Search

Training deep learning models for vision-based monitoring of construction sites usually requires a large amount of labeled data. Semisupervised learning methods can efficiently obtain unlabeled data with substantial cost savings. Thus, this paper proposes a semisupervised object detection method for construction site monitoring. Weather as well as strong and weak data augmentation are integrated to cope with the complex construction site conditions (weather changes, camera view shifts, and so on) by integrating semisupervised learning to leverage the valid information in unlabeled construction site images. To validate its effectiveness, the proposed method was tested on the Alberta Construction Image Data Set (ACID), a public data set for the construction research community. The experimental results revealed that the proposed method achieves an average accuracy [mean average precision (mAP)] of 81.1% when trained on only 3% of the labeled images. This study helps to significantly reduce the development cost of vision-based object detection models for construction sites. [ABSTRACT FROM AUTHOR]

A novel framework for adaptive energy management, rooted in deep learning principles, is proposed to minimize fuel consumption in extended‐range electric vehicles amidst intricate driving scenarios. This innovative approach integrates a long short‐term memory (LSTM) network for pattern recognition across three driving patterns and an adaptive fuzzy controller. To mitigate the impact of poor hyperparameter selection on recognition accuracy, Gray Wolf Optimization is employed to optimize the hidden layer nodes, training times, and learning rate of the LSTM. Simultaneously, a genetic algorithm is utilized to optimize the vertex coordinates of the fuzzy control membership function, enabling the adaptive adjustment of parameters in the fuzzy energy management strategy. The condition recognition model accurately identifies the vehicle's driving status and seamlessly transitions to an energy management strategy tailored to the present conditions. This ensures optimal operation, enhancing overall fuel efficiency and performance. The simulation results robustly validate the efficacy of this approach: the GWO‐LSTM network achieves an impressive 97.7% accuracy in recognizing working conditions, surpassing the 88.9% accuracy of the traditional LSTM network. Furthermore, the fuel consumption reduction achieved by the adaptive fuzzy energy management strategy amounts to 11.9% compared with the conventional fuzzy energy management approach. This outcome underscores the tangible enhancement in vehicle fuel economy resulting from the seamless integration of deep learning techniques. [ABSTRACT FROM AUTHOR]

Background: To develop a deep learning(DL) model utilizing ultrasound images, and evaluate its efficacy in distinguishing between benign and malignant parotid tumors (PTs), as well as its practicality in assisting clinicians with accurate diagnosis. Methods: A total of 2211 ultrasound images of 980 pathologically confirmed PTs (Training set: n = 721; Validation set: n = 82; Internal-test set: n = 89; External-test set: n = 88) from 907 patients were retrospectively included in this study. The optimal model was selected and the diagnostic performance evaluation is conducted by utilizing the area under curve (AUC) of the receiver-operating characteristic(ROC) based on five different DL networks constructed at varying depths. Furthermore, a comparison of different seniority radiologists was made in the presence of the optimal auxiliary diagnosis model. Additionally, the diagnostic confusion matrix of the optimal model was calculated, and an analysis and summary of misjudged cases' characteristics were conducted. Results: The Resnet18 demonstrated superior diagnostic performance, with an AUC value of 0.947, accuracy of 88.5%, sensitivity of 78.2%, and specificity of 92.7% in internal-test set, and with an AUC value of 0.925, accuracy of 89.8%, sensitivity of 83.3%, and specificity of 90.6% in external-test set. The PTs were subjectively assessed twice by six radiologists, both with and without the assisted of the model. With the assisted of the model, both junior and senior radiologists demonstrated enhanced diagnostic performance. In the internal-test set, there was an increase in AUC values by 0.062 and 0.082 for junior radiologists respectively, while senior radiologists experienced an improvement of 0.066 and 0.106 in their respective AUC values. Conclusions: The DL model based on ultrasound images demonstrates exceptional capability in distinguishing between benign and malignant PTs, thereby assisting radiologists of varying expertise levels to achieve heightened diagnostic performance, and serve as a noninvasive imaging adjunct diagnostic method for clinical purposes. [ABSTRACT FROM AUTHOR]

Objectives: This study aimed to propose a deep learning (DL)–based framework for identifying the composition of thyroid nodules and assessing their malignancy risk. Methods: We conducted a retrospective multicenter study using ultrasound images from four hospitals. Convolutional neural network (CNN) models were constructed to classify ultrasound images of thyroid nodules into solid and non-solid, as well as benign and malignant. A total of 11,201 images of 6784 nodules were used for training, validation, and testing. The area under the receiver-operating characteristic curve (AUC) was employed as the primary evaluation index. Results: The models had AUCs higher than 0.91 in the benign and malignant grading of solid thyroid nodules, with the Inception-ResNet AUC being the highest at 0.94. In the test set, the best algorithm for identifying benign and malignant thyroid nodules had a sensitivity of 0.88, and a specificity of 0.86. In the human vs. DL test set, the best algorithm had a sensitivity of 0.93, and a specificity of 0.86. The Inception-ResNet model performed better than the senior physicians (p < 0.001). The sensitivity and specificity of the optimal model based on the external test set were 0.90 and 0.75, respectively. Conclusions: This research demonstrates that CNNs can assist thyroid nodule diagnosis and reduce the rate of unnecessary fine-needle aspiration (FNA). Clinical relevance statement: High-resolution ultrasound has led to increased detection of thyroid nodules. This results in unnecessary fine-needle aspiration and anxiety for patients whose nodules are benign. Deep learning can solve these problems to some extent. Key Points: • Thyroid solid nodules have a high probability of malignancy. • Our models can improve the differentiation between benign and malignant solid thyroid nodules. • The differential performance of one model was superior to that of senior radiologists. Applying this could reduce the rate of unnecessary fine-needle aspiration of solid thyroid nodules. [ABSTRACT FROM AUTHOR]

Indoor positioning plays a crucial role in various domains. It is employed in various applications, such as navigation, asset tracking, and location-based services (LBS), in Global Navigation Satellite System (GNSS) denied or degraded areas. The visual-based positioning technique is a promising solution for high-accuracy indoor positioning. However, most visual positioning research uses the side-view perspective, which is susceptible to interferences and may cause concerns about privacy and public security. Therefore, this paper innovatively proposes an up-view visual-based indoor positioning algorithm. It uses the up-view images to realize indoor positioning. Firstly, we utilize a well-trained YOLO V7 model to realize landmark detection and gross extraction. Then, we use edge detection operators to realize the precision landmark extraction, obtaining the landmark pixel size. The target position is calculated based on the landmark detection and extraction results and the pre-labeled landmark sequence via the Similar Triangle Principle. Additionally, we also propose an inertial navigation system (INS)-based landmark matching method to match the landmark within an up-view image with a landmark in the pre-labeled landmark sequence. This is necessary for kinematic indoor positioning. Finally, we conduct static and kinematic experiments to verify the feasibility and performance of the up-view-based indoor positioning method. The results demonstrate that the up-view visual-based positioning is prospective and worthy of research. [ABSTRACT FROM AUTHOR]

Apricot has a long history of cultivation and has many varieties and types. The traditional variety identification methods are timeconsuming and labor-consuming, posing grand challenges to apricot resource management. Tool development in this regard will help researchers quickly identify variety information. This study photographed apricot fruits outdoors and indoors and constructed a dataset that can precisely classify the fruits using a U-net model (F-score: 99%), which helps to obtain the fruit's size, shape, and color features. Meanwhile, a variety search engine was constructed, which can search and identify variety from the database according to the above features. Besides, a mobile and web application (ApricotView) was developed, and the construction mode can be also applied to other varieties of fruit trees. Additionally, we have collected four difficult-to-identify seed datasets and used the VGG16 model for training, with an accuracy of 97%, which provided an important basis for ApricotView. To address the difficulties in data collection bottlenecking apricot phenomics research, we developed the first apricot database platform of its kind (ApricotDIAP, http://apricotdiap.com/) to accumulate, manage, and publicize scientific data of apricot. [ABSTRACT FROM AUTHOR]

Background: Calcification is a common phenomenon in both benign and malignant thyroid nodules. However, the clinical significance of calcification remains unclear. Therefore, we explored a more objective method for distinguishing between benign and malignant thyroid calcified nodules. Methods: This retrospective study, conducted at two centers, involved a total of 631 thyroid nodules, all of which were pathologically confirmed. Ultrasound image sets were employed for analysis. The primary evaluation index was the area under the receiver-operator characteristic curve (AUROC). We compared the diagnostic performance of deep learning (DL) methods with that of radiologists and determined whether DL could enhance the diagnostic capabilities of radiologists. Results: The Xception classification model exhibited the highest performance, achieving an AUROC of up to 0.970, followed by the DenseNet169 model, which attained an AUROC of up to 0.959. Notably, both DL models outperformed radiologists (P < 0.05). The success of the Xception model can be attributed to its incorporation of deep separable convolution, which effectively reduces the model's parameter count. This feature enables the model to capture features more effectively during the feature extraction process, resulting in superior performance, particularly when dealing with limited data. Conclusions: This study conclusively demonstrated that DL outperformed radiologists in differentiating between benign and malignant calcified thyroid nodules. Additionally, the diagnostic capabilities of radiologists could be enhanced with the aid of DL. [ABSTRACT FROM AUTHOR]

The evolution of deep learning has promoted the performance of finger vein verification systems, but also brings some new issues to be resolved, including high computational burden, massive training sample demand, as well as the adaptability and generalization to various image acquisition equipment, etc. In this paper, we propose a novel and lightweight network architecture for finger vein verification, which was constructed based on a Siamese framework and embedded with a pair of eight-layer tiny ResNets as the backbone branch network. Therefore, it can maintain good verification accuracy under the circumstance of a small-scale training set. Moreover, to further reduce the number of parameters, Gabor orientation filters (GoFs) were introduced to modulate the conventional convolutional kernels, so that fewer convolutional kernels were required in the subsequent Gabor modulation, and multi-scale and orientation-insensitive kernels can be obtained simultaneously. The proposed Siamese network framework (Siamese Gabor residual network (SGRN)) embeds two parameter-sharing Gabor residual subnetworks (GRNs) for contrastive learning; the inputs are paired image samples (a reference image with a positive/negative image), and the outputs are the probabilities for accepting or rejecting. The subject-independent experiments were performed on two benchmark finger vein datasets, and the experimental results revealed that the proposed SGRN model can enhance inter-class discrepancy and intra-class similarity. Compared with some existing deep network models that have been applied to finger vein verification, our proposed SGRN achieved an ACC of 99.74 % and an EER of 0.50 % on the FV-USM dataset and an ACC of 99.55 % and an EER of 0.52 % on the MMCBNU_6000 dataset. In addition, the SGRN has smaller model parameters with only 0.21 × 10 6 Params and 1.92 × 10 6 FLOPs, outperforming some state-of-the-art FV verification models; therefore, it better facilitates the application of real-time finger vein verification. [ABSTRACT FROM AUTHOR]

A decade ago, a group of researchers from academia and industry identified a dichotomy between the industrial and academic state-of-the-art in upper-limb prosthesis control, a widely used bio-robotics application. They proposed that four key technical challenges, if addressed, could bridge this gap and translate academic research into clinically and commercially viable products. These challenges are unintuitive control schemes, lack of sensory feedback, poor robustness and single sensor modality. Here, we provide a perspective review on the research effort that occurred in the last decade, aiming at addressing these challenges. In addition, we discuss three research areas essential to the recent development in upper-limb prosthetic control research but were not envisioned in the review 10 years ago: deep learning methods, surface electromyogram decomposition and open-source databases. To conclude the review, we provide an outlook into the near future of the research and development in upper-limb prosthetic control and beyond. This is a perspective review of the last ten years of translational research and development efforts in non-invasive neural interfaces and robotics for practical and clinical applications of upper-limb prosthetics. [ABSTRACT FROM AUTHOR]

Currently, glioma and esophageal cancer are common malignant tumors worldwide with low cure rate and high mortality rate, and they endanger human health seriously. In this study, we analyzed the correlation and difference between glioma and esophageal cancer through serum mid‐infrared and Raman spectra and established a multi‐channel gradient feature fusion convolutional neural network to achieve rapid diagnosis of glioma and esophageal cancer patients. We transformed the spectra from one‐dimensional matrix to two‐dimensional matrix form separately as the input of the network and fused the features extracted from the Flatten layer of the network. First, we fused the features of mid‐infrared and Raman spectra and constructed a two‐channel gradient feature fusion idea. Then, in order to enrich the learning of features further, we took the first‐order derivative of mid‐infrared and Raman original spectra, respectively, and used the derivative spectra as two channels as well. The mid‐infrared and Raman spectra in two‐dimensional matrix form were fused with their derivative spectral features, respectively, and the fused features were fused again to construct a four‐channel gradient feature fusion network model. Finally, compared with the single original spectrum and the one‐dimensional matrix feature fusion spectrum, the two‐dimensional matrix feature fused spectrum was more advantageous, and the classification accuracy of the model was as high as 99.2% ± 0.7%. This study showed that two‐dimensional matrix spectra combined with multi‐channel gradient feature fusion technique had great potential for rapid and accurate identification of patients with glioma and esophageal cancer. [ABSTRACT FROM AUTHOR]

As an emerging technology for artificial intelligence‐aided medical diagnosis, deep learning combined with Raman spectroscopy has great potential. The technology still has some problems in the actual medical diagnosis research process. The differences in spectrometers, experimental conditions, and experimental operations can result in non‐uniform and universally applicable data standards, which in turn lead to low data utilization. At the same time, it is still necessary to retrain the models when building diagnostic models for different diseases, which is time‐consuming and laborious. In this paper, a more complete transfer learning model for multiple types of serum Raman spectra is established for the first time, and a decision fusion strategy is applied to this diagnostic model. The Raman spectral data of serum from hepatitis B patients/control group, serum from abnormal thyroid function patients/control group, and serum from glioma patients/control group were selected as the source domains, and the Raman spectral data of tissue from hepatitis C patients/control group, serum from esophageal cancer patients/control group, and tissue from cervical cancer and cervical inflammation (patients/control) group were selected as the target domains. Three deep neural network models, ResNet, GoogLeNet, and CNN‐LSTM were trained in the source domain data for disease diagnosis, and the trained models were transfer to the target domain. The model is fine‐tuned by freezing different layers and then combined with logistic regression algorithms to construct a decision fusion model, which further improves the model effect. The results show that the proposed method can effectively improve the accuracy of transfer learning models. At the same time, this experiment extends the application of transfer learning in Raman spectroscopy and demonstrates that unrelated and scale‐different Raman datasets are still intrinsically connected, which also lays the foundation for us to build more stable and data‐inclusive spectral transfer learning fusion models in the future. [ABSTRACT FROM AUTHOR]

Water conservancy personnel usually need to know the water level by water gauge images in real-time and with an expected accuracy. However, accurately recognizing the water level from water gauge images is still a complex problem. This article proposes a composite method applied in the Wuyuan City, Jiangxi Province, in China. This method can detect water gauge areas and number areas from complex and changeable scenes, accurately detect the water level line from various water gauges, and finally, obtain the accurate water level value. Firstly, FCOS is improved by fusing a contextual adjustment module to meet the requirements of edge computing and ensure considerable detection accuracy. Secondly, to deal with scenes with indistinct water level features, we also apply the contextual adjustment module for Deeplabv3+ to segment the water gauge area above the water surface. Then, the area can be used to obtain the position of the water level line. Finally, the results of the previous two steps are combined to calculate the water level value. Detailed experiments prove that this method solves the problem of water level recognition in complex hydrological scenes. Furthermore, the recognition error of the water level by this method is less than 1 cm, proving it is capable of being applied in real river scenes. [ABSTRACT FROM AUTHOR]

Hadoop is a popular computing framework designed to deliver timely and cost-effective data processing on a large cluster of commodity machines. It relieves the burden of the programmers dealing with distributed programming, and an ecosystem of Big Data solutions has developed around it. However, Hadoop's job execution time can greatly depend on its runtime configurations and resource selections. Given the more than 100 job configuration settings provided by Hadoop, and diverse resource instance options in a cloud or virtualized computing environment, running Hadoop jobs still requires a substantial amount of expertise and experience. To address this challenge, we apply a deep neural network to predict Hadoop's job time based on historical execution data, and propose optimization methods to reduce job execution time and cost. The results show that our prediction method achieves almost 90% time prediction accuracy and clearly outperforms three other state-of-the-art regression-based prediction methods. Based on the time prediction, our proposed configuration search method and job scheduling algorithm successfully shorten the execution time of a single Hadoop job by more than a factor of 2 and reduce the time of processing a batch of Hadoop jobs by 40%∼65%. • We aim to optimize the performance and cost of running Hadoop MapReduce workload in a cloud environment with on-demand resources. • We propose a deep learning approach to predict the execution time of MapReduce jobs under any given resource allocation and Hadoop configuration setting. • We proposed a 2-step approximate search algorithm for finding the optimal resource allocation and execution configuration of individual job, and a 2D variable size bin packing algorithm for maximize overall resource utilization. • The experiment results show that our prediction method achieved almost 90% of time prediction accuracy and clearly out-performed three other state-of-art machine learning prediction methods. • Our optimization strategies successfully shorten the execution time of a single Hadoop job by more than a factor of 2 and reduce the time of processing a batch of Hadoop jobs by 40%∼65%. [ABSTRACT FROM AUTHOR]

Atmospheric effects are among the primary error sources affecting the accuracy of interferometric synthetic aperture radar (InSAR). The topography-dependent atmospheric effect is particularly noteworthy in reservoir areas for landslide monitoring utilizing InSAR, which must be effectively corrected to complete the InSAR high-accuracy measurement. This paper proposed a topography-dependent atmospheric correction method based on the Multi-Layer Perceptron (MLP) neural network model combined with topography and spatial data information. We used this proposed approach for the atmospheric correction of the interferometric pairs of Sentinel-1 images in the Baihetan dam. We contrasted the outcomes with those obtained using the generic atmospheric correction online service for InSAR (GACOS) correction and the traditional linear model correction. The results indicated that the MLP neural network model correction reduced the phase standard deviation of the Sentinel-1 interferogram by an average of 64% and nearly eliminated the phase-elevation correlation. Both comparisons outperformed the GACOS correction and the linear model correction. Through two real-world examples, we demonstrated how slopes with displacements, which were previously obscured by a significant topography-dependent atmospheric delay, could be successfully and clearly identified in the interferograms following the correction by the MLP neural network. The topography-dependent atmosphere can be better corrected using the MLP neural network model suggested in this paper. Unlike the previous model, this proposed approach could be adjusted to fit each interferogram, regardless of how much of the topography-dependent atmosphere was present. In order to improve the effectiveness of DInSAR and time-series InSAR solutions, it can be applied immediately to the interferogram to retrieve the effective displacement information that cannot be identified before the correction. [ABSTRACT FROM AUTHOR]

Magnetic Resonance Imaging (MRI) has been proven to be an efficient way to diagnose Alzheimer’s disease (AD). Recent dramatic progress on deep learning greatly promotes the MRI analysis based on data-driven CNN methods using a large-scale longitudinal MRI dataset. However, most of the existing MRI datasets are fragmented due to unexpected quits of volunteers. To tackle this problem, we propose a novel Temporal Recurrent Generative Adversarial Network (TR-GAN) to complete missing sessions of MRI datasets. Unlike existing GAN-based methods, which either fail to generate future sessions or only generate fixed-length sessions, TR-GAN takes all past sessions to recurrently and smoothly generate future ones with variant length. Specifically, TR-GAN adopts recurrent connection to deal with variant input sequence length and flexibly generate future variant sessions. Besides, we also design a multiple scale & location (MSL) module and a SWAP module to encourage the model to better focus on detailed information, which helps to generate high-quality MRI data. Compared with other popular GAN architectures, TR-GAN achieved the best performance in all evaluation metrics of two datasets. After expanding the Whole MRI dataset, the balanced accuracy of AD vs. cognitively normal (CN) vs. mild cognitive impairment (MCI) and stable MCI vs. progressive MCI classification can be increased by 3.61% and 4.00%, respectively. [ABSTRACT FROM AUTHOR]

Lung cancer and glioma are common malignancies worldwide and pose a serious threat to human health. There may be a certain correlation between lung cancer patients and glioma patients in serum composition, but to date, no study on the classification and correlation of lung cancer and glioma is available. In this paper, the differences and relationships between lung cancer and glioma were analyzed from serum Raman spectra. The existing detection methods of lung cancer and glioma are time consuming and expensive, so we propose a method based on patient serum Raman spectra combined with deep learning, which can screen lung cancer and glioma accurately with speed and low cost. In this study, features were extracted from the original spectral data of patients with lung cancer, glioma, and control subjects. By adding different decibels of white Gaussian noise to the training set for data enhancement, the enhanced training set data were imported into a multilayer perceptron (MLP), recursive neural network (RNN), convolutional neural network (CNN), and AlexNet using fivefold cross‐validation to build the diagnostic model. The results show that PLS‐AlexNet is the best model. The accuracy of this model in the binary classification experiment of lung cancer and control subjects, lung cancer and glioma, and glioma and control subjects were 99%, 95.2%, and 100%, respectively, and the experimental accuracy of the AlexNet triclassification algorithm is also above 85%. This method has great potential in clinical diagnosis of diseases. [ABSTRACT FROM AUTHOR]

In recent years, deep learning has been widely used in breast cancer diagnosis, and many high-performance models have emerged. However, most of the existing deep learning models are mainly based on static breast ultrasound (US) images. In actual diagnostic process, contrast-enhanced ultrasound (CEUS) is a commonly used technique by radiologists. Compared with static breast US images, CEUS videos can provide more detailed blood supply information of tumors, and therefore can help radiologists make a more accurate diagnosis. In this paper, we propose a novel diagnosis model based on CEUS videos. The backbone of the model is a 3D convolutional neural network. More specifically, we notice that radiologists generally follow two specific patterns when browsing CEUS videos. One pattern is that they focus on specific time slots, and the other is that they pay attention to the differences between the CEUS frames and the corresponding US images. To incorporate these two patterns into our deep learning model, we design a domain-knowledge-guided temporal attention module and a channel attention module. We validate our model on our Breast-CEUS dataset composed of 221 cases. The result shows that our model can achieve a sensitivity of 97.2% and an accuracy of 86.3%. In particular, the incorporation of domain knowledge leads to a 3.5% improvement in sensitivity and a 6.0% improvement in specificity. Finally, we also prove the validity of two domain knowledge modules in the 3D convolutional neural network (C3D) and the 3D ResNet (R3D). [ABSTRACT FROM AUTHOR]

In this paper, we introduce a deep learning aided constraint encoding method to tackle the frequency-constraint microgrid scheduling problem. The nonlinear function between system operating condition and frequency nadir is approximated by using a neural network, which admits an exact mixed-integer formulation (MIP). This formulation is then integrated with the scheduling problem to encode the frequency constraint. With the stronger representation power of the neural network, the resulting commands can ensure adequate frequency response in a realistic setting in addition to islanding success. The proposed method is validated on a modified 33-node system. Successful islanding with a secure response is simulated under the scheduled commands using a detailed three-phase model in Simulink. The advantages of our model are particularly remarkable when the inertia emulation functions from wind turbine generators are considered. [ABSTRACT FROM AUTHOR]

Diabetic kidney disease (DKD) is one of the most common kidney diseases worldwide. It is estimated that approximately 537 million adults worldwide have diabetes, and up to 30%–40% of diabetic patients are at risk of developing nephropathy. The pathogenesis of DKD is complex, and its onset is insidious. Currently, the clinical diagnosis of DKD primarily relies on the increase of urinary albumin and the decrease in glomerular filtration rate in diabetic patients. However, the excretion of urinary albumin is influenced by various factors, such as physical activity, infections, fever, and high blood glucose, making it challenging to achieve an objective and accurate diagnosis. Therefore, there is an urgent need to develop an efficient, fast, and low-cost auxiliary diagnostic technology for DKD. In this study, an improved Dual Branch Attention Network (DBAN) was developed to quickly identify DKD. Serum Raman spectroscopy samples were collected from 32 DKD patients and 32 healthy volunteers. The collected data were preprocessed using the adaptive iteratively reweighted penalized least squares (airPLS) algorithm, and the DBAN was used to classify the serum Raman spectroscopy data of DKD. The model consists of a dual branch structure that extracts features using Convolutional Neural Network (CNN) and bottleneck layer modules. The attention module allows the model to learn features specifically, and lateral connections are added between the dual branches to achieve multi-level and multi-scale fusion of shallow and deep features, as well as local and global features, improving the classification accuracy of the experiment. The results of the study showed that compared to traditional deep learning algorithms such as Artificial Neural Network (ANN), CNN, GoogleNet, ResNet, and AlexNet, our proposed DBAN classification model achieved 95.4% accuracy, 98.0% precision, 96.5% sensitivity, and 97.2% specificity, demonstrating the best classification performance. This is the best method for identifying DKD, and has important reference value for the diagnosis of DKD patients, as well as improving the accuracy of medical auxiliary diagnosis. [Display omitted] • A new dual branch attention network (DBAN) is proposed. • The dual branch combines different attention mechanisms to achieve multi-level and multi-scale fusion. • The DBAN model achieves excellent classification performance for diabetic kidney disease diagnosis. [ABSTRACT FROM AUTHOR]

Purpose: The application of deep learning methods to the intelligent diagnosis of diseases has been the focus of intelligent medical research. When dealing with image classification tasks, if the lesion area is small and uneven, the background image involved in the training will affect the ultimate accuracy in determining the extent of the lesion. We did not follow the traditional approach of building an intelligent system to assist physicians in diagnosis from the perspective of CNN models, but instead proposed a pure transformer framework that can be used for diagnostic grading of pathological images. Methods: We propose a Symmetric Mask Pre-Training vision Transformer SMiT model for grading pathological cancer images. SMiT performs a symmetrically identical high probability sparsification of the input image token sequence at the first and last encoder layer positions to pre-train visual transformers, and the parameters of the baseline model are fine-tuned after loading the pre-training weights, allowing the model to concentrate more on extracting detailed features in the lesion region, effectively getting rid of the potential feature dependency problem. Results: SMiT achieved 92.8% classification accuracy on 4500 histopathological images of colorectal cancer processed by Gaussian filter denoising. We validated the effectiveness and generalizability of this study's methodology on the publicly available diabetic retinopathy dataset APTOS2019 from Kaggle and achieved quadratic Cohen Kappa, accuracy and F1-score of 91.9%, 86.91% and 72.85%, respectively, which were 1–2% better than previous studies based on CNN models. Conclusion: SMiT uses a simpler strategy to achieve better results to assist physicians in making accurate clinical decisions, which can be an inspiration for making good use of the visual transformers in the field of medical imaging. [ABSTRACT FROM AUTHOR]

[Display omitted] • Differences in the biochemical composition of five types of cervical tissue were analyzed. • A multi-layered attention mechanism feature fusion architecture (MAFA) is proposed. • MAFA can effectively improve the classification accuracy of deep learning models for tissue samples. • MAFA as a model building method can be easily combined with a variety of deep learning models. Cervical cancer ranks among the most prevalent forms of gynecological malignancies. Timely identification of cervical lesions and prompt intervention can effectively prevent the development of cervical cancer or enhance patients' chances of survival. In this study, we propose an innovative method based on Raman spectroscopy, i.e., a multi-level SENet attention mechanism feature fusion architecture (MAFA) for rapid diagnosis of cervical cancer and precancerous lesions. The convolution process of this architecture can extract features from shallow to deep layers, and the attention mechanism is added to achieve the fusion of features from different layers. The added attention mechanism can automatically determine the importance of each layer feature channel and assign weight values to that layer according to the importance of each layer to achieve the purpose of focusing the model on certain waveform features and improve the targeting of model learning. We collected Raman spectra of 212 cervical tissues containing cervical cancer and its precancerous lesions.The experimental results show that MAFA can effectively improve the diagnostic accuracy of VGGNet, GoogLeNet and ResNet models in the validation of Raman spectral data of cervical tissue. Among them, ResNet performed the best, with the highest average accuracy, precision, recall and F1-Score of 82.36%, 84.00%, 82.35% and 82.26%, respectively, when no feature fusion was performed. The evaluation metrics improved by 4.91%, 3.97%, 4.97%, and 5.06%, respectively, after using the MAFA; they also improved by 4.16%, 2.90%, 4.17%, and 4.32%, respectively, compared with the model that directly performs feature fusion without using the attention mechanism. Therefore, the MAFA proposed in this study is better than that of the neural network that directly fuses the features of each convolutional layer. The experimental results show that the performance of the MAFA proposed in this paper is significantly higher than that of traditional deep learning algorithms, indicating that the present architecture can effectively improve the diagnostic accuracy of deep learning networks for cervical cancer. [ABSTRACT FROM AUTHOR]

Protein fold recognition is one of the most critical tasks to explore the structures and functions of the proteins based on their primary sequence information. The existing protein fold recognition approaches rely on features reflecting the characteristics of protein folds. However, the feature extraction methods are still the bottleneck of the performance improvement of these methods. In this paper, we proposed two new feature extraction methods called MotifCNN and MotifDCNN to extract more discriminative fold-specific features based on structural motif kernels to construct the motif-based convolutional neural networks (CNNs). The pairwise sequence similarity scores calculated based on fold-specific features are then fed into support vector machines to construct the predictor for fold recognition, and a predictor called MotifCNN-fold has been proposed. Experimental results on the benchmark dataset showed that MotifCNN-fold obviously outperformed all the other competing methods. In particular, the fold-specific features extracted by MotifCNN and MotifDCNN are more discriminative than the fold-specific features extracted by other deep learning techniques, indicating that incorporating the structural motifs into the CNN is able to capture the characteristics of protein folds. [ABSTRACT FROM AUTHOR]

Protein fold recognition is critical for studying the structures and functions of proteins. The existing protein fold recognition approaches failed to efficiently calculate the pairwise sequence similarity scores of the proteins in the same fold sharing low sequence similarities. Furthermore, the existing feature vectorization strategies are not able to measure the global relationships among proteins from different protein folds. In this article, we proposed a new computational predictor called DeepSVM-fold for protein fold recognition by introducing a new feature vector based on the pairwise sequence similarity scores calculated from the fold-specific features extracted by deep learning networks. The feature vectors are then fed into a support vector machine to construct the predictor. Experimental results on the benchmark dataset (LE) show that DeepSVM-fold obviously outperforms all the other competing methods. [ABSTRACT FROM AUTHOR]

Monitoring pig drinking has been a topic of interest to pig researchers and producers for many years. However, challenges still remain due to the fact that pigs like to play with drinkers in nursery environments and that the drinking pig is often touching others. These factors negatively influence the performance of camera-based pig drinking detection algorithms. The aim of this study is to investigate a deep learning method based on convolutional neural network (CNN) and long short-term memory (LSTM) to classify drinking and drinker-playing. In the experiment, two pens of pigs were video recorded for 3 days. In video from the first pen, 5400 2 s drinking episodes and 5400 2 s drinker-playing episodes were generated with 80% of these data being allocated as training set and the remaining 20% as validation set. In video from the second pen, 12,000 2 s drinking and drinker-playing episodes were generated as a test set. Firstly, the CNN architecture ResNet50 was used to extract spatial features. These features were input into LSTM framework to extract spatial–temporal features. Through the fully connected layer, the prediction function Softmax was finally used to classify these drinking and drinker-playing episodes. In the test set, the classification accuracy in the body and head regions of interest was 87.2% and 92.5%, respectively. The results indicate that the proposed method can be used to classify pigs' drinking and drinker-playing. These classification results have potential to improve the accuracy of pig drinking detection and help farmers to estimate pig welfare. • A novel video-based deep learning method was used to study pig drinking behaviour. • Long short-term memory was used to extract the spatial–temporal features. • Classification accuracy in the body and head regions of interest was 87.2% and 92.5%. • Drinking behaviour can be detected under conditions of pigs touching and overlapping. • Shortening the region of interest can be used to improve the classification accuracy. [ABSTRACT FROM AUTHOR]

In zero-shot learning, attributes play as a bridge from original images to class labels. Therefore, to achieve accurate zero-shot image classification, we mainly focus on improving attribute prediction accuracy by taking full advantage of prior information about attribute from two aspects. First, we present a new attribute classifier called deep attribute prediction (DeepAP) model by using supervised deep convolutional neural networks (DCNNs), where the attribute label information participates in the training of DCNNs. Unlike common DCNNs that are usually used to extract image features, the constructed DCNNs are used to directly predict attribute values from the original input images. Thus, the designed DeepAP model can serve as the mapping from low-level image features to high-level semantic attributes in the traditional direct attribute prediction (DAP) model. Second, another prior information about attribute, i.e., class-attribute matrix is used to mine the attribute-class correlation with sparse representation coefficients. Since the attribute-class correlation can reflect different contributions of attributes to classification, we use it to define attribute weights and incorporate the idea of weighted attributes into DeepAP to form the deep weighted attribute prediction (DWAP) model. Experiments on three real datasets show that DWAP outperforms the deep attribute network and DAP on attribute prediction and zero-shot image classification. [ABSTRACT FROM AUTHOR]

In recent years, Raman spectroscopy combined with deep learning techniques has been widely used in various fields such as medical, chemical, and geological. However, there is still room for optimization of deep learning techniques and model compression algorithms for processing Raman spectral data. To further optimize deep learning models applied to Raman spectroscopy, in this study time, accuracy, sensitivity, specificity and floating point operations numbers(FLOPs) are used as evaluation metrics to optimize the model, which is named RamanCompact(RamanCMP). The experimental data used in this research are selected from the RRUFF public dataset, which consists of 723 Raman spectroscopy data samples from 10 different mineral categories. In this paper, 1D-EfficientNet adapted to the spectral data as well as 1D-DRSN are proposed to improve the model classification accuracy. To achieve better classification accuracy while optimizing the time parameters, three model compression methods are designed: knowledge distillation using 1D-EfficientNet model as a teacher model to train convolutional neural networks(CNN), proposing a channel conversion method to optimize 1D-DRSN model, and using 1D-DRSN model as a feature extractor in combination with linear discriminant analysis(LDA) model for classification. Compared with the traditional LDA and CNN models, the accuracy of 1D-EfficientNet and 1D-DRSN is improved by more than 20%. The time of the distilled model is reduced by 9680.9s compared with the teacher model 1D-EfficientNet under the condition of losing 2.07% accuracy. The accuracy of the distilled model is improved by 20% compared to the CNN student model while keeping inference efficiency constant. The 1D-DRSN optimized with channel conversion method saves 60% inference time of the original 1D-DRSN model. Feature extraction reduces the inference time of 1D-DRSN model by 93% with 94.48% accuracy. This study innovatively combines lightweight models and model compression algorithms to improve the classification speed of deep learning models in the field of Raman spectroscopy, forming a complete set of analysis methods and laying the foundation for future research. [Display omitted] • Proposed RamanCMP, a Raman spectral classification acceleration method. • Proposed 1D-EfficientNet and 1D-DRSN for spectral data. • Proposed channel conversion method and 1D-DRSN feature extractor. • Testing RamanCMP using the RRUFF public dataset and the external validation dataset for Sjögren's syndrome. [ABSTRACT FROM AUTHOR]

Distributed training is needed to shorten the training time of deep neural networks. However, the communication overhead often hurts performance efficiency, especially in a distributed computing environment with limited network bandwidth. Hence, gradient compression techniques have been proposed to reduce communication time. But, compression also has the risk of causing lower model accuracy and longer training time due to compression loss and compression time. As a result, compression may not consistently achieve desired results, and there are limited discussions on when and which compression should be used. To address this problem, we propose a performance-driven hybrid compression solution. We make three main contributions. (1) We describe a hybrid compression strategy that chooses the compression method for individual model gradients. (2) We build an offline performance estimator and an online loss monitor to ensure the compression decision can minimize training time without sacrificing mode accuracy. (3) Our implementation can be imported to existing deep learning frameworks and applicable to a wide range of compression methods. Up to 3.6x training performance speedup was observed compared to other state-of-the-art methods. • Our goal is to constrict a better compression strategy for training a DNN model in distributed computing environment. • Our proposed compression strategy is fine-grained, hybrid and performance-driven. • Our method is built based on an offline performance estimator, an online loss monitor, and a linear search time optimization algorithm. • Our approach is implemented as a lightweight library that can be imported to existing deep learning frameworks. • Our evaluations show that we achieved up to 3.6x training performance speedup compared to other compression methods. [ABSTRACT FROM AUTHOR]

The aim of this study is to develop AI-assisted software incorporating a deep learning (DL) model based on static ultrasound images. The software aims to aid physicians in distinguishing between malignant and benign thyroid nodules with echogenic foci and to investigate how the AI-assisted DL model can enhance radiologists' diagnostic performance. For this retrospective study, a total of 2724 ultrasound (US) scans were collected from two independent institutions, encompassing 1038 echogenic foci nodules. All echogenic foci were confirmed by pathology. Three DL segmentation models (DeepLabV3+, U-Net, and PSPNet) were developed, with each model using two different backbones to extract features from the nodular regions with echogenic foci. Evaluation indexes such as Mean Intersection over Union (MIoU), Mean Pixel Accuracy (MPA), and Dice coefficients were employed to assess the performance of the segmentation model. The model demonstrating the best performance was selected to develop the AI-assisted diagnostic software, enabling radiologists to benefit from AI-assisted diagnosis. The diagnostic performance of radiologists with varying levels of seniority and beginner radiologists in assessing high-echo nodules was then compared, both with and without the use of auxiliary strategies. The area under the receiver operating characteristic curve (AUROC) was used as the primary evaluation index, both with and without the use of auxiliary strategies. In the analysis of Institution 2, the DeepLabV3+ (backbone is MobileNetV2 exhibited optimal segmentation performance, with MIoU = 0.891, MPA = 0.945, and Dice = 0.919. The combined AUROC (0.693 [95% CI 0.595–0.791]) of radiology beginners using AI-assisted strategies was significantly higher than those without such strategies (0.551 [0.445–0.657]). Additionally, the combined AUROC of junior physicians employing adjuvant strategies improved from 0.674 [0.574–0.774] to 0.757 [0.666–0.848]. Similarly, the combined AUROC of senior physicians increased slightly, rising from 0.745 [0.652–0.838] to 0.813 [0.730–0.896]. With the implementation of AI-assisted strategies, the accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of both senior physicians and beginners in the radiology department underwent varying degrees of improvement. This study demonstrates that the DL-based auxiliary diagnosis model using US static images can improve the performance of radiologists and radiology students in identifying thyroid echogenic foci. [ABSTRACT FROM AUTHOR]

Quantifying uncertainty of predictions has been identified as one way to develop more trustworthy artificial intelligence (AI) models beyond conventional reporting of performance metrics. When considering their role in a clinical decision support setting, AI classification models should ideally avoid confident wrong predictions and maximise the confidence of correct predictions. Models that do this are said to be well calibrated with regard to confidence. However, relatively little attention has been paid to how to improve calibration when training these models, i.e. to make the training strategy uncertainty-aware. In this work we: (i) evaluate three novel uncertainty-aware training strategies with regard to a range of accuracy and calibration performance measures, comparing against two state-of-the-art approaches, (ii) quantify the data (aleatoric) and model (epistemic) uncertainty of all models and (iii) evaluate the impact of using a model calibration measure for model selection in uncertainty-aware training, in contrast to the normal accuracy-based measures. We perform our analysis using two different clinical applications: cardiac resynchronisation therapy (CRT) response prediction and coronary artery disease (CAD) diagnosis from cardiac magnetic resonance (CMR) images. The best-performing model in terms of both classification accuracy and the most common calibration measure, expected calibration error (ECE) was the Confidence Weight method, a novel approach that weights the loss of samples to explicitly penalise confident incorrect predictions. The method reduced the ECE by 17% for CRT response prediction and by 22% for CAD diagnosis when compared to a baseline classifier in which no uncertainty-aware strategy was included. In both applications, as well as reducing the ECE there was a slight increase in accuracy from 69% to 70% and 70% to 72% for CRT response prediction and CAD diagnosis respectively. However, our analysis showed a lack of consistency in terms of optimal models when using different calibration measures. This indicates the need for careful consideration of performance metrics when training and selecting models for complex high risk applications in healthcare. [Display omitted] • Propose three novel uncertainty-aware training strategies. • Compare with state-of-the-art methods on two medical image classification tasks. • Report a wide range of accuracy and calibration performance measures. • Quantify performance of all models in terms of aleatoric and epistemic uncertainty. • Evaluate use of calibration-based model selection on accuracy and calibration. [ABSTRACT FROM AUTHOR]

In steerable filters, a filter of arbitrary orientation can be generated by a linear combination of a set of “basis filters.” Steerable properties dominate the design of the traditional filters, e.g., Gabor filters and endow features the capability of handling spatial transformations. However, such properties have not yet been well explored in the deep convolutional neural networks (DCNNs). In this paper, we develop a new deep model, namely, Gabor convolutional networks (GCNs or Gabor CNNs), with Gabor filters incorporated into DCNNs such that the robustness of learned features against the orientation and scale changes can be reinforced. By manipulating the basic element of DCNNs, i.e., the convolution operator, based on Gabor filters, GCNs can be easily implemented and are readily compatible with any popular deep learning architecture. We carry out extensive experiments to demonstrate the promising performance of our GCNs framework, and the results show its superiority in recognizing objects, especially when the scale and rotation changes take place frequently. Moreover, the proposed GCNs have much fewer network parameters to be learned and can effectively reduce the training complexity of the network, leading to a more compact deep learning model while still maintaining a high feature representation capacity. The source code can be found at https://github.com/bczhangbczhang. [ABSTRACT FROM AUTHOR]

Focusing on the low accuracy and timeliness of traditional fault diagnosis methods for rolling bearings which combine massive amounts of data, a fault diagnosis method for rolling bearings based on Gramian angular field (GAF) coding technology and an improved ResNet50 model is proposed. Using the Graham angle field technology to recode the one-dimensional vibration signal into a two-dimensional feature image, using the two-dimensional feature image as the input for the model, combined with the advantages of the ResNet algorithm in image feature extraction and classification recognition, we realized automatic feature extraction and fault diagnosis, and, finally, achieved the classification of different fault types. In order to verify the effectiveness of the method, the rolling bearing data of Casey Reserve University are selected for verification, and compared with other commonly used intelligent algorithms, the results show that the proposed method has a higher classification accuracy and better timeliness than other intelligent algorithms. [ABSTRACT FROM AUTHOR]

As a highly prevalent and recurrent cancer, detecting the degree of differentiation in oral cancer is crucial. Current methods rely on biopsies in the presence of significant lesions, which are time-consuming. This study introduces an efficient and rapid approach for mass determination of oral cancer differentiation levels. By leveraging serum Raman spectroscopy combined with deep neural networks and extreme gradient boosting, we performed feature selection and interaction on oral cancer samples of varying differentiation levels, achieving the most accurate and reliable classification of oral cancer differentiation stages. [ABSTRACT FROM AUTHOR]

Recently, the deep learning schemes have been well investigated for improving the driving safety and efficiency in the transportation systems. In this paper, a probabilistic model named as CPGN (Collision Prediction model based on GA-optimized Neural Network) for decision-making in the rear-end collision avoidance system is proposed, targeting modeling the impact of important influential factors of collisions on the occurring probability of possible accidents in the Internet of Vehicles (IoV). The decision on how to serve the chauffeur is determined by a typical deep learning model, i.e., the BP neural network through evaluating the possible collision risk with V2I (Vehicle-to-Infrastructure) communication, V2V (Vehicle-to-Vehicle) communication and GPS infrastructure supporting. The proper structure of our BP neural network model is deeply learned with training data generated from VISSIM with multiple influential factors considered. In addition, since the selection of the connection coefficient array and thresholds of the neural network has great randomness, a local optimization issue is readily occurring during the modeling procedure. To overcome this problem and consider the ability to efficiently find out a global optimization, this paper chooses the genetic algorithm to optimize the coefficient array and thresholds of proposed neural network. For the purpose of enhancing the convergence speed of the proposed model, we further adjust the studying rate according to the relationship between the actual and predicated values of two adjacent iterations. Simulation results demonstrate that the proposed collision risk evaluation framework could offer rationale estimations to the possible collision risk in car-following scenarios for the next discrete monitoring interval. [ABSTRACT FROM AUTHOR]

Monitoring the fatigue of construction equipment operators (CEOs) is critical for preventing accidents and ensuring precision construction occupational health and safety (COHS). However, there exists a theoretical dilemma between centralized technical efficiency and decentralized data privacy. Thus, this study introduces smart work package learning (SWPL), a decentralized deep learning approach to monitor CEOs' fatigue without privacy exposure risks. To illustrate the feasibility of SWPL as the fatigue classifier, this study implements fatigue monitoring through noninvasive facial images, and SWPL merges the updated parameters of the model from each smart work package (SWP). These updates are then validated by SWPs in the blockchain network and stored on the blockchain. More than 356 videos were derived from 124 operators. The results present that SWPL on decentralized SWP networks outperforms the deep learning model on individual SWP. The computational novelty is SWPL's dynamic parameter aggregation mechanism to avoid parameter exposure in centralized or fixed aggregators. The proposed SWPL will open up advanced developments in precision COHS. [ABSTRACT FROM AUTHOR]

In the past two decades, robotics in construction (RiC) has become an interdisciplinary research field that integrates a large number of urgent technologies (e.g., additive manufacturing, deep learning, building information modelling (BIM)), resulting in the related literature being both fragmented and vast. This paper has explored the advances in RiC in the past two decades using a mixed quantitative-qualitative review method. Initially, 940 related articles (170 journal articles and 770 conference papers) were identified by keyword-searching in Scopus and then fed into a bibliometric analysis to build science maps. Following this, a qualitative discussion highlights recent achievements in RiC across three dimensions: tasks, algorithms, and collaborations. Moreover, four future research directions are proposed: 1) in-depth integration of BIM and robotics; 2) near-site robotic fabrication; 3) deep reinforcement learning for flexible environment adaption; and 4) high-level robot-to-robot collaboration. The contributions of this research are twofold: 1) identifying the latest research topics and trends concerning robotic technologies in construction; and 2) providing in-depth insights into the future direction of RiC. The findings from this research can serve both academia and industry in terms of promoting robotic algorithms, hardware, and applications in construction industry. [Display omitted] • A mixed-method review of literature of robotics in construction since 21 century. • A bibliometric analysis was used to conduct publication cluster and research cluster analysis. • A qualitative analysis was performed to present the hot topics in the research areas. • Four potential research directions are proposed for robotics in construction. [ABSTRACT FROM AUTHOR]

Intelligent monitoring and early warning of rock mass failure is vital. To realize the early intelligent identification of dynamic fractures in the failure process of complex fractured rocks, 3D printing of the fracture network model was used to produce rock-like specimens containing 20 random joints. An algorithm for the early intelligent identification of dynamic fractures was proposed based on the YOLOv5 deep learning network model and DIC cloud. The results demonstrate an important relationship between the overall strength of the specimen with complex fractures and dynamic fracture propagation, and the overall specimen strength can be judged semi-quantitatively by counting dynamic fracture propagation. Before the initiation of each primary fracture, a strain concentration area appears, which indicates new fracture initiation. The dynamic evolution of primary fractures can be divided into four types: primary fractures, stress concentration areas, new fractures, and cross fractures. The cross fractures have the greatest impact on the overall strength of the specimen. The overall identification accuracy of the four types of fractures identified by the algorithm reached 88%, which shows that the method is fast, accurate, and effective for fracture identification and location, and classification of complex fractured rock masses. [ABSTRACT FROM AUTHOR]

Fully-supervised deep learning segmentation models are inflexible when encountering new unseen semantic classes and their fine-tuning often requires significant amounts of annotated data. Few-shot semantic segmentation (FSS) aims to solve this inflexibility by learning to segment an arbitrary unseen semantically meaningful class by referring to only a few labeled examples, without involving fine-tuning. State-of-the-art FSS methods are typically designed for segmenting natural images and rely on abundant annotated data of training classes to learn image representations that generalize well to unseen testing classes. However, such a training mechanism is impractical in annotation-scarce medical imaging scenarios. To address this challenge, in this work, we propose a novel self-supervised FSS framework for medical images, named SSL-ALPNet, in order to bypass the requirement for annotations during training. The proposed method exploits superpixel-based pseudo-labels to provide supervision signals. In addition, we propose a simple yet effective adaptive local prototype pooling module which is plugged into the prototype networks to further boost segmentation accuracy. We demonstrate the general applicability of the proposed approach using three different tasks: organ segmentation of abdominal CT and MRI images respectively, and cardiac segmentation of MRI images. The proposed method yields higher Dice scores than conventional FSS methods which require manual annotations for training in our experiments. [ABSTRACT FROM AUTHOR]

Medical diagnosis technology based on convolutional neural networks (CNNs) has achieved good performance. In this study, we collected serum samples from 38 glioma patients and 45 healthy controls and used partial least squares (PLS) analysis to reduce the dimension of the data. Different levels of noise were added to the reduced data onto data augmentation, and the AlexNet, ResNet, and GoogLeNet fine‐tuning models were applied for classification. To evaluate the performance of the models, we used five‐fold cross‐validation. The accuracy rates of the AlexNet, ResNet, and GoogLeNet fine‐tuning models were 98.50%, 98.24%, and 99.50%, respectively. The model with the best classification effect was GoogLeNet. The specificity and sensitivity of this model were 98.98% and 98.48%, respectively. In addition, the area under the receiver operating characteristic (ROC) curve (AUC) of the established diagnostic model was 0.9949. The results showed that the combination of serum Raman spectroscopy and the PLS‐Gaussian‐GoogLeNet model achieved a good diagnostic effect for glioma. This method has high clinical application value and is worthy of further popularization. [ABSTRACT FROM AUTHOR]

In recent years, liver cancer has caused great harm to human health. This study aims to use serum Raman spectroscopy combined with deep learning algorithms to classify liver cancer patients and control groups. For improving the robustness of models, we added equal proportions of Gaussian white noise of 5, 10, 15, 20, 25 dBW to enhance the data, and compared the results of convolutional neural networks and long short-term memory networks which show that the convolutional neural network combined with 10-fold data enhancement was better. The accuracy was 96.95%, indicating the great potential of this experimental model in liver cancer detection. [ABSTRACT FROM AUTHOR]

Surface-enhanced Raman spectroscopy (SERS), as a rapid, non-invasive and reliable spectroscopic detection technique, has promising applications in disease screening and diagnosis. In this paper, an annealed silver nanoparticles/porous silicon Bragg reflector (AgNPs/PSB) composite SERS substrate with high sensitivity and strong stability was prepared by immersion plating and heat treatment using porous silicon Bragg reflector (PSB) as the substrate. The substrate combines the five deep learning algorithms of the improved AlexNet, ResNet, SqueezeNet, temporal convolutional network (TCN) and multiscale fusion convolutional neural network (MCNN). We constructed rapid screening models for patients with primary Sjögren's syndrome (pSS) and healthy controls (HC), diabetic nephropathy patients (DN) and healthy controls (HC), respectively. The results showed that the annealed AgNPs/PSB composite SERS substrates performed well in diagnosing. Among them, the MCNN model had the best classification effect in the two groups of experiments, with an accuracy rate of 94.7% and 92.0%, respectively. Previous studies have indicated that the AgNPs/PSB composite SERS substrate, combined with machine learning algorithms, has achieved promising classification results in disease diagnosis. This study shows that SERS technology based on annealed AgNPs/PSB composite substrate combined with deep learning algorithm has a greater developmental prospect and research value in the early identification and screening of immune diseases and chronic kidney disease, providing reference ideas for non-invasive and rapid clinical medical diagnosis of patients. [ABSTRACT FROM AUTHOR]

Background: This study aimed to apply the backpropagation neural network (BPNN) to develop a model for predicting multidrug-resistant organism (MDRO) infection in critically ill patients. Methods: This study collected patient information admitted to the intensive care unit (ICU) of the Affiliated Hospital of Qingdao University from August 2021 to January 2022. All patients enrolled were divided randomly into a training set (80%) and a test set (20%). The least absolute shrinkage and selection operator and stepwise regression analysis were used to determine the independent risk factors for MDRO infection. A BPNN model was constructed based on these factors. Then, we externally validated this model in patients from May 2022 to July 2022 over the same center. The model performance was evaluated by the calibration curve, the area under the curve (AUC), sensitivity, specificity, and accuracy. Results: In the primary cohort, 688 patients were enrolled, including 109 (15.84%) MDRO infection patients. Risk factors for MDRO infection, as determined by the primary cohort, included length of hospitalization, length of ICU stay, long-term bed rest, antibiotics use before ICU, acute physiology and chronic health evaluation II, invasive operation before ICU, quantity of antibiotics, chronic lung disease, and hypoproteinemia. There were 238 patients in the validation set, including 31 (13.03%) MDRO infection patients. This BPNN model yielded good calibration. The AUC of the training set, the test set and the validation set were 0.889 (95% CI 0.852–0.925), 0.919 (95% CI 0.856–0.983), and 0.811 (95% CI 0.731–0.891), respectively. Conclusions: This study confirmed nine independent risk factors for MDRO infection. The BPNN model performed well and was potentially used to predict MDRO infection in ICU patients. [ABSTRACT FROM AUTHOR]

• A Convolutional Long Short Term Memory Network is used to predict the flood events based on deep learning techniques. • The spatial and time characteristics of floods in China are well modeled to overcome the shortcomings generated by merely relying on time-series analysis. • Different from traditional methods, the hydrological area is gridded into different watersheds for future processing using image processing methods. Floods cause substantial damage across the world every year. Accurate and timely prediction of floods can significantly minimize the loss of life and property. Recently, numerous machine learning models have been used for flood prediction, showing that their performance is preferable to traditional statistical models. However, the existing models neglect the spatial features of floods, which drive flood generation and concentration. In this paper, the area of interest is divided into grids based on longitude and latitude, and the rainfall and discharge collected by stations are combined into tensors according to station coordinates. Different from one-dimensional time series, our input feature is a two-dimensional time series with spatial information. Hence, combining a Convolutional Neural Network (CNN) with a Long Short Term Memory Network (LSTM), we propose the convolution LSTM (ConvLSTM) to extract spatiotemporal features of hydrological information. The methodology is demonstrated using the hydrological data collected at the Xi County stations, located on the Huai River in Henan Province, China. Numerical results indicate that the relative error of arrival time is within 30%, and the relative error of peak discharge is within 20%, satisfying the 2005 Chinese Water Resource Standard on flood prediction permit error. The experiments also show that the ConvLSTM outperforms the recent models in terms of flood arrival time and peak discharge, thereby proving a promising alternative. [ABSTRACT FROM AUTHOR]

Crotonylation on lysine sites in human non-histone proteins plays a crucial role in biology activities. However, because traditional experimental methods for crotonylation site identification are time-consuming and labor-intensive, computational prediction methods have become increasingly popular in recent years. Despite its significance, crotonylation site prediction has received less attention in non-histone proteins than in histones. In this study, we proposed a Multi-View Neural Network for identification of Human Non-Histone Crotonylation sites, named MVNN-HNHC. MVNN-HNHC integrated multi-view encoding features and adaptive encoding features through multi-channel neural network to deeply learn about attribute differences between crotonylation sites and non-crotonylation sites from various aspects. In MVNN-HNHC, convolutional neural networks can obtain local information from these features, and bidirectional long short term memory networks were utilized to extract sequence information. Then, we employ the attention mechanism to fuse the outputs of various feature extraction modules. Finally, the fully connection network acted as the classifier to predict whether a lysine site was crotonylation site or non-crotonylation site. Performance metrics on independent test set, including sensitivity, specificity, accuracy, Matthews correlation coefficient, and area under the curve (AUC) values reach 80.06 %, 75.77 %, 77.06 %, 0.5203, and 0.7792, respectively. To verify the effectiveness of this method, we carry out a series of experiments and the results show that MVNN-HNHC is an effective tool for predicting crotonylation sites in non-histone proteins. The data and code are available on https://github.com/xbbxhbc/junjun0612.git. [Display omitted] • In this study, we proposed a deep learning framework to identify non-histone crotonylation sites, integrating multi-view encoding features. • MVNN-HNHC applied multi-channel neural network for various types of features to deeply learn about discriminative attributes. • CNN, BLSTM are used to extract features and reduce dimensions, so as to obtain more valuable information. [ABSTRACT FROM AUTHOR]

Emotion recognition has recently attracted extensive interest due to its significant applications to human–computer interaction. The expression of human emotion depends on various verbal and non-verbal languages like audio, visual, text, etc. Emotion recognition is thus well suited as a multimodal rather than single-modal learning problem. Owing to the powerful feature learning capability, extensive deep learning methods have been recently leveraged to capture high-level emotional feature representations for multimodal emotion recognition (MER). Therefore, this paper makes the first effort in comprehensively summarize recent advances in deep learning-based multimodal emotion recognition (DL-MER) involved in audio, visual, and text modalities. We focus on: (1) MER milestones are given to summarize the development tendency of MER, and conventional multimodal emotional datasets are provided; (2) The core principles of typical deep learning models and its recent advancements are overviewed; (3) A systematic survey and taxonomy is provided to cover the state-of-the-art methods related to two key steps in a MER system, including feature extraction and multimodal information fusion; (4) The research challenges and open issues in this field are discussed, and promising future directions are given. [ABSTRACT FROM AUTHOR]

Floods have brought a great threat to the life and property of human beings. Under the premise of strengthening flood control engineering measures and following the strategic thinking of sustainable development, many achievements have been made in flood forecasting recently. However, due to the complexity of the traditional lumped model and distributed model, the hydrologic parameter calibration process is full of difficulties, leading to a long development cycle of a reasonable hydrologic prediction model. Even for modern data-driven models, the spatial distribution characteristics of the rainfall data are also not fully mined. Based on this situation, this paper abstracts the rainfall data into the graph structure data, uses remote sensing images to extract the elevation information, introduces the graph attention mechanism to extract the spatial characteristics of rainfall, and employs long-term and short-term memory (LSTM) network to fuse the spatial and temporal characteristics for flood prediction. Through well-designed experiments, the forecasting effect of flood peak value and flood arrival time is verified. Furthermore, compared with the LSTM model and BIGRU model without spatial feature extraction, the advantages of spatiotemporal feature fusion are highlighted. The specific performance is that the RMSE (the root means square error) and R 2 (coefficient of determination) of the GA-RNN model have been significantly improved. Finally, we conduct experiments on the observed ten rainfall events in the history of the target watershed. According to the hydrological prediction specifications, the model can be evaluated as a Class B flood forecasting model. [ABSTRACT FROM AUTHOR]

• Computer vision methods for livestock behaviour recognition were evaluated. • Journey from computer vision to deep learning was elaborated. • This paper involves with segmentation, identification and behaviour recognition. • Research trend of livestock behaviour recognition was illustrated from four aspects. • This review could provide researchers and producers with technical references. The increasing demand for sustainable livestock products also demands new considerations in animal breeding. Breeding programs are now seeking to integrate animal behavioural phenotypes, as these relate to the productivity, health and welfare of the animals and thereby can influence yield and economic benefits in the industry. Traditional manual observation of pig behaviour is time-consuming, laborious, subjective, and difficult to achieve in continuous and large-scale operations. It is not surprising that computer vision technology with the advantages of being objective, non-invasive and continuous has been widely researched for its use in the recognition of livestock behaviours over recent years. Nevertheless, in studies of livestock behaviour recognition, computer vision technology faces some challenges, e.g., complex scenes, variable illumination, occlusion, touching and overlapping between livestock, which has limited the fast translation of technology to industry. On the other hand, deep learning technology has proven to solve these difficulties to a certain extent and is being adopted to recognise livestock behaviours. This paper mainly evaluates the recent developments in computer vision methods for recognition of these behaviours in pigs and cattle. The focus on these species is made possible by the number of studies exist quantifying behaviours that are of importance for their health, welfare and productivity such as aggression, drinking, feeding, lameness, mounting, posture, tail-biting and nursing. This review paper especially analyses the development of image segmentation, identification and behaviour recognition using tradition computer vision and more recent deep learning methods, and evaluates the evolution of key research in the field. We elaborate the research trend of livestock behaviour recognition from four aspects, i.e., development of robust livestock identification algorithms, recognition of livestock behaviours for different growth stages, further quantification of the results of behaviour recognition, and building evaluation system of growth status, health and welfare. [ABSTRACT FROM AUTHOR]

Accurate classification and identification of chicken parts are critical to improve the productivity and processing speed in poultry processing plants. However, the overlapping of chicken parts has an impact on the effectiveness of the identification process. To solve this issue, this study proposed a real‐time classification and detection method for chicken parts, utilizing YOLOV4 deep learning. The method can identify segmented chicken parts on the assembly line in real time and accurately, thus improving the efficiency of poultry processing. First, 600 images containing multiple chicken part samples were collected to build a chicken part dataset after using the image broadening technique, and then the dataset was divided according to the 6:2:2 division principle, with 1200 images as the training set, 400 images as the test set, and 400 images as the validation set. Second, we utilized the single‐stage target detector YOLO to predict and calculate the chicken part images, obtaining the categories and positions of the chicken leg, chicken wing, and chicken breast in the image. This allowed us to achieve real‐time classification and detection of chicken parts. This approach enabled real‐time and efficient classification and detection of chicken parts. Finally, the mean average precision (mAP) and the processing time per image were utilized as key metrics to evaluate the effectiveness of the model. In addition, four other target detection algorithms were introduced for comparison with YOLOV4‐CSPDarknet53 in this study, which include YOLOV3‐Darknet53, YOLOV3‐MobileNetv3, SSD‐MobileNetv3, and SSD‐VGG16. A comprehensive comparison test was conducted to assess the classification and detection performance of these models for chicken parts. Finally, for the chicken part dataset, the mAP of the YOLOV4‐CSPDarknet53 model was 98.86% on a single image with an inference speed of 22.2 ms, which was higher than the other four models of YOLOV3‐Darknet53, YOLOV3‐MobileNetv3, SSD‐MobileNetv3, and SSD‐VGG16 mAP by 3.27%, 3.78%, 6.91%, and 6.13%, respectively. The average detection time was reduced by 13, 1.9, 6.2, and 20.3 ms, respectively. In summary, the chicken part classification and detection method proposed in this study offers numerous benefits, including the ability to detect multiple chicken parts simultaneously, as well as delivering high levels of accuracy and speed. Furthermore, this approach effectively addresses the issue of accurately identifying individual chicken parts in the presence of occlusion, thereby reducing waste on the assembly line. Practical Application: The aim of this study is to offer visual technical assistance in minimizing wastage and resource depletion during the sorting and cutting of chicken parts in poultry production and processing facilities. Furthermore, considering the diverse demands and preferences regarding chicken parts, this research can facilitate product processing that caters specifically to consumer preferences. [ABSTRACT FROM AUTHOR]

Surface-enhanced Raman spectroscopy (SERS), as a rapid, non-invasive and reliable spectroscopic detection technique, has promising applications in disease screening and diagnosis. In this paper, an annealed silver nanoparticles/porous silicon Bragg reflector (AgNPs/PSB) composite SERS substrate with high sensitivity and strong stability was prepared by immersion plating and heat treatment using porous silicon Bragg reflector (PSB) as the substrate. The substrate combines the five deep learning algorithms of the improved AlexNet, ResNet, SqueezeNet, temporal convolutional network (TCN) and multiscale fusion convolutional neural network (MCNN). We constructed rapid screening models for patients with primary Sjögren's syndrome (pSS) and healthy controls (HC), diabetic nephropathy patients (DN) and healthy controls (HC), respectively. The results showed that the annealed AgNPs/PSB composite SERS substrates performed well in diagnosing. Among them, the MCNN model had the best classification effect in the two groups of experiments, with an accuracy rate of 94.7% and 92.0%, respectively. Previous studies have indicated that the AgNPs/PSB composite SERS substrate, combined with machine learning algorithms, has achieved promising classification results in disease diagnosis. This study shows that SERS technology based on annealed AgNPs/PSB composite substrate combined with deep learning algorithm has a greater developmental prospect and research value in the early identification and screening of immune diseases and chronic kidney disease, providing reference ideas for non-invasive and rapid clinical medical diagnosis of patients. [ABSTRACT FROM AUTHOR]

Objective: For several years, computer technology has been utilized to diagnose lung nodules. When compared to traditional machine learning methods for image processing, deep-learning methods can improve the accuracy of lung nodule diagnosis by avoiding the laborious pre-processing step of the picture (extraction of fake features, etc.). Our goal is to investigate how well deep-learning approaches classify lung nodule malignancy. Method: We evaluated the performance of deep-learning methods on lung nodule malignancy classification via a systematic literature search. We conducted searches for appropriate articles in the PubMed and ISI Web of Science databases and chose those that employed deep learning to classify or predict lung nodule malignancy for our investigation. The figures were plotted, and the data were extracted using SAS version 9.4 and Microsoft Excel 2010, respectively. Results: Sixteen studies that met the criteria were included in this study. The articles classified or predicted pulmonary nodule malignancy using classification and summarization, using convolutional neural network (CNN), autoencoder (AE), and deep belief network (DBN). The AUC of deep-learning models is typically greater than 90% in articles. It demonstrated that deep learning performed well in the diagnosis and forecasting of lung nodules. Conclusion: It is a thorough analysis of the most recent advancements in lung nodule deep-learning technologies. The advancement of image processing techniques, traditional machine learning techniques, deep-learning techniques, and other techniques have all been applied to the technology for pulmonary nodule diagnosis. Although the deep-learning model has demonstrated distinct advantages in the detection of pulmonary nodules, it also carries significant drawbacks that warrant additional research. [ABSTRACT FROM AUTHOR]