Explore the vast range of titles available.

The definition of human-computer interaction (HCI) has changed in the current year because people are interested in their various ergonomic devices ways. Many researchers have been working to develop a hand gesture recognition system with a kinetic sensor-based dataset, but their performance accuracy is not satisfactory. In our work, we proposed a multistage spatial attention-based neural network for hand gesture recognition to overcome the challenges. We included three stages in the proposed model where each stage is inherited the CNN; where we first apply a feature extractor and a spatial attention module by using self-attention from the original dataset and then multiply the feature vector with the attention map to highlight effective features of the dataset. Then, we explored features concatenated with the original dataset for obtaining modality feature embedding. In the same way, we generated a feature vector and attention map in the second stage with the feature extraction architecture and self-attention technique. After multiplying the attention map and features, we produced the final feature, which feeds into the third stage, a classification module to predict the label of the correspondent hand gesture. Our model achieved 99.67%, 99.75%, and 99.46% accuracy for the senz3D, Kinematic, and NTU datasets.

The author offers a comprehensive, up-to-date overview of attention theories and models and a full description of the selective tuning model, confining the formal elements to two chapters and two appendixes.

Protein content is an important index in the assessment of dairy nutrition. As a crucial source of protein absorption in people's daily life, the quality of milk powder products not only has a deep impact on the development of the dairy industry, but also seriously damages the health of consumers. It is of great significance to find a faster and more accurate method for detecting milk protein content. This paper utilizes the chemical content of milk powder and hyperspectral data as independent variables. By comparing 14 kinds of preprocessing algorithms, the mean‐centered (MC) method is selected to preprocess the data, and then the combined method of competitive adaptive reweighted sampling (CARS) and uninformative variable elimination (UVE) is used to screen the feature wavelength, so as to establish the model and learn the internal dynamic change law of the feature. Furthermore, the Attention mechanism was introduced to assign different weights to bidirectional long short‐term memory (BiLSTM) hidden states through mapping weighting and learning parameter matrix. To reduce the loss of information and strengthen the influence of important information, at the same time, in order to solve the difficult problem of hyperparameter selection of the model, the whale optimization algorithm (WOA) is proposed to optimize the hyperparameter selection of the model. The test results showed that with WOA‐BiLSTM‐Attention model algorithm, the coefficient of determination (R2) of 0.9975 and root mean square error (RMSEP) of 0.0337 in comparison with R2 and RMSEP values obtained from BiLSTM‐Attention model algorithm, which were higher by 0.799% lower by 56.5%, respectively. This study provides algorithm support and theoretical basis for fast non‐destructive testing based on deep learning algorithm to predict protein content in milk powder. Whale algorithm to optimize bidirectional long short‐term memory‐Attention prediction model. Wavelength selection using combined method. High precision protein content in milk powder.

Rationalizing site‐specific crop types is an effective strategy for ensuring food security under climate change. This study employed environmental covariates representing climate, soil, and vegetation, combined with a hybrid convolutional neural network ‐ Long Short‐term Memory‐self‐attention (CNN‐LSTM‐SA) model to predict net primary productivity (NPP) of the Northeast China (NEC) and the Mississippi River Basin (MRB) Mollisol regions. The analysis covered the periods from 2001 to 2020, and 2021 to 2040 under two Shared Socioeconomic Pathways (SSPs): SSP245 and SSP585. Subsequently, areas requiring crop type adjustments were identified, and appropriate crops were assigned to each growth site. Our results elucidate that: (a) During 2021–2040, a general increase in temperature and minor fluctuations in precipitation were observed across the study area. In the NEC, crop NPP initially increases before decreasing, whereas in the MRB, it consistently decreases. (b) Both vegetation and soil covariates explained 75.6% of NPP variability in the NEC, while in the MRB, climate factors, particularly precipitation, accounted for 18.4% of the variability. (c) The proportion of area requiring adjustment in the NEC ranged from 4.45% to 5.13% (SSP245) to 5.05%–5.77% (SSP585), while in the MRB, it varied from 4.92% to 7.54% (SSP245) to 6.49%–9.10% (SSP585), suggesting a necessity for more substantial cropping type adjustments under the SSP585 climate scenario. (d) In the NEC, the area cultivated with corn, soybean, and other crops will decrease, while rice cultivation will increase. Conversely, a decrease in wheat and pasture, and an increase in corn and soybean cultivation are suggested in the MRB. (e) Following crop type adjustments, the average NPP enhancements for corn, soybean, rice, and other crops in unsuitable areas of the NEC were 22.85%, 22.2%, 17.35%, and 20.5%, respectively, In the MRB, the average NPP enhancements for corn, soybean, wheat, and pasture were 28.5%, 26.9%, 32.4%, and 21.1%, respectively. Our research provides valuable insights into predicting future NPP changes, and develops effective crop adjustment strategies to address global food security challenges. Plain Language Summary It is estimated that approximately 30% of the global population faces moderate or severe food insecurity. Changes in crop net primary productivity (NPP) under current and future climate change remain highly uncertain. This raises the question of how to adjust spatial crop cultivation strategies to address food crises due to growing global population under climate change. In this study, we predicted future changes of NPP in the Northeast China (NEC) and the Mississippi River Basin (MRB) Mollisol regions. We then developed adjustment strategies for the spatial distribution of crops. The results show that NPP in the NEC is expected to increase initially and then decrease, whereas a continuous decline is predicted for the MRB, especially in highly productive areas. Soil conditions exert the greatest influence on NPP in the NEC, while meteorological factors, particularly precipitation, dominate crop growth in the MRB. Under both SSP245 and SSP585 climate scenarios, the area requiring adjustment ranged from 4.45% to 5.77% for the NEC and from 4.92% to 9.10% for the MRB. We recommend increasing rice acreage in the NEC and promoting more corn and soybean planting in the MRB. This strategy is expected to be most effective in sustaining and improving NPP. These results emphasize the negative impact of future climate change on crop growth, highlighting the urgent need for crop adjustment strategies. Key Points During 2021–2040, Net primary productivity exhibits an initial rise and fall in Northeast China (NEC), while the Mississippi River Basin (MRB) experiences a consistent decline Proportions of areas requiring crop adjustments substantial changes under SSP585 climate scenario In Mollisols, a potential decrease in corn, soybean was observed in NEC, while a potential increase in corn and soybean cultivation in MRB

The focus of fine-grained image classification tasks is to ignore interference information and grasp local features. This challenge is what the visual attention mechanism excels at. Firstly, we have constructed a two-level attention convolutional network, which characterizes the object-level attention and the pixel-level attention. Then, we combine the two kinds of attention through a second-order response transform algorithm. Furthermore, we propose a clustering-based grouping attention model, which implies the part-level attention. The grouping attention method is to stretch all the semantic features, in a deeper convolution layer of the network, into vectors. These vectors are clustered by a vector dot product, and each category represents a special semantic. The grouping attention algorithm implements the functions of group convolution and feature clustering, which can greatly reduce the network parameters and improve the recognition rate and interpretability of the network. Finally, the low-level visual features and high-level semantic information are merged by a multi-level feature fusion method to accurately classify fine-grained images. We have achieved good results without using pre-training networks and fine-tuning techniques.

Hashtags of microblogs can provide valuable information for many natural language processing tasks. How to recommend reliable hashtags automatically has attracted considerable attention. However, existing studies assumed that all the training corpus crawled from social networks are labelled correctly, while large sample statistics on real social media shows that there are 8.9% of microblogs with hashtags having wrong labels. The notable influence of noisy data to the classifier is ignored before. Meanwhile, recency also plays an important role in microblog hashtag, but the information is not used in the existing studies. Some temporal hashtags such as World Cup will ignite at a particular time, but at other times, the number of people talking about it will sharply decrease. To address the twofold shortcomings above, the authors propose an long short-term memory-based model, which uses temporal enhanced selective sentence-level attention to reduce the influence of wrong labelled microblogs to the classifier. Experimental results using a dataset of 1.7 million microblogs collected from SINA Weibo microblogs demonstrated that the proposed method could achieve significantly better performance than the state-of-the-art methods.

Due to natural disaster and global warning, one can expect unexpected fire, which causes panic among people and extent to death. To reduce the impact of fire, the authors propose a new method for predicting and rating fire in video through deep-learning models in this work such that rescue team can save lives of people. The proposed method explores a hybrid deep convolutional neural network, which involves motion detection and maximally stable extremal region for detecting and rating fire in video. Further, the authors propose to use a channel-wise attention mechanism of the deep neural network for detecting rating of fire level. Experimental results on a large dataset show the proposed method outperforms the existing methods for detecting and rating fire in video.

In humans, Attention is a core property of all perceptual and cognitive operations. Given our limited ability to process competing sources, attention mechanisms select, modulate, and focus on the information most relevant to behavior. For decades, concepts and functions of attention have been studied in philosophy, psychology, neuroscience, and computing. For the last 6 years, this property has been widely explored in deep neural networks. Currently, the state-of-the-art in Deep Learning is represented by neural attention models in several application domains. This survey provides a comprehensive overview and analysis of developments in neural attention models. We systematically reviewed hundreds of architectures in the area, identifying and discussing those in which attention has shown a significant impact. We also developed and made public an automated methodology to facilitate the development of reviews in the area. By critically analyzing 650 works, we describe the primary uses of attention in convolutional, recurrent networks, and generative models, identifying common subgroups of uses and applications. Furthermore, we describe the impact of attention in different application domains and their impact on neural networks’ interpretability. Finally, we list possible trends and opportunities for further research, hoping that this review will provide a succinct overview of the main attentional models in the area and guide researchers in developing future approaches that will drive further improvements.

We study the problem of recovering an underlying 3D shape from a set of images. Existing learning based approaches usually resort to recurrent neural nets, e.g., GRU, or intuitive pooling operations, e.g., max/mean poolings, to fuse multiple deep features encoded from input images. However, GRU based approaches are unable to consistently estimate 3D shapes given different permutations of the same set of input images as the recurrent unit is permutation variant. It is also unlikely to refine the 3D shape given more images due to the long-term memory loss of GRU. Commonly used pooling approaches are limited to capturing partial information, e.g., max/mean values, ignoring other valuable features. In this paper, we present a new feed-forward neural module, named AttSets, together with a dedicated training algorithm, named FASet, to attentively aggregate an arbitrarily sized deep feature set for multi-view 3D reconstruction. The AttSets module is permutation invariant, computationally efficient and flexible to implement, while the FASet algorithm enables the AttSets based network to be remarkably robust and generalize to an arbitrary number of input images. We thoroughly evaluate FASet and the properties of AttSets on multiple large public datasets. Extensive experiments show that AttSets together with FASet algorithm significantly outperforms existing aggregation approaches.

Horticulture and agriculture are considered as the important pillars of any economy. Current technological advancements have led to the development of several new technologies which are useful in atomizing the agriculture process. Apple farming has a significant role in Italy’s agriculture domain where manual labor is widely employed for apple picking which can be replaced by automated robot mechanisms. However, these mechanisms are based on computer vision methods. These methods focus on detection, localization and tracking the apple fruits in given video frames. Later, appropriate actions can be taken to enhance the production and harvesting. Several techniques have been presented for apple detection, but complex background, noise and image blurriness are the major causes which can deteriorate the performance of the system. Thus, in this work, we present a deep learning-based scheme to detect apples which uses Yolov5 architecture in live apple farm images. We further improve the Yolov5 architecture by incorporating an adaptive pooling scheme and attribute augmentation model. This model detects the smaller objects and improves the feature quality to detect the apples in complex backgrounds. Moreover, a loss function is also incorporated to obtain the accurate bounding box which helps to maximize the detection accuracy. The comparative study shows that the proposed approach with the improved Yolov5 architecture achieves overall accuracy of 0.97, 0.99, and 0.98 in terms of precision, recall, and F1-score, respectively.