Birds are significant bioindicators in the assessment of habitat biodiversity, ecological impacts and ecosystem health. Against the backdrop of easier bird vocalization data acquisition, and with deep learning and machine learning technologies as the technical support, exploring recognition and classification networks suitable for bird calls has become the focus of bioacoustics research. Due to the fact that the spectral differences among various bird calls are much greater than the differences between human languages, constructing birdsong classification networks based on human speech recognition networks does not yield satisfactory results. Effectively capturing the differences in birdsong across species is a crucial factor in improving recognition accuracy. To address the differences in features, this study proposes multi-scale deep features. At the same time, we separate the classification part from the deep network by using machine learning to adapt to classification with distinct feature differences in birdsong. We validate the effectiveness of multi-scale deep features on a publicly available dataset of 20 bird species. The experimental results show that the accuracy of the multi-scale deep features on a log-wavelet spectrum, log-Mel spectrum and log-power spectrum reaches 94.04%, 97.81% and 95.89%, respectively, achieving an improvement over single-scale deep features on these three spectrograms. Comparative experimental results show that the proposed multi-scale deep feature method is superior to five state-of-the-art birdsong identification methods, which provides new perspectives and tools for birdsong identification research, and is of great significance for ecological monitoring, biodiversity conservation and forest research.
The knapsack problem is a typical bi-objective combinatorial optimization issue, wherein maximizing the value of the packed items is achieved concurrently with minimizing the weight of the load. Due to the conflicting objectives of the knapsack problem and the typical discrete property of the items involved, swarm intelligence algorithms are commonly employed. The diversity of optimal combinations in the knapsack problem has become a focal point, which involves finding multiple packing solutions at the same value and weight. For this purpose, this paper proposes a Multi-Objective Equilibrium Optimizer Algorithm based on Weighted Congestion Distance (MOEO_WCD). The algorithm employs a non-dominated sorting method to find a set of Pareto front solutions rather than a single optimal solution, offering multiple decision-making options based on the varying needs of the decision-makers. Additionally, MOEO_WCD improves the balance pool generation mechanism and incorporates a weighted congestion incentive, emphasizing the diversity of packing combination solutions under the objectives of value and weight to explore more Pareto front solutions. Considering the discrete characteristics of the knapsack combination optimization problem, our algorithm also incorporates appropriate discrete constraint handling. This paper designs multiple sets of multi-objective knapsack combinatorial optimization problems based on the number of knapsacks, the number of items, and the weights and values of the items. This article compares five algorithms suitable for solving multi-objective problems: MODE, MO-PSO-MM, MO-Ring-PSO-SCD, NSGA-II, and DN-NSGAII. In order to evaluate the performance of the algorithm, this paper proposes a new solution set coverage index for evaluation. We also used the hypervolume indicator to evaluate the diversity of algorithms. The results show that our MOEO-WCD algorithm achieves optimal coverage of the reference composite Pareto front in the decision space of four knapsack problems. The experimental results indicate that our MOEO_WCD algorithm achieves the optimal coverage of the reference composite Pareto front in the decision space for four sets of knapsack problems. Although our MOEO_WCD algorithm covers less of the composite front in the objective space compared with the MODE algorithm for knapsack problem 1, its coverage of the integrated reference solutions in the decision space is greater than that of the MODE algorithm. The experiments demonstrate the superior performance of the MOEO_WCD algorithm on bi-objective knapsack combinatorial optimization problem instances, which provides an important solution to the search for diversity in multi-objective combinatorial optimization solutions.
The syllable is the most fundamental acoustic unit in bird vocalizations and is highly informative of species-specific behavioral characteristics. However, because syllables vary significantly across different species and environments, existing syllable extraction methods still rely on manual or semi-automatic processing, which constrains deep learning-based research on birdsong syllables. This study proposes SFWA-TweetyNet for automatic syllable annotation and applies it to the red-winged blackbird (Agelaius phoeniceus), achieving a validation accuracy of 0.978 and a loss of 0.073. Based on high-quality syllable recognition, this study conducted exploratory cross-regional and cross-seasonal acoustic comparisons at the syllable level to demonstrate a syllable-based analytical framework. Specifically: (1) Acoustic features were extracted from the principal syllables and analyzed using the Kruskal–Wallis test to explore potential variations in acoustic characteristics across regions and seasons; (2) A syllable-based frequency-weighted Acoustic Complexity Index (FW-ACI) was proposed to demonstrate how FW-ACI can be applied for acoustic analysis within the proposed framework, with the Kruskal–Wallis test used as an exploratory statistical tool. In addition, this study constructs a high-quality syllable-level dataset of red-winged blackbird vocalizations, providing important foundational data resources for automatic birdsong annotation, cross-domain soundscape analysis, and avian ecological and behavioral research.
With the rapid development of wireless communication, Wireless Local Area Networks (WLANs) are widely deployed in high-density environments. Ensuring fast handovers and optimal AP selection during device roaming is critical for maintaining network throughput and user experience. However, frequent mobility, high access density, and dynamic channel fluctuations complicate throughput prediction. To address this, we propose a method combining the Snow-Melting Optimizer (SMO) with decision tree regression models to optimize feature selection and model transmission opportunities (TXOP) and AP throughput. Experimental results show that the Extreme Gradient Boosting (XGBoost) model performs best, achieving high prediction accuracy for TXOP (MSE = 1.3746, R2 = 0.9842) and AP throughput (MAE = 2.5071, R2 = 0.9896). This approach effectively captures the nonlinear relationships between throughput and network factors in dense WLAN scenarios, demonstrating its potential for real-world applications.
The Location-Routing Problem (LRP) becomes a more intricate subject when the limits of capacities of vehicles and warehouses are considered, which is an NP-hard problem. Moreover, as the number of vehicles increases, the solution to LRP is exacerbated because of the complexity of transportation and the combination of routes. To solve the problem, this paper proposed a Discrete Assembly Combination-Delivery (DACA) strategy based on, the Binary Equilibrium Optimizer (BiEO) algorithm, in addition, this paper also proposes a mixed-integer linear programming model for the problem of this paper. Our primary objective is to address both the route optimization problem and the assembly group sum problem concurrently. Our BiEO algorithm was designed as discrete in decision space to meet the requirements of the LRP represented by the DACA strategy catering to the multi-vehicle LRP scenario. The efficacy of the BiEO algorithm with the DACA strategy is demonstrated. through empirical analysis utilizing authentic data from Changchun City, China, Remarkably, the experiments reveal that the BiEO algorithm outperforms conventional methods, specifically GA, PSO, and DE algorithms, resulting in reduced costs. Notably, the results show the DACA strategy enables the simultaneous optimization of the LRP and the vehicle routing problem (VRP), ultimately leading to cost reduction. This innovative algorithm proficiently tackles both the assembly group sum and route optimization problems intrinsic to multi-level LRP instances.
Birdsong is a valuable indicator of rich biodiversity and ecological significance. Although feature extraction has demonstrated satisfactory performance in classification, single-scale feature extraction methods may not fully capture the complexity of birdsong, potentially leading to suboptimal classification outcomes. The integration of multi-scale feature extraction and fusion enables the model to better handle scale variations, thereby enhancing its adaptability across different scales. To address this issue, we propose a Multi-Scale Hybird Convolutional Attention Mechanism Model (MUSCA). This method combines depth wise separable convolution and traditional convolution for feature extraction and incorporates self-attention and spatial attention mechanisms to refine spatial and channel features, thereby improving the effectiveness of multi-scale feature extraction. To further enhance multi-scale feature fusion, we have developed a layer-by-layer aligned feature fusion method that establishes deeper correlations, thereby improving classification accuracy and robustness. In our study, we investigated the songs of 20 bird species, extracting wavelet spectrogram, log-Mel spectrogram and log-spectrogram features. The classification accuracies achieved by our proposed method were 93.79%, 96.97% and 95.44% for these respective features. The results indicate that the birdcall recognition method proposed in this paper outperforms recent and state-of-the-art methods.