical practices. Full article

This paper proposes the design and construction of the prototype of a solid-state relay (SSR) that is controlled remotely through an interface developed in an Android application using a WIFI connection. Likewise, the prototype has a system for measuring electrical variables such as voltage, current, and power factor, whose values are also visualized in the application for monitoring the system’s load. Experimental results demonstrate the effective control of various load profiles, including resistive and resistive–inductive loads. The SSR successfully regulates the firing angle of an electronic device called TRIAC, allowing precise control over the load. Key features include a network snubber and heatsink, enhancing the durability and reliability of the system. The main contribution of this work is the integration of IoT-based remote control and monitoring with a robust SSR design, offering enhanced functionality and reliability for domotic applications. This integration facilitates improved productivity, resource management, and equipment monitoring in smart home environments, addressing the current gap in the availability of intelligent SSR solutions. Full article

The detection of bolt loosening in key components of aircraft engines faces problems such as complex and difficult-to-establish bolt loosening mechanism models, difficulty in identifying early loosening, and difficulty in extracting signal features with nonlinear and non-stationary characteristics. Therefore, the automated structural bolt micro looseness monitoring method using deep learning was proposed. Specifically, the addition of batch normalization methods enables the established Batch Normalized Stacked Autoencoders (BNSAEs) model to converge quickly and effectively, making the model easy to build and effective. Additionally, using characterization functions preprocess the original response signal not only simplifies the data structure but also ensures the integrity of features, which is beneficial for network training and reduces time costs. Finally, the effectiveness of the proposed method was verified by taking the bolted connection structures of two key components of aircraft engines, namely bolt connection structures and flange connection structures, as examples. Full article

Overcurrent protection is a fundamental aspect of power system protection and is widely utilised in distribution networks. The increasing integration of renewable energy sources (RESs) into the conventional power system has introduced operating challenges due to the variability in fault directions. As a result, protection engineers must not only adjust basic parameters such as pickup current or time delay, but also carefully evaluate the directional protection to align with specific protection objectives and the devices being protected. The complexity of considering multiple aspects in the protection system design can pose challenges for operators in configuring their settings. Therefore, it is necessary to have a systematic approach for protection system design. For this purpose, this paper proposes a methodology for protection system design focusing on directional overcurrent protection setting configuration with detailed implementation. A well-known distribution network, the CIGRE European (EU) medium-voltage (MV) benchmark network, is used to test and validate the proposed methodology with the support of DIgSILENT PowerFactory version 2023 SP1. This article provides a useful document for the configuration of overcurrent protection systems in order to prepare for the challenges arising from the high integration of RESs in the future grid. Full article

When classifying breeds of dogs, the accuracy of classification significantly affects breed identification and dog research. Using images to classify dog breeds can improve classification efficiency; however, it is increasingly challenging due to the diversities and similarities among dog breeds. Traditional image classification methods primarily rely on extracting simple geometric features, while current convolutional neural networks (CNNs) are capable of learning high-level semantic features. However, the diversity of dog breeds continues to pose a challenge to classification accuracy. To address this, we developed a model that integrates multiple CNNs with a machine learning method, significantly improving the accuracy of dog images classification. We used the Stanford Dog Dataset, combined image features from four CNN models, filtered the features using principal component analysis (PCA) and gray wolf optimization algorithm (GWO), and then classified the features with support vector machine (SVM). The classification accuracy rate reached 95.24% for 120 breeds and 99.34% for 76 selected breeds, respectively, demonstrating a significant improvement over existing methods using the same Stanford Dog Dataset. It is expected that our proposed method will further serve as a fundamental framework for the accurate classification of a wider range of species. Full article

Green innovation provides powerful incentives to achieve sustained social progress. However, the available research examines the financial drivers of green innovation, overlooking the impact of digital government development and the institutional environment. The integration of digital government construction with the institutional environment, and the coupling of the two with green innovation, will paint a picture of the future that promotes sustainable social progress and the modernization of governance. This research utilizes data from 31 provinces in China from 2018 to 2022 to study the impact of digital government construction and the institutional environment on the provincial green innovation efficiency. An empirical analysis is conducted on the basis of analyzing the spatiotemporal evolution and pattern of digital government construction, the institutional environment and the provincial green innovation efficiency. Firstly, digital government construction emphasizes data openness and sharing, and data become a key link between those inside and outside the government. The digital platform becomes an important carrier connecting the government and multiple subjects in collaborative innovation to continuously shape a new digital governance ecology. The netting of digital ecology is conducive to the institutional environment, serving to break the path dependence and create a more open, inclusive and synergistic institutional environment. Based on this, we consider that digital government construction positively affects the institutional environment, and this is verified. Secondly, a good government–market relationship, mature market development, a large market service scale, a complete property rights system and a fair legal system brought about by the improved institutional environment provide macro-external environmental support for enhanced innovation dynamics. Based on this, it is proposed that the institutional environment positively affects the provincial green innovation efficiency. Meanwhile, building on embeddedness theory, the industrial embeddedness of the institutional environment for green innovation highlights the scattered distribution of innovation components. Geographical embeddedness stresses indigenous resource distribution grounded in space vicinity and clustering. The better the institutional environment, the greater the forces of disempowerment at the industrial tier and the easier it is for resources to flow out. This may potentially have a detrimental role in improving the local green innovation efficiency. In view of this, it is proposed that the institutional environment negatively affects the provincial green innovation efficiency, and this is verified. Thirdly, digital government construction, as an important aspect of constructing a digital governance system and implementing the strategy of a strong network state, can effectively release the multiplier effect of digital technology in ecological environment governance and green innovation, continuously enhancing the provincial green innovation efficiency. In view of this, it is proposed that digital government construction positively affects the provincial green innovation efficiency, and this is verified. When the institutional environment is used as a mediating variable, digital government construction will have a certain non-linear impact in terms of provincial green innovation efficiency improvement. Building on the evidence-based analysis results, it is found that the institutional environment plays a competitive mediating role. This study integrates digital government construction, the institutional environment and the provincial green innovation efficiency under a unified analytical structure, offering theoretical inspiration and operational directions to enhance the provincial green innovation efficiency. Full article

Oncidium hybridum is one of the important cut-flowers in the world. However, the lack of aroma in its cut-flower varieties greatly limits the sustainable development of the Oncidium hybridum cut-flowers industry. This paper is an integral investigation of the diel pattern and influencing factors of the aroma release of Oncidium Twinkle ‘Red Fantasy’. GC-MS analysis revealed that the release of 3-Carene peaked at 10:00, while Butyl tiglate and Prenyl senecioate did so at 14:00, with a diel rhythm. By analyzing the correlation network between aroma component synthesis and differentially expressed genes, 15 key structural genes were detected and regulated by multiple circadian rhythm-related transcription factors. Cluster-17371.18_TPS, Cluster-65495.1_TPS, Cluster-46699.0_TPS, Cluster-60935.10_DXS, Cluster-47205.4_IDI, and Cluster-65313.7_LOX were key genes in the terpenoid and fatty acid derivative biosynthetic pathway, which were co-expressed with aroma release. Constant light/dark treatments revealed that the diurnal release of 3-Carene may be influenced by light and the circadian clock, and Butyl tiglate and Prenyl senecioate may be mainly determined by endogenous circadian clock. Under constant light treatment, the TPS, DXS, IDI, and LOX genes seem to lose their regulatory role in the release of aroma compounds from Oncidium Twinkle ‘Red Fantasy’. Under constant dark treatment, the TPS genes were consistent with the release pattern of 3-Carene, which may be a key factor in regulating the diel rhythm of 3-Carene biosynthesis. These results laid a theoretical foundation for the study of floral transcriptional regulation and genetic engineering technology breeding of Oncidium hybridum. 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

Large-scale mapping of soil resources can be crucial and indispensable for several of the managerial applications and policy implications. With machine learning models being the most utilized modeling technique for digital soil mapping (DSM), the implementation of model-based deep learning methods for spatial soil predictions is still under scrutiny. In this study, soil continuous (pH and OC) and categorical variables (order and suborder) were predicted using deep learning–multi layer perceptron (DL-MLP) and one-dimensional convolutional neural networks (1D-CNN) for the entire state of Tamil Nadu, India. For training the deep learning models, 27,098 profile observations (0–30 cm) were extracted from the generated soil database, considering soil series as the distinctive stratum. A total of 43 SCORPAN-based environmental covariates were considered, of which 37 covariates were retained after the recursive feature elimination (RFE) process. The validation and test results obtained for each of the soil attributes for both the algorithms were most comparable with the DL-MLP algorithm depicting the attributes’ most intricate spatial organization details, compared to the 1D-CNN model. Irrespective of the algorithms and datasets, the R² and RMSE values of the pH attribute ranged from 0.15 to 0.30 and 0.97 to 1.15, respectively. Similarly, the R² and RMSE of the OC attribute ranged from 0.20 to 0.39 and 0.38 to 0.42, respectively. Further, the overall accuracy (OA) of the order and suborder classification ranged from 39% to 67% and 35% to 64%, respectively. The explicit quantification of the covariate importance derived from the permutation feature importance implied that both the models tried to incorporate the covariate importance with respect to the genesis of the soil attribute under study. Such approaches of the deep learning models integrating soil–environmental relationships under limited parameterization and computing costs can serve as a baseline study, emphasizing opportunities in increasing the transferability and generalizability of the model while accounting for the associated environmental dependencies. Full article

Human activities, especially industrial production and urbanization, have significantly affected vegetation cover, water resource cycles, climate change, and biodiversity in the Qinling-Daba Mountain region and its surrounding areas. These activities contribute to complex and lasting impacts on ecological vulnerability. The Qinling Mountain region exhibits a complex interaction with human activities. The current research on the ecological vulnerability of the Qinling Mountain region primarily focuses on spatial distribution and the driving factors. This study innovatively applies the VSD assessment and Bayesian networks to systematically evaluate and simulate the ecological vulnerability of the study area over the past 20 years, which indicates that the integration of the VSD model with the Bayesian network model enables the simulation of dynamic relationships and interactions among various factors within the study areas, providing a more accurate assessment and prediction of ecosystem responses to diverse changes from a dynamic perspective. The key findings are as follows. (1) Areas of potential and slight vulnerability are concentrated in the Qinling-Daba mountainous regions. Over the past 20 years, areas of extreme and high vulnerability have significantly decreased, while areas of potential vulnerability and slight vulnerability have increased. (2) The key factors impacting ecological vulnerability during this period included industrial water use, SO₂ emissions, industrial wastewater, and ecological water use. (3) Areas primarily hindering the transition to potential vulnerability are concentrated in well-developed small urban regions within basins. Furthermore, natural factors like altitude and temperature, which cannot be artificially regulated, are the major impediments to future ecological restoration. Therefore, this paper recommends natural restoration strategies based on environmental protection and governance strategies that prioritize green development as complementary measures. The discoveries of the paper provide a novel analytical method for the study of ecological vulnerability in mountainous areas, offering valuable insights for enhancing the accuracy of ecological risk prediction, fostering the integration of interdisciplinary research, and optimizing environmental governance and protection strategies. Full article

The water temperature of lakes is one of their fundamental characteristics, upon which numerous processes in lake ecosystems depend. Therefore, it is crucial to have detailed knowledge about its changes and the factors driving those changes. In this article, a neural network model was developed to examine the impact of meteorological variables on lake water temperature by integrating daily meteorological data with data on interday variations. Neural networks were selected for their ability to model complex, non-linear relationships between variables, often found in environmental data. Among various architectures, the Artificial Neural Network (ANN) was chosen due to its superior performance, achieving an R² of 0.999, MSE of 0.0352, and MAE of 0.1511 in validation tests. These results significantly outperformed other models such as Multi-Layer Perceptrons (MLPs), Recurrent Neural Networks (RNNs), and Long Short-Term Memory (LSTM). Two lakes (Lake Mikołajskie and Sławskie) differing in morphometric parameters and located in different physico-geographical regions of Poland were analyzed. Performance metrics for both lakes show that the model is capable of providing accurate water temperature forecasts, effectively capturing the primary patterns in the data, and generalizing well to new datasets. Key variables in both cases turned out to be air temperature, while the response to wind and cloud cover exhibited diverse characteristics, which is a result of the morphometric features and locations of the measurement sites. Full article

Background. To investigate the behavior of spiking neural networks (SNNs), the sensitivity of input perturbation serves as an effective metric for assessing the influence on the network output. However, existing methods fall short in evaluating the sensitivity of SNNs featuring biologically plausible leaky integrate-and-fire (LIF) neurons due to the intricate neuronal dynamics during the feedforward process. Methods. This paper first defines the sensitivity of a temporal-coded spiking neuron (SN) as the deviation between the perturbed and unperturbed output under a given input perturbation with respect to overall inputs. Then, the sensitivity algorithm of an entire SNN is derived iteratively from the sensitivity of each individual neuron. Instead of using the actual firing time, the desired firing time is employed to derive a more precise analytical expression of the sensitivity. Moreover, the expectation of the membrane potential difference is utilized to quantify the magnitude of the input deviation. Results/Conclusions. The theoretical results achieved with the proposed algorithm are in reasonable agreement with the simulation results obtained with extensive input data. The sensitivity also varies monotonically with changes in other parameters, except for the number of time steps, providing valuable insights for choosing appropriate values to construct the network. Nevertheless, the sensitivity exhibits a piecewise decreasing tendency with respect to the number of time steps, with the length and starting point of each piece contingent upon the specific parameter values of the neuron. Full article

Automated water body (WB) extraction is one of the hot research topics in the field of remote sensing image processing. To address the challenges of over-extraction and incomplete extraction in complex water scenes, we propose an encoder–decoder architecture semantic segmentation network for high-precision extraction of WBs called EDWNet. We integrate the Cross-layer Feature Fusion (CFF) module to solve difficulties in segmentation of WB edges, utilizing the Global Attention Mechanism (GAM) module to reduce information diffusion, and combining with the Deep Attention Module (DAM) module to enhance the model’s global perception ability and refine WB features. Additionally, an auxiliary head is incorporated to optimize the model’s learning process. In addition, we analyze the feature importance of bands 2 to 7 in Landsat 8 OLI images, constructing a band combination (RGB 763) suitable for algorithm’s WB extraction. When we compare EDWNet with various other semantic segmentation networks, the results on the test dataset show that EDWNet has the highest accuracy. EDWNet is applied to accurately extract WBs in the Weihe River basin from 2013 to 2021, and we quantitatively analyzed the area changes of the WBs during this period and their causes. The results show that EDWNet is suitable for WB extraction in complex scenes and demonstrates great potential in long time-series and large-scale WB extraction. Full article