Search

Medieval paper, a handmade product, is made with a mould which leaves an indelible imprint on the sheet of paper. This imprint includes chain lines, laid lines and watermarks which are often visible on the sheet. Extracting these features allows the identification of the paper stock and gives information about the chronology, localisation and movement of manuscripts and people. Most computational work for feature extraction of paper analysis has so far focused on radiography or transmitted light images. While these imaging methods provide clear visualisation of the features of interest, they are expensive and time consuming in their acquisition and not feasible for smaller institutions. However, reflected light images of medieval paper manuscripts are abundant and possibly cheaper in their acquisition. In this paper, we propose algorithms to detect and extract the laid and chain lines from reflected light images. We tackle the main drawback of reflected light images, that is, the low contrast attenuation of chain and laid lines and intensity jumps due to noise and degradation, by employing the spectral total variation decomposition and develop methods for subsequent chain and laid line extraction. Our results clearly demonstrate the feasibility of using reflected light images in paper analysis. This work enables feature extraction for paper manuscripts that have otherwise not been analysed due to a lack of appropriate images. We also open the door for paper stock identification at scale. [ABSTRACT FROM AUTHOR]

During the past decades, several academic paper recommendation systems were introduced in literature aiming to assist users in finding relevant papers close to their needs. In particular, those models have used users' past preferences combined with papers' side information to personalize their recommendations. Unfortunately, the majority of those models fail to utilize the implicit relationship between the crucial elements along with the semantic relations of the nodes in a Heterogeneous Information Network (HIN), which can further improve the accuracy of the models. In this paper, we propose a research article recommendation model that aims to tackle those issues by exploiting both textual and graph representations, simultaneously. The model employs SPECTER document embedding to learn context-preserving research article representations. In particular, it learns the features from a HIN, which is a knowledge graph of the node entities and their relationships. Then, an attention module strengthens the semantic feature extraction process and learns enhanced representations. The combined semantic and structural features are then provided as input to a Deep Neural Network (DNN) in order to learn high-level representations of query and candidate papers. We have evaluated our model against state-of-the-art models over two popular datasets. The results indicate a significant improvement in terms of MAP, recall, and MRR. [ABSTRACT FROM AUTHOR]

Recommender systems have been increasingly popular in entertainment and consumption, and they are evident in academics, especially for applications that suggest submitting scientific articles to scientists. However, due to the various acceptance rates, impact factors, and rankings in different publishers, searching for a proper venue or journal to submit a scientific work usually takes a lot of time and effort. In this paper, we aim to present two new approaches extended from our paper (Huynh et al. 2021) presented at IAE/AIE 2021. In the first approach, we employ RNN structures besides using Conv1D. In the second approach, we introduce a new method, using DistillBert for two cases of uppercase and lowercase words. It can help vectorize features (such as Title, Abstract, and Keywords) and then use Conv1d to perform feature extraction. Furthermore, we propose a new calculation method for similarity score for Aim & Scope with other features (we name this approach is DistilBertAims). It can help keep the weights of similarity score calculation continuously updated and then continue to fit more data. The experimental results show that the second approach could obtain a better performance, which are 62.46%, 90.32%, 94.89%, 97.96% while the best performance in previous studies barely gained 50.02%, 78.89%, 86.27%, 93.23% in terms of Top K Accuracy (K = 1, 3, 5, 10). Interestingly, our best approach in this paper is higher than 12.44% the best of the previous study (Huynh et al. 2021) in terms of the Top 1 accuracy, which was presented in the conference IEA/AIE 2021. [ABSTRACT FROM AUTHOR]

Single-frame infrared small target detection is affected by the low image resolution and small target size, and is prone to the problems of small target feature loss and positional offset during continuous downsampling; at the same time, the sparse features of the small targets do not correlate well with the global-local linkage of the background features. To solve the above problems, this paper proposes an efficient infrared small target detection method. First, this paper incorporates BlurPool in the feature extraction part, which reduces the loss and positional offset of small target features in the process of convolution and pooling. Second, this paper designs an interactive attention deep feature fusion module, which acquires the correlation information between the target and the background from a global perspective, and designs a compression mechanism based on deep a priori knowledge, which reduces the computational difficulty of the self-attention mechanism. Then, this paper designs the context local feature enhancement and fusion module, which uses deep semantic features to dynamically guide shallow local features to realize enhancement and fusion. Finally, this paper proposes an edge feature extraction module for shallow features, which utilizes the complete texture and location information in the shallow features to assist the network to initially locate the target position and edge shape. Numerous experiments show that the method in this paper significantly improves nIoU, F1-Measure and AUC on IRSTD-1k Datasets and NUAA-SIRST Datasets. [ABSTRACT FROM AUTHOR]

Around a third of the total population of Europe suffers from mental disorders. The use of electroencephalography (EEG) together with Machine Learning (ML) algorithms to diagnose mental disorders has recently been shown to be a prominent research area, as exposed by several reviews focused on the field. Nevertheless, previous to the application of ML algorithms, EEG data should be correctly preprocessed and prepared via Feature Engineering (FE). In fact, the choice of FE techniques can make the difference between an unusable ML model and a simple, effective model. In other words, it can be said that FE is crucial, especially when using complex, non-stationary data such as EEG. To this aim, in this paper we present a Systematic Mapping Study (SMS) focused on FE from EEG data used to identify mental disorders. Our SMS covers more than 900 papers, making it one of the most comprehensive to date, to the best of our knowledge. We gathered the mental disorder addressed, all the FE techniques used, and the Artificial Intelligence (AI) algorithm applied for classification from each paper. Our main contributions are: (i) we offer a starting point for new researchers on these topics, (ii) we extract the most used FE techniques to classify mental disorders, (iii) we show several graphical distributions of all used techniques, and (iv) we provide critical conclusions for detecting mental disorders. To provide a better overview of existing techniques, the FE process is divided into three parts: (i) signal transformation, (ii) feature extraction, and (iii) feature selection. Moreover, we classify and analyze the distribution of existing papers according to the mental disorder they treat, the FE processes used, and the ML techniques applied. As a result, we provide a valuable reference for the scientific community to identify which techniques have been proven and tested and where the gaps are located in the current state of the art. [ABSTRACT FROM AUTHOR]

Freehand sketching on a paper is commonly found to be used as it is a natural and intuitive communication channel for portraying ideas. Additional strokes are often drawn over the existing ones to make the sketch clearer. For its usefulness in subsequent steps, a sketch is transformed to be a 3D CAD model that is typically performed manually by a designer due to a lack of technology support. Geometrical reconstruction from an offline scanning of a sketch has been a challenge because enriched information obtained during sketching is reduced to a batch of data points. This paper presents an algorithm for identifying a single-line drawing from a paper-based overtraced sketch as it is the first important step towards geometrical reconstruction. Key activities in this approach are thick-line sketch creation, contour boundary extraction, segments identification, and line drawing creation. The algorithm has been successfully implemented on LabVIEW and tested with several samples. [ABSTRACT FROM AUTHOR]

Thermal infrared image colorization is very difficult, and colorized images suffer from poor texture detail recovery and low color matching. To solve the above problems, this paper proposes an Efficient and Effective Generative Adversarial Network (E2GAN). This paper proposes multi-level dense module, feature fusion module, and color-aware attention module in the improved generator. Adding multi-level dense module can enhance the feature extraction capability and the improve detail recovery capability Using the feature fusion module in the middle of the encoder–decoder reduces the information loss caused by encoder down-sampling and improves the prediction of fine color of the image. Using the color-aware attention module during up-sampling allows for capturing more semantic details, focusing on more key objects, and generating high-quality colorized images. And the proposed discriminator is the PatchGAN with color-aware attention module, which enhances its ability to discriminate between true and false colorized images. Meanwhile, this paper proposes a novel composite loss function that can improve the quality of colorized images, generate fine local details, and recover semantic and texture information. Extensive experiments demonstrate that the proposed E2GAN has significantly improved SSIM, PSNR, LPIPS, and NIQE on the KAIST dataset and the FLIR dataset compared to existing methods. [ABSTRACT FROM AUTHOR]

Automatic Speech Emotion Recognition (ASER) has recently garnered attention across various fields including artificial intelligence, pattern recognition, and human–computer interaction. However, ASER encounters numerous challenges such as a shortage of diverse datasets, appropriate feature selection, and suitable intelligent recognition techniques. To address these challenges, a systematic literature review (SLR) was conducted following established guidelines. A total of 60 primary research papers spanning from 2011 to 2023 were reviewed to investigate, interpret, and analyze the related literature by addressing five key research questions. Despite being an emerging area with applications in real-life scenarios, ASER still grapples with limitations in existing techniques. This SLR provides a comprehensive overview of existing techniques, datasets, and feature extraction tools in the ASER domain, shedding light on the weaknesses of current research studies. Additionally, it outlines a list of limitations for consideration in future work. [ABSTRACT FROM AUTHOR]

In this paper, a method based on transfer learning is proposed to recover the three-dimensional shape of cultural relics faces from a single old photo. It can simultaneously reconstruct the three-dimensional facial structure and align the texture of the cultural relics with fewer training samples. The UV position map is used to represent the three-dimensional shape in space and act as the output of the network. A convolutional neural network is used to reconstruct the UV position map from a single 2D image. In the training process, the human face data is used for pre-training, and then a small amount of artifact data is used for fine-tuning. A deep learning model with strong generalization ability is trained with fewer artifact data, and a three-dimensional model of the cultural relic face can be reconstructed from a single old photograph. The methods can train more complex deep networks without a large amount of cultural relic data, and no over-fitting phenomenon occurs, which effectively solves the problem of fewer cultural relic samples. The method is verified by restoring a Chinese Terracotta Warrior with facial cracks and a Buddha with a broken nose. Other applications can be used in the fields such as texture recovery, facial feature extraction, and three-dimensional model estimation of the damaged cultural relics or sculptures in the photos. [ABSTRACT FROM AUTHOR]

With the development of image feature matching technology, feature matching algorithms based on deep learning have achieved excellent results, but in scenarios with low texture or extreme perspective changes, the matching accuracy is still difficult to guarantee. In this paper, a superresolution reconstruction method based on a Residual-ESPCN (efficient subpixel convolutional neural network) approach is proposed based on LoFTR (local feature matching with transformers). The superresolution method is used to improve the interpolation method used in ASFF (adaptive spatial feature fusion) to increase the image resolution, enhance the detailed information of the image, and make the extracted features richer. Then, ASFF is introduced into the local feature extraction module of LoFTR, which can alleviate the inconsistency problem of information transmission between different scale features of the feature pyramid and lessen the amount of information lost during transmission from low- to high-resolution levels. Moreover, to improve the adaptability of the algorithm to different scenarios, OTSU is introduced to adaptively calculate the threshold of feature matching. The experimental results show that in different indoor or outdoor scenarios, our proposed algorithm for matching features can effectively improve the adaptability of feature matching and can achieve good results in terms of the area under the curve (AUC), accuracy and recall. [ABSTRACT FROM AUTHOR]

Brain–computer interfaces (BCIs) based on steady-state visual evoked potentials (SSVEP) have received widespread attention due to their high information transmission rate, high accuracy, and rich instruction set. However, the performance of its identification methods strongly depends on the amount of calibration data for within-subject classification. Some studies use deep learning (DL) algorithms for inter-subject classification, which can reduce the calculation process, but there is still much room for improvement in performance compared with intra-subject classification. To solve these problems, an efficient SSVEP signal recognition deep learning network model e-SSVEPNet based on the soft saturation nonlinear module is proposed in this paper. The soft saturation nonlinear module uses a similar exponential calculation method for output when it is less than zero, improving robustness to noise. Under the conditions of the SSVEP data set, two sliding time window lengths (1 s and 0.5 s), and three training data sizes, this paper evaluates the proposed network model and compares it with other traditional and deep learning model baseline methods. The experimental results of the nonlinear module were classified and compared. A large number of experimental results show that the proposed network has the highest average accuracy of intra-subject classification on the SSVEP data set, improves the performance of SSVEP signal classification and recognition, and has higher decoding accuracy under short signals, so it has huge potential ability to realize high-speed SSVEP-based for BCI. [ABSTRACT FROM AUTHOR]

Danmakus are user-generated comments that overlay on videos, enabling real-time interactions between viewers and video content. The emotional orientation of danmakus can reflect the attitudes and opinions of viewers on video segments, which can help video platforms optimize video content recommendation and evaluate users' abnormal emotion levels. Aiming at the problems of low transferability of traditional sentiment analysis methods in the danmaku domain, low accuracy of danmaku text segmentation, poor consistency of sentiment annotation, and insufficient semantic feature extraction, this paper proposes a video danmaku sentiment analysis method based on MIBE-RoBERTa-FF-BiLSTM. This paper constructs a "Bilibili Must-Watch List and Top Video Danmaku Sentiment Dataset" by ourselves, covering 10,000 positive and negative sentiment danmaku texts of 18 themes. A new word recognition algorithm based on mutual information (MI) and branch entropy (BE) is used to discover 2610 irregular network popular new words from trigrams to heptagrams in the dataset, forming a domain lexicon. The Maslow's hierarchy of needs theory is applied to guide the consistent sentiment annotation. The domain lexicon is integrated into the feature fusion layer of the RoBERTa-FF-BiLSTM model to fully learn the semantic features of word information, character information, and context information of danmaku texts and perform sentiment classification. Comparative experiments on the dataset show that the model proposed in this paper has the best comprehensive performance among the mainstream models for video danmaku text sentiment classification, with an F1 value of 94.06%, and its accuracy and robustness are also better than other models. The limitations of this paper are that the construction of the domain lexicon still requires manual participation and review, the semantic information of danmaku video content and the positive case preference are ignored. [ABSTRACT FROM AUTHOR]

In industry, the task of defect classification and defect localization is an important part of defect detection system. However, existing studies only focus on one task and it is difficult to ensure the accuracy of both tasks. This paper proposes a defect detection system based on improved Yolo_v4, which greatly improves the detection ability of minor defects. For K_Means algorithm clustering prianchors question with strong subjectivity, the paper proposes the Density Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm to determine the number of Anchors. To solve the problem of low detection rate of small targets caused by insufficient reuse rate of low-level features in CSPDarknet53 feature extraction network, this paper proposes an ECA-DenseNet-BC-121 feature extraction network to improve it. And the Dual Channel Feature Enhancement (DCFE) module is proposed to improve the local information loss and gradient propagation obstruction caused by quad chain convolution in PANet networks to improve the robustness of the model. The experimental results on the fabric surface defect detection datasets show that the mAP of the improved Yolo_v4 is 98.97%, which is 7.67% higher than SSD, 3.75% higher than Faster_RCNN, 10.82% higher than Yolo_v4 tiny, and 5.35% higher than Yolo_v4, and the detection speed reaches 39.4 fps. It can meet the real-time monitoring needs of industrial sites. [ABSTRACT FROM AUTHOR]

The detection of pulmonary nodules has a low accuracy due to the various shapes and sizes of pulmonary nodules. In this paper, a multi-scale detection network for pulmonary nodules based on the attention mechanism is proposed to accurately predict pulmonary nodules. During data processing, the pseudo-color processing strategy is designed to enhance the gray image and introduce more contextual semantic information. In the feature extraction network section, this paper designs a basic module of ResSCBlock integrating attention mechanism for feature extraction. At the same time, the feature pyramid structure is used for feature fusion in the network, and the problem of the detection of small-size nodules which are easily lost is solved by multi-scale prediction method. The proposed method is tested on the LUNA16 data set, with an 83% mAP value. Compared with other detection networks, the proposed method achieves an improvement in detecting pulmonary nodules. [ABSTRACT FROM AUTHOR]

In recent years, highway accidents occur frequently, the main reason is that there is always foreign body invasion on the highway, which makes people unable to respond to emergencies in time. In order to reduce the occurrence of highway incidents, an object detection algorithm for highway intrusion was proposed in this paper. Firstly, a new feature extraction module was proposed to better preserve the main information. Secondly, a new feature fusion method was proposed to improve the accuracy of object detection. Finally, a lightweight method was proposed to reduce the computational complexity. We compare the algorithm in this paper with existing algorithms, the experimental results showed that: On the Visdrone dataset (small size targets), (a) the CS-YOLO was 3.6% more accurate than the YOLO v8. (b) The CS-YOLO was 1.2% more accurate than the YOLO v8 on the Tinypersons dataset (minimal size targets). (c) CS-YOLO was 1.4% more accurate than YOLO v8 on VOC2007 data set (normal size). [ABSTRACT FROM AUTHOR]

Ancient murals have suffered from continuous damage over time, and especially paint loss disease. Therefore, disease labeling, as the basis for ancient mural restoration, plays an important role in the protection of cultural relics. The predominant method of disease labeling is currently manual labeling, which is highly dependent on expert experience, time consuming, inefficient and results in inconsistent accuracy of the marking effect. In this paper, we propose a labeling framework for paint loss disease of ancient murals based on hyperspectral image classification and segmentation. The proposed framework involves first the extraction of features from the hyperspectral image, and then image segmentation is performed based on the spatial features to obtain more accurate region boundaries. Then, the hyperspectral image's regions are classified based on their spatial-spectral characteristics, and the candidate areas of paint loss disease are obtained. Finally, by leveraging the true color image segmentation results, the proposed disease labeling strategy combines the results of classification and segmentation to propose the final paint loss disease labeling areas. The experimental results show that the proposed method can not only combine the hyperspectral space and spectral information effectively to obtain accurate labeling of paint loss disease, but can also mark the paint loss disease not easily observed using ordinary digital cameras. Compared with the state-of-the-art methods, the proposed framework could be promising for accurate and effective paint loss disease labeling for ancient murals. [ABSTRACT FROM AUTHOR]

With a significant number of mechanical products approaching the retirement phase, the batch recycling of discarded mechanical parts necessitates a preliminary assessment of their surface condition. However, the presence of surface rust poses a challenge to defect identification. Therefore, this paper proposes a method for detecting heavily rusted surface defects based on an improved YOLOv8n network. In the Backbone, the C2f-DBB module of re-parameterized deep feature extraction was introduced, and the attention module was designed to improve the accuracy of information extraction. In the Neck part, a Bi-Afpn multiscale feature fusion strategy is designed to facilitate information exchange between features at different scales. Finally, Focal-CIoU is employed as the bounding box loss function to enhance the network's localization performance and accuracy for defects. Experimentally, it is proved that the improved network in this paper improves the Recall, Precision, and mAP0.5 by 1.2%, 2.1%, and 1.9%, respectively, on the original basis, which is better than other network models. [ABSTRACT FROM AUTHOR]

Existing salient object detection networks are large, have many parameters, are bulky and take up a lot of computational resources. Seriously hinder its application and promotion in boning robot. To solve this problem, this paper proposes a lightweight saliency detection algorithm for real-time localization of livestock meat bones. First, a lightweight feature extraction network based on multi-scale attention is constructed in the encoding stage. To ensure that more adequate salient object features are extracted with fewer parameters. Second, the fusion of jump connections is introduced in the decoding phase. Used to capture fine-grained semantics and coarse-grained semantics at full scale. Finally, we added a residual refinement module at the end of the backbone network. For optimizing salient target regions and boundaries. Experimental results on both publicly available datasets and self-made Pig leg X-ray (PLX) datasets show that. The proposed method is capable of ensuring first-class detection accuracy with 40 times less parameters than the conventional model. In the most challenging SOD dataset. The proposed algorithm in this paper achieves a value of Fωβ of 0.699. And the segmentation of livestock bones can be effectively performed on the homemade PLX dataset. Our model has a detection speed of 5fps on industrial control equipment. [ABSTRACT FROM AUTHOR]

With the advancement of society, ensuring the safety of personnel involved in municipal construction projects, particularly in the context of pandemic control measures, has become a matter of utmost importance. This paper introduces a security measure for municipal engineering, combining deep learning with object detection technology. It proposes a lightweight artificial intelligence (AI) detection method capable of simultaneously identifying individuals wearing masks and safety helmets. The method primarily incorporates the ShuffleNetv2 feature extraction mechanism within the framework of the YOLOv5s network to reduce computational overhead. Additionally, it employs the ECA attention mechanism and optimized loss functions to generate feature maps with more comprehensive information, thereby enhancing the precision of target detection. Experimental results indicate that this algorithm improves the mean average precision (mAP) value by 4.3%. Furthermore, it reduces parameter and computational loads by 54.8% and 53.8%, respectively, effectively striking a balance between lightweight operation and precision. This study serves as a valuable reference for research pertaining to lightweight target detection in the realm of municipal construction safety measures. [ABSTRACT FROM AUTHOR]

With the increasing number and types of global power loads and the development and popularization of smart grid technology, a large number of researches on load-level non-intrusive load monitoring technology have emerged. However, the unique power characteristics of the load make NILM face the difficult problem of low robustness of feature extraction and low accuracy of classification and identification in the recognition stage. This paper proposes a structured V-I mapping method to address the inherent limitations of traditional V-I trajectory mapping methods from a new perspective. In addition, for the verification of the V-I trajectory mapping method proposed in this paper, the complexity of load characteristics is comprehensively considered, and a lightweight convolutional neural network is designed based on AlexNet. The experimental results on the NILM dataset show that the proposed method significantly improves recognition accuracy compared to existing VI trajectory mapping methods. [ABSTRACT FROM AUTHOR]

The segmentation and extraction on color features can provide useful information for many different application domains. However, most of the existing image processing algorithms on feature extraction are gray image-based and consider only one-dimensional parameters. In order to carry out a fast and accurate color feature extraction, this paper proposes a color extraction algorithm by segmentation that is called a color extraction algorithm This algorithm is compared under different color distribution situations, and the extraction effect on color is also shown by the combination of the segmentation and feature extraction algorithms. Experimental results show that such segmentation algorithm has some advantages for color segmentation. In the fuzzy color image preprocessing, this paper gives the location method of region of interest. Moreover, compared with other existing extraction algorithms, the presented segmentation extraction algorithm in this paper not only has higher accuracy, shorter extraction time and stronger anti-interference ability, but also has better effect on more divergent color edge. Experimental evaluation of the proposed color extraction algorithm demonstrates dominance over existing algorithms for feature extraction. These researches in this paper provide a new way of thinking for color feature extraction by segmentation, which has an important theoretical references and practical significance. [ABSTRACT FROM AUTHOR]

YOLOv5 is one of the most popular object detection algorithms, which is divided into multiple series according to the control of network depth and width. To realize the deployment of mobile devices or embedded devices, the paper proposes a lightweight aerial image object detection algorithm (LAI-YOLOv5s) based on the improvement of YOLOv5s with a relatively small amount of calculation and parameter and relatively fast reasoning speed. Firstly, to better detect small objects, the paper replaces the minimum detection head with the maximum detection head and proposes a new feature fusion method, DFM-CPFN(Deep Feature Map Cross Path Fusion Network), to enrich the semantic information of deep features. Secondly, the paper designs a new module based on VoVNet to improve the feature extraction ability of the backbone network. Finally, based on the idea of ShuffleNetV2, the paper makes the network more lightweight without affecting detection accuracy. Based on the VisDrone2019 dataset, the detection accuracy of LAI-YOLOv5s on the mAP@0.5 index is 8.3% higher than that of the original algorithm. Compared with other series of YOLOv5 and YOLOv3 algorithms, LAI-YOLOv5s has the advantages of low computational cost and high detection accuracy. [ABSTRACT FROM AUTHOR]

The detection of steel surface defects is of great significance to steel production. In order to better meet the requirements of accuracy, real-time, and lightweight model, this paper proposes a highly efficient and lightweight steel surface defect detection method based on YOLOv5n. Firstly, ODMobileNetV2 composed of MobileNetV2 and ODConv is used as the backbone to improve the defect feature extraction capability. Secondly, GSConv is utilized in the neck to achieve deep information fusion through channel concatenation and shuffling, enhancing the ability of feature fusion. Finally, this paper proposes a spatial-channel reconstruction block (SCRB) designed to suppress redundant features and improve the representation ability of defect features through feature separation and reconstruction. Experimental results show that this method achieves 84.1% mAP and 109 FPS on the NEU-DET dataset, and 72.9% mAP and 110.1 FPS on the GC10-DET dataset, enabling accurate and efficient detection. Furthermore, the number of parameters is only 5.04M, which has a significant lightweight advantage. [ABSTRACT FROM AUTHOR]

Emergent news is characterized by few labels, and news detection methods that rely on a large number of labels are difficult to apply to learned features for emerging events and are ineffective in coping with less labeled emergent news detection. To address the challenge of limited labeled data, this study first establishes a scenario for detecting breaking news, ensuring that the domain of detecting events is distinct from the domain of historical events. Secondly, we propose the Clip-GCN multimodal fake news detection model. The model utilizes the Clip pre-training model to perform joint semantic feature extraction of image-text information, with text information as the supervisory signal, which solves the problem of semantic interaction between modalities. Meanwhile, considering the domain attributes of news, the model is trained to extract inter-domain invariant features through Adversarial Neural Network ideation, and intra-domain knowledge information is utilized through graph convolutional networks (GCN) to detect emergent news. Through an extensive number of experiments on Chinese and English datasets from two major social media platforms, Weibo and Twitter, it is demonstrated that the model proposed in this paper can accurately screen multimodal emergent news on social media with an average accuracy of 88.7%. The contribution of this study lies not only in the improvement of model performance but also in the proposal of a solution for the challenges posed by limited labels and multimodal breaking news. This provides robust support for research in related fields. [ABSTRACT FROM AUTHOR]

Epilepsy is one of the most well-known neurological disorders globally, leading to individuals experiencing sudden seizures and significantly impacting their quality of life. Hence, there is an urgent necessity for an efficient method to detect and predict seizures in order to mitigate the risks faced by epilepsy patients. In this paper, a new method for seizure detection and prediction is proposed, which is based on multi-class feature fusion and the convolutional neural network-gated recurrent unit-attention mechanism (CNN-GRU-AM) model. Initially, the Electroencephalography (EEG) signal undergoes wavelet decomposition through the Discrete Wavelet Transform (DWT), resulting in six subbands. Subsequently, time–frequency domain and nonlinear features are extracted from each subband. Finally, the CNN-GRU-AM further extracts features and performs classification. The CHB-MIT dataset is used to validate the proposed approach. The results of tenfold cross validation show that our method achieved a sensitivity of 99.24% and 95.47%, specificity of 99.51% and 94.93%, accuracy of 99.35% and 95.16%, and an AUC of 99.34% and 95.15% in seizure detection and prediction tasks, respectively. The results show that the method proposed in this paper can effectively achieve high-precision detection and prediction of seizures, so as to remind patients and doctors to take timely protective measures. [ABSTRACT FROM AUTHOR]

In the realm of prognosticating the remaining useful life (RUL) of pivotal components, such as aircraft engines, a prevalent challenge persists where the available historical life data often proves insufficient. This insufficiency engenders obstacles such as impediments in performance degradation feature extraction, inadequacies in capturing temporal relationships comprehensively, and diminished predictive accuracy. To address this issue, a 1D CNN-GRU prediction model for few-shot conditions is proposed in this paper. In pursuit of more comprehensive data feature extraction and enhanced RUL prognostication precision, the Convolutional Neural Network (CNN) is selected for its capacity to discern high-dimensional features amid the intricate dynamics of the data. Concurrently, the Gated Recurrent Unit (GRU) network is leveraged for its robust capability in extracting temporal features inherent within the data. We combine the two to construct a CNN-GRU hybrid network. Moreover, the integration of data distribution alongside correlation and monotonicity indices is employed to winnow the input of multi-sensor monitoring parameters into the CNN-GRU network. Finally, the engine RULs are predicted by the trained model. In this paper, experiments are conducted on a sub-dataset of the National Aeronautics and Space Administration (NASA) C-MAPSS multi-constraint dataset to validate the effectiveness of the method. Experimental results have demonstrated that this method has high accuracy in RUL prediction tasks, which can powerfully demonstrate its effectiveness. [ABSTRACT FROM AUTHOR]

The intelligent appearance quality classification method for Auricularia auricula is of great significance to promote this industry. This paper proposes an appearance quality classification method for Auricularia auricula based on the improved Faster Region-based Convolutional Neural Networks (improved Faster RCNN) framework. The original Faster RCNN is improved by establishing a multiscale feature fusion detection model to improve the accuracy and real-time performance of the model. The multiscale feature fusion detection model makes full use of shallow feature information to complete target detection. It fuses shallow features with rich detailed information with deep features rich in strong semantic information. Since the fusion algorithm directly uses the existing information of the feature extraction network, there is no additional calculation. The fused features contain more original detailed feature information. Therefore, the improved Faster RCNN can improve the final detection rate without sacrificing speed. By comparing with the original Faster RCNN model, the mean average precision (mAP) of the improved Faster RCNN is increased by 2.13%. The average precision (AP) of the first-level Auricularia auricula is almost unchanged at a high level. The AP of the second-level Auricularia auricula is increased by nearly 5%. And the third-level Auricularia auricula AP is increased by 1%. The improved Faster RCNN improves the frames per second from 6.81 of the original Faster RCNN to 13.5. Meanwhile, the influence of complex environment and image resolution on the Auricularia auricula detection is explored. [ABSTRACT FROM AUTHOR]

Automatic and accurate recognition of abnormal working conditions of fused magnesia furnace is of great significance to the safe and reliable production of fused magnesia. Aiming at the defects of manual judgment of abnormal working conditions in the production process of fused magnesium furnace and the existing recognition method of abnormal working conditions based on machine learning, this paper proposes a working condition recognition model for fused magnesium furnace based on stochastic configuration networks and reinforcement learning. Firstly, a hybrid data augmentation method of generative and non-generative is used to obtain high-quality sample data with salient features. Secondly, based on ResNeXt, multi-scale local features are extracted under the condition of limited parameter quantity by controlling the cardinality. Combining a mixed model that enjoys the benefit of both self-attention and convolution (ACmix) and bidirectional feature pyramid network (BiFPN), the extracted local feature maps of different scales are cross-scale fused and focused, and more differentiated detailed feature information of the region of interest is retained. Thirdly, based on Transformer, the working condition recognition network of fused magnesium furnace is constructed to improve the global correlation between adjacent local features in the spatial dimension. The fused features are sent to stochastic configuration networks to establish a classification criterion for working condition recognition of fused magnesium furnace with generalization ability. Finally, reinforcement learning is used to evaluate the credibility of uncertain recognition results of samples in real time, and a self-optimizing adjustment action strategy at the Transformer encoding layer is defined. Build a library of Transformer models with different encoding layers, which is adapt to the different feature extraction requirements of multi-modal working samples. The experimental results show that the method in this paper has better recognition performance and generalization ability than other algorithms. [ABSTRACT FROM AUTHOR]

Marine mammals are an important part of marine ecosystems, and human intervention seriously threatens their living environments. Few studies exist on the marine mammal call recognition task, and the accuracy of current research needs to improve. In this paper, a novel MG-ResFormer two-channel fusion network architecture is proposed, which can extract local features and global timing information from sound signals almost perfectly. Second, in the input stage of the model, we propose an improved acoustic feature energy fingerprint, which is different from the traditional single feature approach. This feature also contains frequency, energy, time sequence and other speech information and has a strong identity. Additionally, to achieve more reliable accuracy in the multiclass call recognition task, we propose a multigranular joint layer to capture the family and genus relationships between classes. In the experimental section, the proposed method is compared with the existing feature extraction methods and recognition methods. In addition, this paper also compares with the latest research, and the proposed method is the most advanced algorithm thus far. Ultimately, our proposed method achieves an accuracy of 99.39% in the marine mammal call recognition task. [ABSTRACT FROM AUTHOR]

Knowledge graph embedding converts knowledge graphs based on symbolic representations into low-dimensional vectors. Effective knowledge graph embedding methods are key to ensuring downstream tasks. Some studies have shown significant performance differences among various knowledge graph embedding models on different datasets. They attribute this issue to the insufficient representation ability of the models. However, what representation ability knowledge graph embedding models possess is still unknown. Therefore, this paper first selects three representative models for analysis: translation and rotation models in distance models, and the Bert model in neural network models. Based on the analysis results, it can be concluded that the translation model focuses on clustering features, the rotation model focuses on hierarchy features, and the Bert model focuses on word co-occurrence features. This paper categorize clustering and hierarchy as structure features, and word co-occurrence as semantic features. Furthermore, a model that solely focuses on a single feature will lead to a lack of accuracy and generality, making it challenging for the model to be applicable to modern large-scale knowledge graphs. Therefore, this paper proposes an ensemble model with structure and semantic features for knowledge graph embedding. Specifically, the ensemble model includes a structure part and a semantic part. The structure part consists of three models: translation, rotation and cross. Translation and rotation models serve as basic feature extraction, while the cross model enhances the interaction between them. The semantic part is built based on Bert and integrated with the structure part after fine-tuning. In addition, this paper also introduces a frequency model to mitigate the training imbalance caused by differences in entity frequencies. Finally, we verify the effectiveness of the model through link prediction. Experiments show that the ensemble model has achieved improvement on FB15k-237 and YAGO3-10, and also has good performance on WN18RR, proving the effectiveness of the model. [ABSTRACT FROM AUTHOR]

Industrial defect detection is a hot topic in the field of computer vision. It is a challenging task due to complex features and many categories of industrial defects. In this paper, a deep learning model based on the multiscale feature extraction module is introduced for steel surface defect detection. The main focus on the feature extraction capability of the model and feature fusion capability to improve the accuracy of the model for steel surface defect detection. First, to improve the feature extraction ability of the model, a multiscale feature extraction (MSFE) module is introduced. The MSFE module can effectively extract multiscale features through three branches that have different convolution kernel sizes. Second, an efficient feature fusion (EFF) module is proposed to optimize feature fusion by adding features from the backbone network to the neck network. Third, this paper puts forward a new Bottleneck module by reducing the normalization layer and activation function in the original Bottleneck module. Finally, the backbone network is deepened to further enhance the feature extraction ability of the model. Extensive experiments are conducted on the public NEU-DET dataset. The experimental results validate the effectiveness of the designed modules and the proposed model. Compared with other state-of-the-art methods, the proposed model achieves optimal accuracy(73.08% mAP@0.5) while maintaining a small number of parameters. [ABSTRACT FROM AUTHOR]

Around 50 million individuals worldwide suffer from epilepsy, a chronic, non-communicable brain disorder. Several screening methods, including electroencephalography, have been proposed to identify epileptic episodes. EEG data, which are frequently utilised to enhance epilepsy analysis, offer essential information on the electrical processes of the brain. Prior to the emergence of deep learning (DL), feature extraction was accomplished by standard machine learning techniques. As a result, they were only as good as the people who made the features by hand. But with DL, both feature extraction and classification are fully automated. These methods have significantly advanced several fields of medicine, including the diagnosis of epilepsy. In this paper, the works focused on automated epileptic seizure detection using ML and DL techniques are presented as well as their comparative analysis is done. The UCI-Epileptic Seizure Recognition dataset is used for training and validation. Some of the conventional ML and DL algorithms are used with a proposed model which uses long short-term memory (LSTM) to find the best approach. Post that comparative analysis is performed on these algorithms to find the best approach for epileptic seizure detection. As a result, the proposed model LSTM gives a validation accuracy of 97% giving the most appropriate and precise result as compared to other mentioned algorithms used in this study. [ABSTRACT FROM AUTHOR]

Collecting and analyzing data from all devices to improve the efficiency of business processes is an important task of Industrial Internet of Things (IIoT). In the age of data explosion, extensive text data generated by the IIoT have given birth to a variety of text representation methods. The task of text representation is to convert the natural language to a form that computer can understand with retaining the original semantics. However, these methods are difficult to effectively extract the semantic features among words and distinguish polysemy in natural language. Combining the advantages of convolutional neural network (CNN) and variational autoencoder (VAE), this paper proposes an intelligent CNN-VAE text representation algorithm as an advanced learning method for social big data within next-generation IIoT, which help users identify the information collected by sensors and perform further processing. This method employs the convolution layer to capture the local features of the context and uses the variational technique to reconstruct feature space to make it conform to the normal distribution. In addition, the improved word2vec model based on topical word embedding (TWE) is utilized to add topical information to word vectors to distinguish polysemy. This paper takes the social big data as an example to illustrate the way of the proposed algorithm applied in the next-generation IIoT and utilizes Cnews dataset to verify the performance of proposed method with four evaluating metrics (i.e., recall, accuracy, precision, and F1-score). Experimental results indicate that the proposed method outperforms word2vec-avg and CNN-AE in K-nearest neighbor (KNN), random forest (RF), and support vector machine (SVM) classifiers and distinguishes polysemy effectively. [ABSTRACT FROM AUTHOR]

Natural hazard named entity recognition is a technique used to recognize natural hazard entities from a large number of texts. The method of natural hazard named entity recognition can facilitate acquisition of natural hazards information and provide reference for natural hazard mitigation. The method of named entity recognition has many challenges, such as fast change, multiple types and various forms of named entities. This can introduce difficulties in research of natural hazard named entity recognition. To address the above problem, this paper constructed a natural disaster annotated corpus for training and evaluation model, and selected and compared several deep learning methods based on word vector features. A deep learning method for natural hazard named entity recognition can automatically mine text features and reduce the dependence on manual rules. This paper compares and analyzes the deep learning models from three aspects: pretraining, feature extraction and decoding. A natural hazard named entity recognition method based on deep learning is proposed, namely XLNet-BiLSTM-CRF model. Finally, the research hotspots of natural hazards papers in the past 10 years were obtained through this model. After training, the precision of the XLNet-BilSTM-CRF model is 92.80%, the recall rate is 91.74%, and the F1-score is 92.27%. The results show that this method, which is superior to other methods, can effectively recognize natural hazard named entities. [ABSTRACT FROM AUTHOR]

A. Kireeva et al. contributed another paper in the field of cellular automata: "Parallel simulation of drift-diffusion-recombination by cellular automata and global random walk algorithm". Parallel computing technologies enable the solution of large-scale numerical simulation and data processing problems in science and industry. The previously proposed contention-aware scheduling algorithm is formally described with this model, modifications of the algorithm are proposed: look-ahead technique, chunked data transfers, data caching, and peer-to-peer data transfers. [Extracted from the article]

Advances in computer image recognition have significantly impacted many industries, including healthcare, security and autonomous systems. This paper aims to explore the potential of improving image algorithms to enhance computer image recognition. Specifically, we will focus on regression methods as a means to improve the accuracy and efficiency of identifying images. In this study, we will analyze various regression techniques and their applications in computer image recognition, as well as the resulting performance improvements through detailed examples and data analysis. This paper deals with the problems related to visual image processing in outdoor unstructured environment. Finally, the heterogeneous patterns are converted into the same pattern, and the heterogeneous patterns are extracted from the fusion features of data modes. The simulation results show that the perception ability and recognition ability of outdoor image recognition in complex environment are improved. [ABSTRACT FROM AUTHOR]

In recent years, the field of bionics has attracted the attention of numerous scholars. Some models combined with biological vision have achieved excellent performance in computer vision and image processing tasks. In this paper, we propose a new bio-inspired lightweight contour detection network (BLCDNet) by combining parallel processing mechanisms of bio-visual information with convolutional neural networks. The backbone network of BLCDNet simulates the parallel pathways of ganglion cell–lateral geniculate nucleus and primary visual cortex (V1) area, realizing parallel processing and step-by-step extraction of input information, effectively extracting local features and detailed features in images, and thus improving the overall performance of the model. In addition, we design a depth feature extraction module combining depth separable convolution and residual connection in the decoding network to integrate the output of the backbone network, which further improves the performance of the model. We conducted a large number of experiments on BSDS500 and NYUD datasets, and the experimental results show that the BLCDNet proposed in this paper achieves the best performance compared with traditional methods and previous biologically inspired contour detection methods. In addition, BLCDNet still outperforms some VGG-based contour detection methods without pre-training and with fewer parameters, and it is competitive among all of them. The research in this paper also provides a new idea for the combination of biological vision and convolutional neural networks. [ABSTRACT FROM AUTHOR]

The retinal impulse signal is the basic carrier of visual information. It records the distribution of light on the retina. However, its direct conversion to a scene image is difficult due to the nonlinear characteristics of its distribution. Therefore, the use of artificial neural network to reconstruct the scene from retinal spikes has become an important research area. This paper proposes the architecture of a neural network based on vector quantization, where the feature vectors of spike trains are extracted, compressed, and stored using a feature extraction and compression network. During the decoding process, the nearest neighbour search method is used to find the nearest feature vector corresponding to each feature vector in the feature map. Finally, a reconstruction network is used to decode a new feature map composed of matching feature vectors to obtain a visual scene. This paper also verifies the impact of vector quantization on the characteristics of pulse signals by comparing experiments and visualizing the characteristics before and after vector quantization. The network delivers promising performance when evaluated on different datasets, demonstrating that this research is of great significance for improving relevant applications in the fields of retinal image processing and artificial intelligence. [ABSTRACT FROM AUTHOR]

Background: Emotion is a complex phenomenon that greatly affects human behavior and thinking in daily life. Electroencephalography (EEG), one of the human physiological signals, has been emphasized by most researchers in emotion recognition as its specific properties are closely associated with human emotion. However, the number of human emotion recognition studies using computer games as stimuli is still insufficient as there were no relevant publicly available datasets provided in the past decades. Most of the recent studies using the Gameemo public dataset have not clarified the relationship between the EEG signal's changes and the emotion elicited using computer games. Thus, this paper is proposed to introduce the use of data mining techniques in investigating the relationships between the frequency changes of EEG signals and the human emotion elicited when playing different kinds of computer games. The data acquisition stage, data pre-processing, data annotation and feature extraction stage were designed and conducted in this paper to obtain and extract the EEG features from the Gameemo dataset. The cross-subject and subject-based experiments were conducted to evaluate the classifiers' performance. The top 10 association rules generated by the RCAR classifier will be examined to determine the possible relationship between the EEG signal's frequency changes and game-induced emotions. Results: The RCAR classifier constructed for cross-subject experiment achieved highest accuracy, precision, recall and F1-score evaluated with over 90% in classifying the HAPV, HANV and LANV game-induced emotions. The 20 experiment cases' results from subject-based experiments supported that the SVM classifier could accurately classify the 4 emotion states with a kappa value over 0.62, demonstrating the SVM-based algorithm's capabilities in precisely determining the emotion label for each participant's EEG features' instance. Conclusion: The findings in this study fill the existing gap of game-induced emotion recognition field by providing an in-depth evaluation on the ruleset algorithm's performance and feasibility of applying the generated rules on the game-induced EEG data for justifying the emotional state prediction result. [ABSTRACT FROM AUTHOR]

The object scale of a small object scene changes greatly, and the object is easily disturbed by a complex background. Generic object detectors do not perform well on small object detection tasks. In this paper, we focus on small object detection based on FocusDet. FocusDet refers to the small object detector proposed in this paper. It consists of three parts: backbone, feature fusion structure, and detection head. STCF-EANet was used as the backbone for feature extraction, the Bottom Focus-PAN for feature fusion, and the detection head for object localization and recognition.To maintain sufficient global context information and extract multi-scale features, the STCF-EANet network backbone is used as the feature extraction network.PAN is a feature fusion module used in general object detectors. It is used to perform feature fusion on the extracted feature maps to supplement feature information.In the feature fusion network, FocusDet uses Bottom Focus-PAN to capture a wider range of locations and lower-level feature information of small objects.SIOU-SoftNMS is the proposed algorithm for removing redundant prediction boxes in the post-processing stage. SIOU multi-dimension accurately locates the prediction box, and SoftNMS uses the Gaussian algorithm to remove redundant prediction boxes. FocusDet uses SIOU-SoftNMS to address the missed detection problem common in dense tiny objects.The VisDrone2021-DET and CCTSDB2021 object detection datasets are used as benchmarks, and tests are carried out on VisDrone2021-det-test-dev and CCTSDB-val datasets. Experimental results show that FocusDet improves mAP@.5% from 33.6% to 46.7% on the VisDrone dataset. mAP@.5% on the CCTSDB2021 dataset is improved from 81.6% to 87.8%. It is shown that the model has good performance for small object detection, and the research is innovative. [ABSTRACT FROM AUTHOR]

The fusion of multimodal medical images has garnered painstaking attention for clinical diagnosis and surgical planning. Although various scholars have designed numerous fusion methods, the challenges of extracting substantial features without introducing noise and non-uniform contrast hindered the overall quality of fused photos. This paper presents a multimodal medical image fusion (MMIF) using a novel deep convolutional neural network (D-CNN) along with preprocessing schemes to circumvent the mentioned issues. A non-linear average median filtering (NL-AMF) and multiscale improved top-hat (MI-TH) approach are utilized at the preprocessing stage to remove noise and improve the contrast of images. The non-linear anisotropic diffusion (NL-AD) scheme is employed to split the photos into base and detailed parts. The fusion of base parts is accomplished by a dimension reduction method to retain the energy information. In contrast, the detailed parts are fused by novel D-CNN to preserve the enriched detailed features effectively. The simulation results demonstrate that the proposed method produces better brightness contrast and more image details than existing methods by acquiring 0.7649 to 0.8986, 0.3520 to 0.4783, 0.7639 to 0.9056, 68.8932 to 81.0487 gain for quality transfer ratio from source photo to a generated photo ( Q G AB ), feature mutual information (FMI), structural similarity index (SSIM), and average pixel intensity (API) respectively. [ABSTRACT FROM AUTHOR]

It has been proved that the two-branch network architecture for real-time semantic segmentation is effectiveness. However, existing methods still can not obtain sufficient context information and sufficient detailed information, which limits the improvement of the accuracy of existed two-branch methods. In this paper, we proposed a real-time high-precision semantic segmentation network based on a novel multi-resolution feature fusion module, an auxiliary feature extracting module, an upsampling module and multi-ASPP(atrous spatial pyramid pooling) module. We designed a feature fusion module, which is integrated with sufficient features of different resolutions to help the network get both sufficient semantic information and sufficient detailed information. We also studied the effect of the side-branch architecture on the network, and made new discoveries that the role of the side-branch is more than regularization, it may either slow down the convergence or accelerate the convergence by influencing the gradient of different layers of the network, which is dependent on the parameters of the network and the input data. Based on the new discoveries about the side-branch architecture, we used a side-branch auxiliary feature extraction layer in the network to improve the performance of the network. We also designed an upsampling module, which can get better detailed information than the original upsampling module. In addition, we also re-considered the locations and number of atrous spatial pyramid pooling (ASPP) modules, and modified the network architecture according to the experimental results to further improve the performance of the network. We proposed a network based on the above study. We named this network Deep Multiple-resolution Bilateral Network for Real-time, referred to as DMBR-Net. The network proposed in the paper achieved 81.3% mIoU(Mean Intersection over Union) at 110FPS on the Cityscapes validation dataset, 80.7% mIoU at 104FPS on the CamVid test dataset, 32.2% mIoU at 78FPS on the COCO-Stuff test dataset. [ABSTRACT FROM AUTHOR]

Power quality disturbance (PQD) is an important problem affecting the safe and stable operation of power system. Traditional single modal methods not only have a large number of parameters, but also usually focus on only one type of feature, resulting in incomplete information about the extracted features, and it is difficult to identify complex and diverse PQD types in modern power systems. In this regard, this paper proposes a multi-modal parallel feature extraction and classification model. The model pays attention to both temporal and spatial features of PQD, which effectively improves classification accuracy. And a lightweight approach is adopted to reduce the number of parameters of the model. The model uses Long Short Term Memory Neural Network (LSTM) to extract the temporal features of one-dimensional temporal modes of PQD. At the same time, a lightweight residual network (LResNet) is designed to extract the spatial features of the two-dimensional image modality of PQD. Then, the two types of features are fused into multi-modal spatio-temporal features (MSTF). Finally, MSTF is input to a Support Vector Machine (SVM) for classification. Simulation results of 20 PQD signals show that the classification accuracy of the multi-modal model proposed in this paper reaches 99.94%, and the parameter quantity is only 0.08 MB. Compared with ResNet18, the accuracy of the proposed method has been improved by 2.55% and the number of parameters has been reduced by 99.25%. [ABSTRACT FROM AUTHOR]

In the process of mining belt transportation, various foreign objects may appear, which will have a great impact on the crusher and belt, thus affecting production progress and causing serious safety accidents. Therefore, it is important to detect foreign objects in the early stages of intrusion in mining belt conveyor systems. To solve this problem, the YOLOv4_GECA method is proposed in this paper. Firstly, the GECA attention module is added to establish the YOLOv4_GECA foreign object detection model in the mineral belt to enhance the foreign object feature extraction capability. Secondly, based on this model, the learning rate decay of restart cosine annealing is used to improve the foreign object image detection performance of the model. Finally, we collected belt transport image information from the Pai Shan Lou gold mine site in Shenyang and established a belt foreign body detection dataset. The experimental results show that the average detection accuracy of the YOLOv4_GECA method proposed in this paper is 90.1%, the recall rate is 90.7%, and the average detection time is 30 ms, which meets the requirements for detection accuracy and real-time performance at the mine belt transportation site. [ABSTRACT FROM AUTHOR]

Copyright of Fire Ecology is the property of Springer Nature and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Deep learning has made substantial progress in crowd counting, but in practical applications, due to interference factors such as perspective distortion and complex background, the existing methods still have large errors in counting. In response to the above problems, this paper designs a multi-scale feature fusion network (IA-MFFCN) based on the reverse attention mechanism, which maps the image to the crowd density map for counting. The network consists of three parts: feature extraction module, inverse attention module, and back-end module. First, to overcome the problem of perspective distortion, deeper single-column CNNs was designed as a feature extraction module to extract multi-scale feature information and merge them; second, to avoid interference of complex backgrounds, the inverse attention module was designed, through the multi-scale inverse attention mechanism, reducing the influence of noise on counting accuracy. Finally, to generate a high-quality crowd density map, dilation convolution was introduced. Simultaneously, to enhance the sensitivity of the network to crowd counting, a comprehensive loss function based on Euclidean loss and predicted population loss is designed to improve training accuracy, to produce a more accurate density value. Experiments show that compared with the comparison algorithm, the algorithm in this paper has a significant reduction in the mean absolute error (MAE) and mean square error (MSE) on the ShanghaiTech dataset, UCF_CC_50 dataset and WorldExpo'10 dataset. [ABSTRACT FROM AUTHOR]

Aiming at the intrinsic aspect that the weak features of the early fault information of rolling bearings are not easy to extract, a parameter Adaptive Variational Modal Decomposition (AVMD) based algorithm is proposed for bearing fault signal feature extraction. Since the number of Variational Modal Decomposition (VMD) decomposition and penalty factor play an important role in VMD decomposition effect, the irregularities in the selection of these two influencing parameters are analyzed. We exploit the stronger global search capability of the improved sparrow search algorithm (LSSA) for adaptive parameter selection of the VMD algorithm. In this paper, the Levy flight algorithm is introduced and chaos is added to initialize sparrow population position to prevent sparrow from falling into the disadvantage of local optimum in the search process. In addition, this paper also combines the maximum kurtosis index, the minimum envelope entropy index and the number of iterations of VMD to form the objective function of the LSSA. The VMD algorithm with optimized parameters decomposes the signal to be measured, the decomposed IMFs was reconstructed, finally the validity of the model was verified by calculating 20 features (time domain and frequency domain) of the reconstructed signal as the input vector of the SVM classifier. Finally, the feasibility of this model in fault diagnosis of rolling bearing is verified using simulation and example experiments. [ABSTRACT FROM AUTHOR]

The ridge beast is a beast placed on the ridge of the roof of ancient Chinese buildings, not only has a decorative function, and has a strict hierarchical meaning, the number and form of the ridge beast placed on different levels of buildings are strictly limited. The detection technology of ridge beast decorative parts has important application value in the fields of fine 3D reconstruction of ancient buildings, historical dating and cultural and tourism services. Aiming at the problem of poor detection performance of traditional detection algorithms due to high texture similarity and poor discrimination of ridge beast, this paper proposed an improved YOLOv3 based detection algorithm for ridge beast decorative pieces. In terms of basic network improvement, local features are aggregated to the deep separable convolution internal embedding summation layer, and point convolution is used to connect the channel information of original features and aggregated features, so as to expand the receptive field and learn more diverse features. The residual structure of the feature extraction network was constructed by using the convolution, and the extraction effect of the model on the fine-grained features of the ridge beast was optimized, so that the detection accuracy was improved. In the prediction head improvement of the model, the original linear structure was reconstructed, and the extrusion and excitation modules were introduced to model the channel relationship of multi-scale feature map, which suppressed the response of interference signals and made the feature more directivity. The parallel 1 × 1 and 3 × 3 convolution are used to construct a multi-size convolution structure, which enhances the semantic information extraction ability of the model and further improves the detection effect. Experiments were conducted on the constructed ridge-beast dataset, and the results showed that the mAP of the improved algorithm can reach 86.48%, which is 3.05% higher than YOLO-v3, and the model parameters are reduced by 70%, which has a better detection performance and can provide a reference for the automated detection of ancient building components. [ABSTRACT FROM AUTHOR]

Pulse-coupled neural networks perform well in many fields such as information retrieval, depth estimation and object detection. Based on pulse coupled neural network (PCNN) theory, this paper constructs a visual perception model framework and builds a real image reproduction platform. The model firstly analyzes the structure and generalization ability of neural network multi-class classifier, uses the minimax criterion of feature space as the splitting criterion of visual perception decision node, which solves the generalization problem of neural network learning algorithm. In the simulation process, the initial threshold is optimized by the two-dimensional maximum inter-class variance method, and in order to improve the real-time performance of the algorithm, the fast recurrence formula of neural network is derived and given. The PCNN image segmentation method based on genetic algorithm is analyzed. The genetic algorithm improves the loop termination condition and the adaptive setting of model parameters of PCNN image segmentation algorithm, but the PCNN image segmentation algorithm still has the problem of complexity. In order to solve this problem, this paper proposed an IGA-PCNN image segmentation method combining the improved algorithm and PCNN model. Firstly, it used the improved immune genetic algorithm to adaptively obtain the optimal threshold, and then replaced the dynamic threshold in PCNN model with the optimal threshold, and finally used the pulse coupling characteristics of PCNN model to complete the image segmentation. From the coupling characteristics of PCNN, junction close space of image and gray level characteristics, it determined the local gray mean square error of image connection strength coefficient. The feature extraction and object segmentation properties of PCNN come from the spike frequency of neurons, and the number of neurons in PCNN is equal to the number of pixels in the input image. In addition, the spatial and gray value differences of pixels should be considered comprehensively to determine their connection matrix. Digital experiments show that the multi-scale multi-task pulse coupled neural network model can shorten the total training time by 17 h, improve the comprehensive accuracy of the task test data set by 1.04%, and shorten the detection time of each image by 4.8 s compared with the series network model of multiple single tasks. Compared with the traditional PCNN algorithm, it has the advantages of fast visual perception and clear target contour segmentation, and effectively improves the anti-interference performance of the model. [ABSTRACT FROM AUTHOR]

Wearable sensors are widely used in medical applications and human–computer interaction because of their portability and powerful privacy. Human activity identification based on sensor data plays a vital role in these fields. Therefore, it is important to improve the recognition performance of different types of actions. Aiming at the problems of insufficient time-varying feature extraction and gradient explosion caused by too many network layers, a time convolution network recognition model with attention mechanism (TCN-Attention-HAR) was proposed. The model effectively recognizes and emphasizes the key feature information. The ability of extracting temporal features from TCN (temporal convolution network) is improved by using the appropriate size of the receiver domain. In addition, attention mechanisms are used to assign higher weights to important information, enabling models to learn and identify human activities more effectively. The performance of the Open Data Set (WISDM, PAMAP2 and USC-HAD) is improved by 1.13%, 1.83% and 0.51%, respectively, compared with other advanced models, these results clearly show that the network model presented in this paper has excellent recognition performance. In the knowledge distillation experiment, the parameters of student model are only about 0.1% of those of teacher model, and the accuracy of the model has been greatly improved, and in the WISDM data set, compared with the teacher's model, the accuracy is 0.14% higher. [ABSTRACT FROM AUTHOR]