Environmental Noise Recognition Method Based on Multi-Channel Resolution Features and Attention Mechanism

Divisive normalization models of covert attention commonly use spike rate modulations as indicators of the effect of top-down attention. In addition, an increasing number of studies have shown that top-down attention increases the synchronization of neuronal oscillations as well, particularly in gamma-band frequencies (25–100 Hz). Although modulations of spike rate and synchronous oscillations are not mutually exclusive as mechanisms of attention, there has thus far been little effort to integrate these concepts into a single framework of attention. Here, we aim to provide such a unified framework by expanding the normalization model of attention with a multi-level hierarchical structure and a time dimension; allowing the simulation of a recently reported backward progression of attentional effects along the visual cortical hierarchy. A simple cascade of normalization models simulating different cortical areas is shown to cause signal degradation and a loss of stimulus discriminability over time. To negate this degradation and ensure stable neuronal stimulus representations, we incorporate a kind of oscillatory phase entrainment into our model that has previously been proposed as the “communication-through-coherence” (CTC) hypothesis. Our analysis shows that divisive normalization and oscillation models can complement each other in a unified account of the neural mechanisms of selective visual attention. The resulting hierarchical normalization and oscillation (HNO) model reproduces several additional spatial and temporal aspects of attentional modulation and predicts a latency effect on neuronal responses as a result of cued attention.

Recently, many scholars have used attention mechanisms to achieve excellent performance results on various neural network applications. However, the attention mechanism also has shortcomings. Firstly, the high computational and storage consumption makes the attention mechanism difficult to apply on long sequences. Second, all tokens are involved in the computation of the attention map, which may increase the influence of noisy tokens on the results and lead to poor training results. Due to these two shortcomings, attention models are usually strictly limited to sequence length. Further, attention models have difficulty in exploiting their excellent properties for modelling long sequences. To solve the above problems, an efficient sparse attention mechanism (SSA) is proposed in this paper. SSA is based on two separate layers: the local layer and the global layer. These two layers jointly encode local sequence information and global context. This new sparse-attention patterns is powerful in accelerating reasoning. The experiments in this paper validate the effectiveness of the SSA mechanism by replacing the self-attentive structure with an SSA structure in a variety of transformer models. The SSA attention mechanism has achieved state-of-the-art performance on several major benchmarks. SSA was validated on a variety of datasets and models encompassing language translation, language modelling and image recognition. With a small improvement in accuracy, the inference calculation speed was increased by 24%.KeywordsTransformersSequenceLocal attentionGlobal attentionSparsity

In order to improve the accuracy of sentiment analysis, this paper presents a new method for sentiment analysis of BiLSTM-cnn text based on self attention mechanism and dense connection. Methods BiLSTM-CNN-Attmodel was established. Firstly, BiLSTM was introduced to extract context words. Then, the convolutional neural network(CNN) is used to extract local semantic features. Combined with DenseNet dense connection module, the memory strength of the whole model is improved, and the utilization rate of weight information is enhanced. Finally, Self-attention mechanism is used to improve the ability of model mining information. This paper selects the data sets of chndenticorp and CCF2012 to train the optimal value of the DenseNet feature mapping matrix. The optimal value is brought into the model contrast experiment. In the experiment, the accuracy rate, recall rate and F value of this method are all greater than 91%, which is the highest among the models. It effectively improves the accuracy of text sentiment analysis, and has high research and practical value.

Reliable estimation of desired motion trajectories plays a crucial part in the continuous control of lower extremity assistance devices such as prostheses and orthoses. Moreover, reliable estimation methods are also required to predict hard-to-measure biomechanical quantities (e.g., joint contact moment/force) for use in sports injury science. Recognising that human locomotion is an inherently time-sequential and limb-synergetic behaviour, this study investigates models and learning algorithms for predicting the motion of a subject’s leg from the motion of complementary limbs. The novel deep learning model architectures proposed are based on the Long Short-Term Memory approach with the addition of an attention mechanism. A dataset comprising Inertial Measurement Unit signals from 21 subjects traversing varied terrains was used, including stair ascent/descent, ramp ascent/descent, stopped, level-ground walking and the transitions between these conditions. Fourier Analysis is deployed to evaluate the model robustness, in addition to assessing time-based prediction errors. The experiment on three unseen test participants suggests that the branched neural network structure is preferred to tackle the multioutput problem, and the inclusion of an attention mechanism demonstrates improved performance in terms of accuracy, robustness and network size. An experimental comparison found that 57% of the model parameters were not needed after adding attention layers meanwhile the prediction error is lower than the LSTM model without attention mechanism. The attention model has errors of 9.06% and 7.64% (normalised root mean square error) for ankle and hip acceleration prediction respectively. Also, less high-frequency noise is present in the attention model predictions. We conclude that the internal structure of the proposed deep learning model is justified, principally the benefit of using an attention mechanism. Experimental results for biomechanical motion estimation are obtained, showing greater accuracy than only with LSTM. The trained attention model can be used throughout despite transitioning between terrain types. Such a model will be useful in, for example, the control of lower-limb prostheses, instead of the need to identify and switch between different trajectory generators for different walking modes.

Recent deep sequential recommendation models often struggle to effectively model key characteristics of user behaviors, particularly in handling sequence length variations and capturing diverse interaction patterns. We propose STAR-Rec, a novel architecture that synergistically combines preference-aware attention and state-space modeling through a sequence-level mixture-of-experts framework. STAR-Rec addresses these challenges by: (1) employing preference-aware attention to capture both inherently similar item relationships and diverse preferences (2) utilizing state-space modeling to efficiently process variable-length sequences with linear complexity, and (3) incorporating a mixture-of-experts component that adaptively routes different behavioral patterns to specialized experts, handling both focused category-specific browsing and diverse category exploration patterns. We theoretically demonstrate how the state space model and attention mechanisms can be naturally unified in recommendation scenarios, where SSM captures temporal dynamics through state compression while attention models both similar and diverse item relationships. Extensive experiments on four real-world datasets demonstrate that STAR-Rec consistently outperforms state-of-the-art sequential recommendation methods, particularly in scenarios involving diverse user behaviors and varying sequence lengths. The implementation code is available anonymously online for easy reproducibility.

Research in sound classification and recognition is rapidly advancing in the field of pattern recognition. One important area in this field is environmental sound recognition, whether it concerns the identification of endangered species in different habitats or the type of interfering noise in urban environments. Since environmental audio datasets are often limited in size, a robust model able to perform well across different datasets is of strong research interest. In this paper, ensembles of classifiers are combined that exploit six data augmentation techniques and four signal representations for retraining five pre-trained convolutional neural networks (CNNs); these ensembles are tested on three freely available environmental audio benchmark datasets: (i) bird calls, (ii) cat sounds, and (iii) the Environmental Sound Classification (ESC-50) database for identifying sources of noise in environments. To the best of our knowledge, this is the most extensive study investigating ensembles of CNNs for audio classification. The best-performing ensembles are compared and shown to either outperform or perform comparatively to the best methods reported in the literature on these datasets, including on the challenging ESC-50 dataset. We obtained a 97% accuracy on the bird dataset, 90.51% on the cat dataset, and 88.65% on ESC-50 using different approaches. In addition, the same ensemble model trained on the three datasets managed to reach the same results on the bird and cat datasets while losing only 0.1% on ESC-50. Thus, we have managed to create an off-the-shelf ensemble that can be trained on different datasets and reach performances competitive with the state of the art.

Due to the vast amount of reviews available on the Web, in the past decades, a growing share of work has focused on sentiment analysis. Aspect-based sentiment classification is the subtask that seeks to detect the sentiment expressed by the content creators towards a defined target within a sentence. This paper introduces three novel unsupervised attentional neural network models for aspect-based sentiment classification, and tests them on English restaurant reviews. The first model employs an autoencoder-like structure to learn a sentiment embedding matrix where each row of the matrix represents the embedding for one sentiment. To improve the model, a target-based attention mechanism is included that de-emphasizes irrelevant words. Last, a redundancy and a seed regularization term constrain the sentiment embedding matrix. The second model extends the first by including a Bi-LSTM layer in the attention mechanism to exploit contextual information. The third model further adapts a Left-Center-Right separated neural network with Rotatory attention structure from the supervised realm to an unsupervised setting. Although all three models construct meaningful sentiment embeddings, experimental results indicate that the inclusion of the Bi-LSTM in the attention mechanism leads to a more precise attention mechanism and, thus, better predictions. The best model, i.e., the second, outperforms all investigated unsupervised and weakly supervised algorithms for aspect-based sentiment classification from the literature.

Dense connected convolutional neural network (Dense Net) is a new architecture of deep convolutional neural network, which ensures the maximum information transmission between network layers by establishing the connection relationship between different layers. In the task of text remote supervised relation extraction, aiming at the limitation of existing neural network methods using shallow network to extract features, a deep convolution neural network model with dense connection based on attention mechanism is designed. In this model, the dense connection module and maximum pooling layer composed of 5 layer convolutional neural network are used as the sentence encoder. By combining the lexical, syntactic and semantic features of different levels, it helps the network to learn the features, so as to obtain more abundant semantic information of the input sentence. At the same time, it reduces the gradient vanishing phenomenon of deep neural network, and makes the network more capable of representing natural language Strong. Secondly, the word level attention is introduced to calculate the relevance between two entities and context words, so as to fully capture the semantic information of the entity context in the sentence; then the sentence level attention is constructed on multiple instances to reduce the problem of label error labeling; finally, the dependency inclusion relationship between different relationships is automatically learned through the attention of the relationship level. The average accuracy of the model on the NYT freebase dataset is 83.5%. Experimental results show that the model can effectively use features and improve the accuracy of remote supervised relationship extraction.

Deep neural networks have been widely used in medical image segmentation and they can achieve good results in segmentation of some big organs. However, for some small organs, such as the pancreas in 3D CT images, the segmentation results are usually not satisfactory due to the low proportion. In this paper, we present a novel network --- Dense Attentional Network (DA-Net), to improve the pancreas segmentation in abdominal CT scans. In DA-Net, dense connection is used to combine low-level features of encoder with corresponding features of decoder, which can help to improve the utilization of feature maps (FMs). In addition, a new module for recombination and recalibration of feature maps (RRFM) and a new attentional mechanism --- deep attentional features (DAF), are used, which can excite the most discriminating features. Pancreas is segmented from 3D CT images by a coarse-to-fine mode, in which pancreas is firstly located from 3D CT images by a coarse segmentation network, and then pancreas is further finely segmented by the DA-Net. We evaluate the proposed method with 129 CT images from NIH pancreas dataset and BTCV segmentation challenge, and compare it with several mainstream segmentation networks. Comparing with these networks, our DA-Net has the higher mean DSC of 81.39%. This shows the effectiveness and advantage of the proposed method.

Unmanned aerial vehicle–human collaboration route planning for intelligent infrastructure inspection

Accurate fault diagnosis is the key to ensure the safe and operation of rotating machines. Accuracy of bearing fault diagnosis will be reduced in complex noise environments and variable load conditions. Therefore, this paper proposes a fault diagnosis method based on attention mechanism and residual neural network (FaultCNN). Firstly, a residual attention module is designed to extract the original fault features of the noise signals. Secondly, the ability to extract features of the residual module is further enhanced by adding an average pooling layer to the residual structure shortcut. To validate the diagnostic performance of the model, CWRU datasets are used for experimental verification. In the noise environment of <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\text{SNR}=-6 \text{dB}$</tex> , the accuracy of model fault diagnosis is 94.23%. Compared to existing bearing fault diagnostic methods, FaultCNN has higher anti-noise performance and variable load adaptability.

Accurate estimation of remaining useful life (RUL) becomes a crucial task when bearing operates under dynamic working conditions. The environmental noise, different operating conditions, and multiple fault modes result in the existence of considerable distribution and feature shifts between different domains. To address these issues, a novel framework TSBiLSTM is proposed that utilizes 1DCNN, SBiLSTM, and attention mechanism (AM) synergically to extract highly abstract feature representation, and domain adaptation is realized using the MK-MMD (multi-kernel maximum mean discrepancy) metric and domain confusion layer. One-dimensional CNN (1DCNN) and stacked bidirectional LSTM (SBiLSTM) are utilized to take advantage of spatiotemporal features with attention mechanism (AM) to selectively process the influential degradation information. MK-MMD provides effective kernel selection along with a domain confusion layer to effectively extract domain-invariant features. Both experimentation and comparison studies are conducted to verify the effectiveness and feasibility of the proposed TSBiLSTM model. The generalized performance is demonstrated using IEEE PHM data sets based on root mean squared error, mean absolute error, absolute percent mean error, and percentage mean error. The promising RUL prediction results validate the superiority and usability of the proposed TSBiLSTM model as a promising prognostic tool for dynamic operating conditions.

Among the high ranking pollution, noise pollution has made its positions throughout the globe. There has been increase in noise pollution levels due to the industrialization, growth of traffic and other human activities. Developing countries are at high risk from the noise pollution. . In India people are less aware about the noise pollution when compared with water and then air.&nbsp; It acts as silent poison on human health. Its affects are mostly visible on the population on long term of exposure. However the decay time of the noise in the environment is very short as compared to water and air pollution. In this book the introduction to sound, noise its monitoring techniques, impact on human and control of noise pollution has been summarized. The main objective of this is to make the population aware about the noise pollution and its adverse affect on the people exposed to it. Government in many countries have amended noise rule in order to control the noise pollution but in real it’s not implemented due to the awareness of the people. The different properties of sound along with its detailed definitions have been summarized in chapter 1. Consequently in the next chapter characteristics of noise along with its source of originations have been given so that people can get knowledge about the sources of noise in the environment. In continuation with this in third chapter measurement techniques and instrument required for the study of noise pollution has also been given in detail. Different noise rating systems and standards of noise as per different pollution board has been given in order to understand the impact on the environment. Impact on the human health due to noise pollution in described in chapter 4. And lastly the control of noise pollution at sources and by equipments has been summarized in the concluding chapter. This book is short introduction about the noise pollution along with properties, impact on human and control techniques. This is helpful in making the people aware about the high ranking noise pollution in the environment.

The recent advances in Vision Transformer (ViT) have demonstrated its impressive performance in image classification, which makes it a promising alternative to Convolutional Neural Network (CNN). Unlike CNNs, ViT represents an input image as a sequence of image patches. The patch-wise input image representation makes the following question interesting: How does ViT perform when individual input image patches are perturbed with natural corruptions or adversarial perturbations, compared to CNNs? In this work, we study the robustness of vision transformers to patch-wise perturbations. Surprisingly, we find that vision transformers are more robust to naturally corrupted patches than CNNs, whereas they are more vulnerable to adversarial patches. Furthermore, we conduct extensive qualitative and quantitative experiments to understand the robustness to patch perturbations. We have revealed that ViT's stronger robustness to natural corrupted patches and higher vulnerability against adversarial patches are both caused by the attention mechanism. Specifically, the attention model can help improve the robustness of vision transformers by effectively ignoring natural corrupted patches. However, when vision transformers are attacked by an adversary, the attention mechanism can be easily fooled to focus more on the adversarially perturbed patches and cause a mistake.

In the course of Part I, we have reviewed the evidence relating to many models of attention. These models have been associated with systems as global as consciousness and as molecular as the graded potential of a single neuron. In this chapter, we will develop a coherent framework to classify attentional components derived from these models, and to discuss the evidence for their theoretical viability.