Search

In the process of steel production, the defects on the surface of steel will adversely affect the subsequent processing of a product. Accurate detection of such defects is the key to improve production efficiency and economic benefits. In this paper, an end-to-end steel surface defect detection and size measurement system based on the YOLOv5 model is designed. Firstly, in consideration of the defect location and direction correlation in the production process, a coordinate attention mechanism is added at the head of YOLOv5 to strengthen the spatial correlation of the steel surface and an adaptive anchor box generation method based on defect shape difference feature is proposed, which realizes the detection of three main types of defects on the Pytorch deep learning framework. Secondly, BiFPN is used to strengthen the feature fusion and a transformer encoder is added to improve the performance of detecting small defects. Thirdly, calculate the conversion ratio between the pixel and the actual size according to the standard reference specimen and obtain the actual size through the pixel statistics of the defect area to achieve pixel level size measurement. Finally, the steel surface defect detection and size measurement system are designed in this paper, which consist of various hardware, related measurement, and detection algorithms. According to the experimental results, the comprehensive defect detection accuracy of this method reaches 93.6%, of which the scratch detection accuracy reaches 95.7%. The detection speed reaches 133 fps and the defect size measurement accuracy reaches 0.5 mm. Experimental result shows that the defect detection and size measurement system designed in this paper can accurately detect and measure various industrial production defects and can be applied to the actual production process. [ABSTRACT FROM AUTHOR]

Ensemble learning, as a kind of method to improve the generalization ability of classifiers, is often used to improve the model effect in the field of deep learning. However, the present ensemble learning methods mostly adopt voting fusion in combining strategies. This strategy has difficulty mining effective information from the classifiers and cannot effectively reflect the relationship between different classifiers. Ensemble learning based on the evidential inference rule (ER rule) can effectively excavate the internal relationships among different classifiers and has a certain interpretability. However, the ER rule depends on the weight distribution of different combination strategies, and the setting of the evidence weight will affect the accuracy and stability of the model. Therefore, this paper proposes a new ensemble learning method based on multiple fusion weighted evidential reasoning rules and constructs an ensemble learning framework for data fusion and decision mapping. This framework takes the evidence weight, confidence, and feature data of each classifier as input and the integration results as output. The weight of evidence was determined by multiple fusion weights of the entropy weight method and order relation method. Finally, the integrated learning process is set up by the ER algorithm. The method proposed in this paper is verified by multiple datasets. Experimental results show that the surface construction model has good performance, and the defects of single weighting instability are greatly improved under the premise of improving the integration effect. [ABSTRACT FROM AUTHOR]

In order to improve the motion route planning effect and obstacle avoidance effect of mobile robots, this paper combines the deep learning theory to analyze the motion route planning and obstacle avoidance process of mobile robots. According to the obstacle avoidance trajectory and constraints, this paper establishes a safe distance model for obstacle avoidance, then analyzes the braking process of the robot, and designs an improved safety model for obstacle avoidance. This model integrates two relatively mature safety models, complements their advantages and disadvantages, and comprehensively considers robot safety and the utilization of the motion path. According to the simulation test research, the robot based on deep learning proposed in this paper has a good motion route planning effect and obstacle avoidance effect and can effectively improve the autonomous motion effect of the robot. [ABSTRACT FROM AUTHOR]

Trash classification is an effective measure to protect the ecological environment and improve resource utilization. With the development of deep learning, it is possible to use the deep convolutional neural network for trash classification. In order to classify the trash of the TrashNet dataset, which consists of six classes of garbage images, this paper proposes a hybrid deep learning model based on deep transfer learning, which includes upper and lower streams. Firstly, the upper stream divides the input garbage image into category MPP (metal, paper, and plastic class) or category CGT (cardboard, glass, and trash class). Then, the lower stream predicts the exact class of trash according to the results of the upper stream. The proposed hybrid deep learning model achieves the best result with 98.5 % than that of the state-of-the-art approaches. Through the verification of CAM (class activation map), the proposed model can reasonably use the features of the image for classification, which explains the reason for the superior performance of this model. [ABSTRACT FROM AUTHOR]

Under the current situation, there are many drawbacks in the integrated development of culture and tourism. Therefore, this paper aims to use big data analysis to study the path and development mechanism of cultural and tourism integration, aiming to explore a road of cultural and tourism integration that is most suitable for domestic development. This paper proposes a big data platform based on deep learning to adapt to domestic cultural data and tourism data. The system can intuitively analyze the domestic cultural tourism industry and display the development of cultural tourism with brief pictures and figures. This article analyzes the performance of the designed system and tests the fusion of cultural tourism data. The experimental results of this paper prove that the stability design of the big data cultural tourism industry analysis platform in this paper meets the requirements, and the platform can be stable at 5 Mb/s for 40–180 G big data transmission. The results of the modeling analysis of the integrated development of cultural tourism can be considered; that is, the cultural tourism industry has made great progress in the process of integration, and the integrated development of these two industries is imperative. [ABSTRACT FROM AUTHOR]

In order to improve the sharing effect of online teaching resources of spoken English, this paper considers the sharing of resources among tasks in a mixed criticality system based on fixed task priority scheduling. Moreover, this paper extends the traditional PCP protocol and proposes a resource sharing protocol suitable for the AMC scheduling model in a verifiable hybrid criticality system. In addition, with the support of deep learning, this paper analyzes the worst blocking time and the worst response time of the task at each stage. Finally, this paper analyzes the sharing methods of online teaching resources of spoken English in combination with deep learning methods and constructs a corresponding intelligent teaching resource sharing system. The experimental research results show that the sharing method of online teaching resources of spoken English based on deep learning has a good resource sharing effect. [ABSTRACT FROM AUTHOR]

The typical pretrained model's feature extraction capabilities are insufficient for medical named entity identification, and it is challenging to express word polysemy, resulting in a low recognition accuracy for electronic medical records. In order to solve this problem, this paper proposes a new model that combines the BERT pretraining model and the BilSTM-CRF model. First, word embedding with semantic information is obtained by pretraining the corpus input to the BERT model. Then, the BiLSTM module is utilized to extract further features from the encoded outputs of BERT in order to account for context information and improve the accuracy of semantic coding. Then, CRF is used to modify the results of BiLSTM to screen out the annotation sequence with the largest score. Finally, extensive experimental results show that the performance of the proposed model is effectively improved compared with other models. [ABSTRACT FROM AUTHOR]

Aircraft detection for remote sensing images, as one of the fields of computer vision, is one of the significant tasks of image processing based on deep learning. Recently, many high-performance algorithms for aircraft detection have been developed and applied in different scenarios. However, the proposed algorithms still have a series of problems; for instance, the algorithms will miss some small-scale aircrafts when applied to the remote sensing image. There are two main reasons for the problem; one reason is that the aircrafts in the remote sensing image are usually small in size, leading to detecting difficulty. The other reason is that the background of the remote sensing image is usually complex, so the algorithms applied to the scenario are easy to be affected by the background. To address the problem of small size, this paper proposes the Multiscale Detection Network (MSDN) which introduces a multiscale detection architecture to detect small-scale aircrafts. With the intention to resist the background noise, this paper proposes the Deeper and Wider Module (DAWM) which increases the perceptual field of the network to alleviate the affection. Besides, to address the two problems simultaneously, this paper introduces the DAWM into the MSDN and names the novel network structure as Multiscale Refined Detection Network (MSRDN). The experimental results show that the MSRDN method has detected the small-scale aircrafts that other algorithms missed and the performance indicators have higher performance than other algorithms. [ABSTRACT FROM AUTHOR]

In 2019, the infectious coronavirus disease 2019 (COVID-19) was first reported in Wuhan, China. It has then become a public health problem in the world. This pandemic is having a heavy impact on the lives of people in our country. All countries are trying to control the spread of this disease. To solve the problem, each person needs to wear masks in a public place. Therefore, we propose a model capable of distinguishing between masked and nonmasked faces using a convolutional neural network (CNN) based on deep learning (DL)—MobileNetV2 in this paper. The model can detect people who are not wearing masks. It has an accuracy of up to 99.37%. The model will be applied in places such as schools, offices, and so on to monitor the wearing masks. [ABSTRACT FROM AUTHOR]

Germination test is an irreplaceable step in seed selection and breeding. The current traditional germination test method must rely on experienced professional technicians to repeatedly classify and count the germination status of seeds and count the germination rate at different moments during the whole test process (usually takes 2 to 10 days). Currently, only the German seed germination detection system (Germination Scanalyzer) can solve this problem, but it is so expensive that it has not been practically promoted. In order to improve breeding efficiency, an automatic monitoring system for seed germination tests based on deep learning was designed. It includes a modified germination thermostat, connected with a three-dimensional movable camera bin with built-in camera; a multifunctional software system capable of online, offline, and sentinel mode monitoring; a dense distributed small target detection algorithm (DDST-CenterNet) for seed germination monitoring systems. The system test results show that the seed germination test automatic monitoring system is low cost, does not depend on the seed background, light, camera model, and other usage environments, and has high scalability. The DDST-CenterNet algorithm proposed in this paper can still maintain high accuracy and good stability in the process of seed target detection and classification as the number and density of seeds increase, which is suitable for a special application scenario of seed germination test. In addition, the algorithm has high computational efficiency and can give detection results at a frame rate of not less than 10fps, which can be used in practical applications. [ABSTRACT FROM AUTHOR]

The aim of this study is to address the real-time requirements of forestry pest detection and the problem of a low detection rate caused by anchor box redundancy of existing detection methods. This paper proposes a real-time forestry pest detection method based on theanchor-free method that can balance the detection rate and detection accuracy. Based on the TTFNet method, a mobile feature extraction network is introduced, and the effective feature weights are increased by one-dimensional convolution before feature output to suppress invalid features. For pest detection, data are mostly small-scale targets. An enhanced feature fusion method is proposed to introduce an asymmetric convolution module in multi-scale feature fusion to feature-enhance the feature maps extracted by the backbone network and connect across layers to improve the detection accuracy. To address the degradation of the anchor box position regression loss in the original method, DIOULoss is introduced to optimize the position regression loss function of the anchor box. Finally, data augmentation is performed on a relatively small number of samples in the dataset, the accuracy of the model is improved by 1.94%, the FPS is improved to 1.6 times of the original one, and the training time is slightly increased compared with the preinnovation model. Ablation experiments are designed to demonstrate the effectiveness of the proposed algorithm while being more conducive to deployment on edge devices. [ABSTRACT FROM AUTHOR]

"Parallel bookkeeping" is a key technical arrangement to achieve the goal of moderately separating and connecting the financial accounting system and budget accounting system established by the government accounting system. It is still a new thing for the majority of financial personnel in the government accounting subject. A deep neural network is the basis of deep learning. Up to now, the neural network has been applied in many fields, and its application in the financial field is more in-depth. The neural network is of great help to financial accounting. Integrating it into parallel bookkeeping in accounting can improve the work efficiency and accuracy of financial personnel. Through experimental analysis, it is found that its efficiency and accuracy are improved by 45% and 21.34% compared with the previous parallel bookkeeping path. The accounting parallel bookkeeping path based on the deep neural network studied in this paper not only has great practical significance for the work of financial personnel but also has far-reaching significance for the research of accounting paths in the future. [ABSTRACT FROM AUTHOR]

Swift development in wind power and extension of wind generation necessitates significant research in numerous fields. Due to this, wind power is weather dependent; it is fluctuating and is sporadic over numerous time periods. Hence, timely wind power prediction is perceived as an extensive contribution to well-grounded wind power prediction with complex patterns. In addition, a number of wind power prediction methods have been developed. For proper planning and operation of power systems with complicated patterns, wind power prediction in an accurate and timely manner is essential. This paper presents a wind power prediction method with feature selection and prediction called, Pearson Autocovariance Distinct Patterns and Attention-based Deep Learning (PACDP-ADL). In the deep learning environment, feature selection plays a crucial aspect and a prediction task. A Pearson Autocovariance Feature Selection model is used for identifying necessary features for wind power prediction and reduces the complexity of the model. Next, an Attention-based Long Short-Term Memory Wind Prediction algorithm is employed to retain required patterns and forget irrelevant patterns to acquire more satisfactory prediction precision. The proposed PACDP-ADL method is validated by utilizing the wind power data with various performance metrics such as wind power accuracy, wind power time, and true positive rate compared with the state-of-the-art method. [ABSTRACT FROM AUTHOR]

Psychological stress refers to the load or oppression that people's thoughts, feelings, and other inner processes bear, as well as the emotional shifts brought on by the school, work, society, everyday life, interpersonal connections, and other things. It can trigger people's worry and other negative feelings, making them mentally dejected and frustrated, as well as raise people's spirits to cheer up and meet stimuli and difficulties. College students are in their 20s, and they are energetic, have extreme mood swings, and are prone to mental problems. As a distinct group in the social development trend, college students are influenced by the learning and growth environment, and their understanding of the world, values, and outlook on life is maintained at the theoretical level, lacking practical thinking and experience, making it difficult to adapt in a short period of time. Excessive psychological strain is caused by new events and new contradicting conditions, which interfere with normal living and learning. This study employs a deep learning model to test and assess the psychological stress in college students, with the goal of addressing the varied psychological stresses that college students are prone to. The deep learning model employed in this paper is based on the classic ResNet50 network model, which compresses its network structure, lowering the computational cost of ResNet50 network model training and increasing the network's efficiency. To boost processing performance and save storage and computational resources, we trained a network with few parameters, a small model, and high precision. The findings of the investigation can help college officials prevent and recognize problems in students early on. It actively builds a good home-school cooperation mechanism and enhances the students' ability to cope with and solve stress through enhancing the students' behavioral experience, so that students can form a good psychological stress coping thinking and behavior, while attaching importance to the cultivation of college students' psychological quality. [ABSTRACT FROM AUTHOR]

Deep learning has brought revolutionary progress to computer vision, so intelligent inspection equipment based on computer vision has developed rapidly. However, due to the large number of existing deep features, it is difficult to deploy it on mobile devices to achieve real-time tracking speed. This paper presents a target-aware deep feature compression for power intelligent inspection tracking. First, a negative balance loss function is designed to mine channel features suitable for the current inspection scene by shrinking the contribution of pure background negative samples and enhancing the impact of difficult negative samples. Based on this, the deep feature compression model is combined with Siamese tracking framework to achieve real-time and robust tracking. Finally, we evaluate the proposed method on real application scenarios and general data to prove the practicability of the proposed method. [ABSTRACT FROM AUTHOR]

The recognition of hand movements is an important method for human-computer interaction (HCI) technology, and it is widely used in virtual reality and other HCI areas. While many valuable efforts have been made, efficient ways to capture over 20 types of hand movements with high accuracy by one data glove are still lacking. This paper addresses a new classification framework for 52 hand movements. This classification framework includes the following two parts: the movement detection algorithm and the movement classification algorithm. The fine K-nearest neighbor (Fine KNN) is the core of the movement detection algorithm. The movement classification algorithm is composed of downsampling in data preparation and a new deep learning network named the DBDF network. Bidirectional Long Short-Term Memory (BiLSTM) is the main part of the DBDF network. The results of experiments using the Ninapro DB1 dataset demonstrate that our work can classify more types of hand movements than related algorithms with a precision of 93.15%. [ABSTRACT FROM AUTHOR]

Loop closure detection serves as the fulcrum of improving the accuracy and precision in simultaneous localization and mapping (SLAM). The majority of loop detection methods extract artificial features, which fall short of learning comprehensive data information, but unsupervised learning as a typical deep learning method excels in self-access learning and clustering to analyze the similarity without handling the data. Moreover, the unsupervised learning method does solve restrictions on image quality and singleness semantics in many traditional SLAM methods. Therefore, a loop closure detection strategy based on an unsupervised learning method is proposed in this paper. The main component adopts BigBiGAN to extract features and establish an original bag of words. Then, the complete bag of words is used to detect loop closing. Finally, a considerable validation check of the ORB descriptor is added to verify the result and output outcome of loop closure detection. The proposed algorithm and other compared algorithms are, respectively, applied on Autolabor Pro1 to execute the indoor visual SLAM. The experiment shows that the proposed algorithm increases the recall rate by 20% compared with ORB-SLAM2 and LSD-SLAM. And it also improves at least 40.0% accuracy than others and reduces 14% time loss of ORB-SLAM2. Therefore, the presented SLAM based on BigBiGAN does benefit much the visual SLAM in the indoor environment. [ABSTRACT FROM AUTHOR]

As one of the major factors of the nontechnical losses (NTLs) in distribution networks, the electricity theft causes significant harm to power grids, which influences power supply quality and reduces operating profits. In order to help utility companies solve the problems of inefficient electricity inspection and irregular power consumption, a novel hybrid convolutional neural network-random forest (CNN-RF) model for automatic electricity theft detection is presented in this paper. In this model, a convolutional neural network (CNN) firstly is designed to learn the features between different hours of the day and different days from massive and varying smart meter data by the operations of convolution and downsampling. In addition, a dropout layer is added to retard the risk of overfitting, and the backpropagation algorithm is applied to update network parameters in the training phase. And then, the random forest (RF) is trained based on the obtained features to detect whether the consumer steals electricity. To build the RF in the hybrid model, the grid search algorithm is adopted to determine optimal parameters. Finally, experiments are conducted based on real energy consumption data, and the results show that the proposed detection model outperforms other methods in terms of accuracy and efficiency. [ABSTRACT FROM AUTHOR]

Seismic events prediction is a crucial task for preventing coal mine rock burst hazards. Currently, this task attracts increasing research enthusiasms from many mining experts. Considering the temporal characteristics of monitoring data, seismic events prediction can be abstracted as a time series prediction task. This paper contributes to address the problem of long-term historical dependence on seismic time series prediction with deep temporal convolution neural networks (CNN). We propose a dilated causal temporal convolution network (DCTCNN) and a CNN long short-term memory hybrid model (CNN-LSTM) to forecast seismic events. In particular, DCTCNN is designed with dilated CNN kernels, causal strategy, and residual connections; CNN-LSTM is established in a hybrid modeling way by utilizing advantage of CNN and LSTM. Based on these manners, both of DCTCNN and CNN-LSTM can extract long-term historical features from the monitoring seismic data. The proposed models are experimentally tested on two real-life coal mine seismic datasets. Furthermore, they are also compared with one traditional time series prediction method, two classic machine learning algorithms, and two standard deep learning networks. Results show that DCTCNN and CNN-LSTM are superior than the other five algorithms, and they successfully complete the seismic prediction task. [ABSTRACT FROM AUTHOR]

Deep learning technique has made a tremendous impact on medical image processing and analysis. Typically, the procedure of medical image processing and analysis via deep learning technique includes image segmentation, image enhancement, and classification or regression. A challenge for supervised deep learning frequently mentioned is the lack of annotated training data. In this paper, we aim to address the problems of training transferred deep neural networks with limited amount of annotated data. We proposed a versatile framework for medical image processing and analysis via deep active learning technique. The framework includes (1) applying deep active learning approach to segment specific regions of interest (RoIs) from raw medical image by using annotated data as few as possible; (2) generative adversarial Network is employed to enhance contrast, sharpness, and brightness of segmented RoIs; (3) Paced Transfer Learning (PTL) strategy which means fine-tuning layers in deep neural networks from top to bottom step by step to perform medical image classification or regression tasks. In addition, in order to understand the necessity of deep-learning-based medical image processing tasks and provide clues for clinical usage, class active map (CAM) is employed in our framework to visualize the feature maps. To illustrate the effectiveness of the proposed framework, we apply our framework to the bone age assessment (BAA) task using RSNA dataset and achieve the state-of-the-art performance. Experimental results indicate that the proposed framework can be effectively applied to medical image analysis task. [ABSTRACT FROM AUTHOR]