Search

The colorimetric method is usually used to test the concentration of substances. However, this method has a big error since different people have different sensitivities to colors. In this paper, in order to solve the identification problem of the color and the concentration of the test paper, firstly, we found out that the concentration of substance is correlated with the color reading by using the Pearson's Chi-squared test method. And by the concentration coefficient of Pearson correlation analysis, the concentration of substance and color reading is highly correlated. Secondly, according to the RGB value of the paper image, the color moments of the image are calculated as the characteristics of the image, and the Levenberg–Marquardt (LM) neural network is established to classify the concentration of the substance. The accuracy of the training set model is 94.5%, and the accuracy of the test set model is 87.5%. The model precision is high, and the model has stronger generalization ability. Therefore, according to the RGB value of the test paper image, it is effective to establish the LM neural network model to identify the substance concentration. [ABSTRACT FROM AUTHOR]

To improve the recognition ability of clinical named entity recognition (CNER) in a limited number of Chinese electronic medical records, it provides meaningful support for clinical advanced knowledge extraction. In this paper, using CCKS2019 Chinese electronic medical record as an experimental data source, a fusion model enhanced by knowledge graph (KG) is proposed, and the model is applied to specific Chinese CNER tasks. This study consists of three main parts: single-mode model construction and comparison experiment, KG enhancement experiment, and model fusion experiment. The model has achieved good performance in CNER from the results. The accuracy rate, recall rate, and F1 value are 83.825%, 84.705%, and 84.263%, respectively, which is the global optimal, which proves the effectiveness of the model. This provides a good help for further research of medical information. [ABSTRACT FROM AUTHOR]

The recognition of steel microstructure images plays a crucial role in the metallographic analysis process. Although some progress has been made through the application of artificial intelligence algorithms, several challenges remain. First, existing algorithms exhibit weak nonlinear feature extraction capabilities and noticeable limitations. Second, they overlook the intrinsic noise and redundant interference present in microscopic images. To address these issues, this paper investigates the automatic recognition of metallographic tissues by leveraging residual structures in deep neural networks. An enhanced residual network model based on transfer learning is proposed, which utilizes the pre-trained weights from the ImageNet dataset to facilitate learning with small sample data. This network offers higher classification accuracy and higher F1 scores. In addition, a deep residual shrinkage network model based on an attention mechanism is proposed. This model incorporates an attention sub-network into the original residual module and employs a soft threshold function to eliminate redundant features, including noise. The proposed algorithms are evaluated against various convolutional neural networks using 20 types of metallographic test sets. The experimental results showed that both methods have high accuracy rates of 95% and 94.44%, respectively, and F1 scores of 0.9464 and 0.9419. While maintaining the complexity of the model, there has been a significant improvement in accuracy, and the models exhibit strong generalization capabilities. Our research contributes to enhancing production efficiency, strengthening quality control, and improving material performance through computer vision technology. [ABSTRACT FROM AUTHOR]

The recognition of steel microstructure images plays a crucial role in the metallographic analysis process. Although some progress has been made through the application of artificial intelligence algorithms, several challenges remain. First, existing algorithms exhibit weak nonlinear feature extraction capabilities and noticeable limitations. Second, they overlook the intrinsic noise and redundant interference present in microscopic images. To address these issues, this paper investigates the automatic recognition of metallographic tissues by leveraging residual structures in deep neural networks. An enhanced residual network model based on transfer learning is proposed, which utilizes the pre-trained weights from the ImageNet dataset to facilitate learning with small sample data. This network offers higher classification accuracy and higher F1 scores. In addition, a deep residual shrinkage network model based on an attention mechanism is proposed. This model incorporates an attention sub-network into the original residual module and employs a soft threshold function to eliminate redundant features, including noise. The proposed algorithms are evaluated against various convolutional neural networks using 20 types of metallographic test sets. The experimental results showed that both methods have high accuracy rates of 95% and 94.44%, respectively, and F1 scores of 0.9464 and 0.9419. While maintaining the complexity of the model, there has been a significant improvement in accuracy, and the models exhibit strong generalization capabilities. Our research contributes to enhancing production efficiency, strengthening quality control, and improving material performance through computer vision technology. [ABSTRACT FROM AUTHOR]

With the advent of deep neural networks, medical image analysis is able to predict results in advance in early detection and diagnosis of diseases found in the human body. Several deep neural network methodologies have been implemented for a quick and efficient analysis of medical images that detect and diagnose cancerous cell growth in any part of the human body. For improving the segmentation and classification accuracy, the paper has proposed a framework comprising modified DoubleU-Net for image segmentation and PolyNet architecture for image classification. The modified DoubleU-Net is composed of two U-Net architectures, in which U-Net1 makes use of ResNet-50 as an encoder in the place of VGG-16 (existing) and Atrous Spatial Pyramid Pooling (ASPP) is replaced by Waterfall Atrous Spatial Pooling (WASP) architecture in both U-Nets to improve the semantic image segmentation. For classifying the segmented medical images as benign or malignant, PolyNet architecture is implemented in the research. The research involves experiments on the brain tumor dataset and lung cancer dataset to analyze the performance of the proposed approach. The processing of the DoubleU-Net and modified DoubleU-Net is evaluated based on precision, Recall, Intersection over Union (IoU), and Dice Score as the performance metrics. Experimental findings indicate that the modified DoubleU-Net design outperformed the existing DoubleU-Net architecture in terms of performance parameters for segmentation. The efficiency of the PolyNet classifier has been evaluated against VGG-16 and Inception-V3 classifiers, in terms of accuracy, specificity, sensitivity, error rate, and computation time as the performance metrics. From the experimental results, it has been proved that the PolyNet classifier performs better than VGG-16 and Inception-V3 with improved accuracy, specificity, sensitivity, and computation time. [ABSTRACT FROM AUTHOR]

Model pruning is one of the main methods of deep neural network model compression. However, the existing model pruning methods are inefficient, there is still a lot of redundancy in the network, and the pruning has a great impact on the accuracy. In addition, the traditional pruning process usually needs to fine-tune the network to restore accuracy, and fine-tuning has a limited effect on accuracy recovery, so it is difficult to achieve a high level of accuracy. In this paper, we propose a new neural network pruning framework: the channel sparsity is realized by introducing a scale factor, and the sparse network is pruned by setting a global threshold, which greatly improves the efficiency of pruning. After pruning, this paper proposes a rewind method to restore the accuracy, that is, save the weight after training, and then reload it on the network for training to restore the accuracy. In addition, we also study the best rewind point of the three networks. The experimental results show that our method significantly reduces the number of parameters and FLOPs without affecting or even improving the accuracy, and the rewind method proposed by us achieves a better accuracy recovery effect than fine-tuning. At the same time, we find that the epoch with the highest accuracy is the best rewind point, and the accuracy is the highest after saving its corresponding weight and retraining the model. [ABSTRACT FROM AUTHOR]

Situational awareness is the ability of pilots to master flight status, which is of great significance to aviation flight safety and flight effect. According to the information processing model, the pilot's main steps of processing information are feeling, perception and execution. There are many problems in situation awareness analysis guided by visual gaze, such as large analysis deviation and high delay due to various influencing factors and complex characteristics. In order to solve this problem, this paper proposes a situation awareness assessment method based on artificial intelligence neural network and integrating visual gaze and flight control. First, this paper carries out simulated flight training experiments for flight cadets, and collects the data of eye movement, line of sight tracking, flight control and flight parameters of pilot cadets. Then, aiming at the flight subjects, a situation awareness analysis method based on events is established, and the situation awareness state in the experiment is evaluated and analyzed through the flight parameter data. Then, the visual gaze and flight control data are sliced in the unit of situational awareness events, and the data set is constructed. Finally, this paper designs a multi-channel sequence data classification and analysis model based on transformer, in which the situation awareness characteristics of visual gaze and operation behavior are analyzed through the attention mechanism. The experimental results show that the accuracy of situation awareness classification of the designed neural network model to the experimental data set is 96%, and can classify and evaluate the pilot's situation awareness state in 5 s. [ABSTRACT FROM AUTHOR]

Aiming to solve the problem of tracking drift during movement, which was caused by the lack of discriminability of the feature information and the failure of a fixed template to adapt to the change of object appearance, the paper proposes an object tracking algorithm combining attention mechanism and correlation filter theory based on the framework of full convolutional Siamese neural networks. Firstly, the apparent information is processed by using the attention mechanism thought, where the object and search area features are optimized according to the spatial attention and channel attention module. At the same time, the cross-attention module is introduced to process the template branch and search area branch, respectively, which makes full use of the diversified context information of the search area. Then, the background perception correlation filter model with scale adaptation and learning rate adjustment is adopted into the model construction, using as a layer in the network model to realize the object template update. Finally, the optimal object location is determined according to the confidence map with similarity calculation. Experimental results show that the designed method in the paper can promote the object tracking performance under various challenging environments effectively; the success rate increases by 16.2%, and the accuracy rate increases by 16%. [ABSTRACT FROM AUTHOR]

Deep learning is a popular topic among machine learning researchers nowadays, with great strides being made in recent years to develop robust artificial neural networks for faster convergence to a reasonable accuracy. Network architecture and hyperparameters of the model are fundamental aspects of model convergence. One such important parameter is the initial values of weights, also known as weight initialization. In this paper, we perform two research tasks concerned with the weights of neural networks. First, we develop three novel weight initialization algorithms inspired by the neuroscientific construction of the mammalian brains and then test them on benchmark datasets against other algorithms to compare and assess their performance. We call these algorithms the lognormal weight initialization, modified lognormal weight initialization, and skewed weight initialization. We observe from our results that these initialization algorithms provide state-of-the-art results on all of the benchmark datasets. Second, we analyze the influence of training an artificial neural network on its weight distribution by measuring the correlation between the quantitative metrics of skewness and kurtosis against the model accuracy using linear regression for different weight initializations. Results indicate a positive correlation between network accuracy and skewness of the weight distribution but no affirmative relation between accuracy and kurtosis. This analysis provides further insight into understanding the inner mechanism of neural network training using the shape of weight distribution. Overall, the works in this paper are the first of their kind in incorporating neuroscientific knowledge into the domain of artificial neural network weights. [ABSTRACT FROM AUTHOR]

With the limitation of air traffic and the rapid increase in the number of flights, flight delay is becoming more frequent. Flight delay leads to financial and time losses for passengers and increases operating costs for airlines. Therefore, the establishment of an accurate prediction model for flight delay becomes vital to build an efficient airline transportation system. The air transportation system has a huge amount of data and complex operation modes, which is suitable for analysis by using machine learning methods. This paper discusses the factors that may affect the flight delay, and presents a new flight delay prediction model. The five warning levels are defined based on flight delay database by using K-means clustering algorithm. After extracting the key factors related to flight operation by the grey relational analysis (GRA) algorithm, an improved machine learning algorithm called GRA — Genetic algorithm (GA) — back propagation neural network, GRA-GA-BP, is introduced, which is optimized by GA. The calculation results show that, compared with models before optimization and other two algorithms in previous papers, the proposed prediction model based on GRA-GA-BP algorithm shows a higher prediction accuracy and more stability. In terms of operation efficiency and memory consumption, it also has good performance. The analysis presented in this paper indicates that this model can provide effective early warnings for flight delay, and can help airlines to intervene in flights with abnormal trend in advance. [ABSTRACT FROM AUTHOR]

Adversarial training is by far one of the most effective methods to improve the robustness of deep neural networks against adversarial examples. However, the trade-off between robustness and accuracy is still a challenge in adversarial training. Previous methods used adversarial examples with a fixed perturbation budget or specific perturbation budgets for each example, which is inefficient in improving the trade-off and lacks the ability to control the trade-off flexibly. In this paper, we show that the largest element of logit, z max , can roughly represent the minimum distance between an example and its neighboring decision boundary. Thus, we propose group adaptive adversarial training (GAAT) that divides the training dataset into several groups based on z max and develops a binary search algorithm to determine the group perturbation budgets for each group. Using the group perturbation budgets to perform adversarial training can fine-tune the trade-off between robustness and accuracy. Extensive experiments conducted on CIFAR-10 and ImageNet-30 show that our GAAT can achieve a more perfect trade-off than TRADES, MMA, and MART. [ABSTRACT FROM AUTHOR]

Mathematical morphology intends to extract object features such as geometric and topological structures in digital images. Given a set of target images and original images, it is cumbersome and time-consuming to determine the suitable morphological operations and structuring elements. In this paper, we propose deep morphological neural networks, which include a nonlinear feature extraction layer to learn the structuring element correctly and an adaptive layer to select appropriate morphological operations automatically. We demonstrate the applications of object recognition, including hand-written digits, geometric shapes, traffic signs, and brain tumor. Experimental results show the higher computational efficiency and higher accuracy of our developed model as compared against existing convolutional neural network models. [ABSTRACT FROM AUTHOR]

EEG has been proved to be an effective tool for researchers' cognition and mental workload by detecting the changes of brain activity potential. The mental workload of pilots in aviation flight is closely related to the characteristics of flight tasks. The previous methods have problems such as lack of objectivity, low EEG analysis ability and lack of real-time analysis ability. In order to solve these problems, this paper proposes a multi-dimensional data fusion brain workload calculation method based on flight effect evaluation, which integrates vision, operational behavior and visual gaze, and classifies and analyzes them in combination with EEG data. This method evaluates the mental workload of pilots from three aspects: visual gaze behavior, control behavior and flight effect in the simulated flight experimental environment, and realizes a more objective mental workload analysis. Then, the synchronously collected EEG data are segmented and sampled to form a dataset, and an LSTM neural network model integrating attention mechanism is established, in which the attention mechanism is used to improve the feature processing ability of the network model for the classification of complex EEG data. After machine learning training, the final model can achieve 94% detection accuracy for 2-s EEG data, and has the ability of real-time analysis in the application environment. Compared with the previous similar LSTM model, the accuracy is improved by 6%, which also shows the effectiveness of the model. [ABSTRACT FROM AUTHOR]

Pests and diseases of tomato fruits are the foremost factors leading to the reduction in produce quantity. Effective and prompt differentiation of these lesion symptoms is essential for agricultural production. Due to the lack of a global receptive field, commonly used convolution neural network models restrict the capability on tomato images under complicated backgrounds. In this paper, we present an efficient and robust method for field diagnosis of tomato fruits based on the context data fusion and capsule network. First, in order to make better the point of inadequate images, the Cycle-GAN algorithm is used to realize the augmentation of the diseases dataset. To improve the quality of the generated images, the feature reconstruction loss function is proposed for the Cycle-GAN method, named Fruit-GAN. The proposed Fruit-GAN learns features of healthy and diseased tomatoes, respectively, and forms lesions based on healthy tomato fruit images. Adding lesion tomato images produced on Fruit-GAN to training sets improves the diagnostic capability compared to classical data augmentation techniques. Subsequently, context fusion studies were used to construct intermediate feature maps from different layers into the fruit diseases recognition compact representation to efficiently leverage the feature reuse mechanism. Finally, the fusion model's enlightened multi-scale capsule network is integrated to form deep features and determine the disease diagnosis. After analyzing the hyper-parameters, the integral technique provides 96.16% accuracy. This research of tomato diseases diagnosis demonstrates the context capsule network model is efficient and establishes a foundation for tomato fruits determination in natural growing environment. [ABSTRACT FROM AUTHOR]

Vocal fold, a significant body structure, is accountable for phonation, which regulates air motion within and out of the lungs. The disorders in the vocal fold influence the quality of life. Thus, diagnosis of vocal fold disorders has a significant need, and CT of the neck is employed for an effective imaging scheme. Accordingly, this paper proposes an advanced multi-resolution algorithm (MRA) that optimally identifies and classifies pathologies. The vocal regions are acquired using the genetic k-means algorithm. The pathology features are generated using the local directional pattern (LDP) fed to pathology classification using moth search-rider optimization-based deep convolutional neural networks (MRA-based DCNN). The hybrid optimization (MRA), integrates the standard rider optimization algorithm (ROA) and moth search algorithm (MS) that trains deep learning classifier (DCNN). The analysis using the real databases regarding the performance metrics divulge that the proposed pathology detection module obtained the accuracy, specificity, and sensitivity of 97.020%, 91.698%, and 96.624%. [ABSTRACT FROM AUTHOR]

Siamese network-based object tracking algorithms have recently gained popularity due to continuous improvement in tracking accuracy and robustness. However, these trackers are often limited by inefficient initialization and unstable online update. The model drift accumulates as more frames are processed. To address the above issues, this paper introduced a method that combines both deep learning and conventional regression algorithms (SVR, Support Vector Regression). Specifically, we propose a feature projection algorithm, which can effectively reduce the dimension of the features extracted from deep neural networks and improve the distinguishability of them at the same time. To make the features more robust for SVR training, we further propose two feature aggregation methods at both the channel level and the spatial level. We update the SVR model online instead of the deep neural network to make the tracking process more robust. Extensive experiments on four challenging benchmarks indicate that our proposed tracker is superior to baseline methods both qualitatively and quantitatively. [ABSTRACT FROM AUTHOR]

The ultimate direction of intelligent vehicle management is to achieve artificial intelligence (AI), and data mining is an important supporting technology for AI. The adoption of new AI technology can effectively improve operational efficiency and safety, especially in terms of performance. This paper takes the researches on traffic jam as an example and proposes one algorithm for combination forecasting model based on a segmentation algorithm for traffic flow sequence and BP neural network prediction. In this paper, it also introduces the traffic flow clustering analysis and mining algorithms for congestion events at the intersections. The blocking point algorithm is improved, and experimental analysis is performed through samples. Experimental results show that the algorithm use for combination forecasting model can greatly improve the real-time performance of short-term traffic flow prediction and significantly reduce the prediction error rate. Therefore, this algorithm has practical and innovative significance in the field of intelligent vehicle management. [ABSTRACT FROM AUTHOR]

To solve the problem in the process of weld seam tracking, a new prediction model for welding deviation based on the weld pool image centroid has been proposed in the paper. First, some weld images under different weld currents were captured by a vision sensor. A composite filter system, which is composed of narrow-band and neutral filters, is used to reduce the disturbance of weld arc. So, several clear weld pool images can be obtained. Then a frontier of weld pool is chosen to be the processing region. Median filter and gray transformation operations are used to enhance the contrast of processing region. On this basis, the variation trend of centroid difference and welding deviation were analyzed. The centroid difference value and the weld current were determined to be welding status parameters. Moreover, a BP neural network was set up, which was composed of three layers. Next, elastic gradient descent method was used to be the training function. So a prediction model between the welding status parameters and and the welding deviation was set up. In the end of the paper, several experiments were performed to test the accuracy of the setup prediction model. The results showed that prediction values of welding deviation calculated by the vision model are fit to the real measured values. The final errors of the vision model under the weld current 70A and 73A were 0.033mm and 0.027mm, which showed excellent accuracy, environmental suitability and intelligence of the model. [ABSTRACT FROM AUTHOR]

Deep learning technology has greatly improved the performance of target tracking, but most recently developed tracking algorithms are short-term tracking algorithms, which cannot meet the actual engineering needs. Based on the Siamese network structure, this paper proposes a long-term tracking framework with a persistent tracking capability. The global proposal module extends the search area globally through the construction of a feature pyramid. The local regression module is mainly responsible for the confidence evaluation of the candidate regions and for performing more accurate bounding box regression. To improve the discriminative ability of the regression network, the error samples are eliminated by synthesizing the temporal information and are then classified through a verification module in advance. Experiments on the VOT long-term tracking dataset and the UAV20L aerial dataset show that the proposed algorithm achieves state-of-the-art performance. [ABSTRACT FROM AUTHOR]

Deep learning algorithms have shown superior performance than traditional algorithms when dealing with computationally intensive tasks in many fields. The algorithm model based on deep learning has good performance and can improve the recognition accuracy in relevant applications in the field of computer vision. TensorFlow is a flexible opensource machine learning platform proposed by Google, which can run on a variety of platforms, such as CPU, GPU, and mobile devices. TensorFlow platform can also support current popular deep learning models. In this paper, an image recognition toolkit based on TensorFlow is designed and developed to simplify the development process of more and more image recognition applications. The toolkit uses convolutional neural networks to build a training model, which consists of two convolutional layers: one batch normalization layer before each convolutional layer, and the other pooling layer after each convolutional layer. The last two layers of the model use the full connection layer to output recognition results. Batch gradient descent algorithm is adopted in the optimization algorithm, and it integrates the advantages of both the gradient descent algorithm and the stochastic gradient descent algorithm, which greatly reduces the number of convergence iterations and has little influence on the convergence effect. The total training parameters of the toolkit model reach 1.7 million. In order to prevent overfitting problems, the dropout layer before each full connection layer is added and the threshold of 0.5 is set in the design. The convolution neural network model is trained and tested by the MNIST set on TensorFlow. The experimental result shows that the toolkit achieves the recognition accuracy of 99% on the MNIST test set. The development of the toolkit provides powerful technical support for the development of various image recognition applications, reduces its difficulty, and improves the efficiency of resource utilization. [ABSTRACT FROM AUTHOR]

The corrosion of reinforcement has always been a problem to be solved in the field of architecture. In this paper, the corrosion characteristics of chromium alloy steel under different pH conditions are studied. The impedance characteristics and equivalent circuit are predicted by neural network model. First of all, in simulated pore solution with different pH values, the characteristics of Nyquist impedance spectroscopy of the whole chromium alloy under passivation stage and the damaged passivation film of reinforcing bars under initial corrosion stage have been found. Then, according to the difference of impedance characteristics under different pH values, different equivalent circuits have been established and χ 2 values of different equivalent circuits under different chloride ion concentration have been calculated. By fitting the electrochemical parameters of the equivalent circuit with χ 2 values, the equivalent circuit model which can be predicted by neural network has good consistency with the equivalent circuit which can be predicted by χ 2 values. [ABSTRACT FROM AUTHOR]

Vision-based behavior recognition is the analysis and recognition of human behavior in video. It has been widely used in many aspects such as multimedia information retrieval, behavior monitoring, and robot perception. This paper uses the Independent Subspace Analysis (ISA) deep network model feature extraction method, which is based on the ISA model and neural network theory, and combines data preprocessing methods, K -means clustering methods, and Support Vector Machine (SVM) classifiers to achieve video classification and identification of human behavior. The ISA-based deep network model feature extraction method is an unsupervised learning method that can obtain behavior characteristics with good invariance and characterization capabilities in video human behavior. The experiment was conducted on the basis of the Hollywood2 human behavior data set. This experiment was compared with other commonly used human behavior feature extraction and recognition methods. The experimental results validated the effectiveness and advantages of this method in the classification and recognition of human behavior. [ABSTRACT FROM AUTHOR]

In the era of globalization, manufacturing industries are facing intense pressure to prevent unexpected breakdowns, reduce maintenance cost and increase plant availability. Induction motors are the most sought-after prime movers in modern-day industries due to their robustness. Recently, research has picked up a fervent pace in the area of fault diagnosis of electrical machines. This paper presents the application of Support Vector Machine (SVM) and Artificial Neural Network (ANN)-based system to diagnose the vibration and Instantaneous Power (IP)-based responses of rolling element bearings and broken rotor bars in an induction motor. The dimensionality of the extracted features was reduced using Principal Component Analysis (PCA) and thereafter the selected features were ranked in order of relevance using the Sequential Floating Forward Selection (SFFS) method for reducing the size of input features and finding the most optimal feature set. A comparative analysis of the effectiveness of SVM and ANN is carried out using statistical parameters extracted from vibration and IP signals. The highest accuracy of 92.5% and 98.2% was achieved for vibration and IP signatures, respectively, using the proposed SFFS-based feature selection technique and ANN classification method. The results reveal that ANN has better performance than SVM and the proposed strategy can be used for automatic recognition of machine faults. The use of this type of intelligent system helps in avoiding unwanted and unplanned system shutdowns due to the failure of the motor. [ABSTRACT FROM AUTHOR]

In the actual cotton planting environment, rapid change of light within a day, reflection from different backgrounds and different weather conditions can affect the imaging of cotton. Therefore, the crop object segmentation is difficult. Images which were captured in 12 natural scenes during cotton planting, including three weather conditions, such as sunny, cloudy and rainy and four soil cover conditions, such as white mulch film, black mulch film, straw and bare soil were regarded as the research objects. This paper presents the cotton leaf segmentation method based on Immune algorithm and pulse coupled neural networks (PCNN). First, 17 color components of white mulch film, black mulch film, straw, bare soil and cotton under the conditions of sunny, cloudy and rainy days were analyzed by using statistical method. Three high feasible and anti-light color components were selected by histogram statistical with mean gray value. Second, the optimal parameters of PCNN model and the optimal number of iterations were determined by using immune algorithm optimization theory, and the method in this paper was tested by using 1200 cotton images which were captured under 12 natural scenes. Finally, the test results showed that this method can distinguish cotton target region from soil and other background regions. Meanwhile, for reflection of mulch film, crop shadow, dark light, complex background, noise, etc. which are often appeared in natural scene, four image segmentation methods of Otsu algorithm, -Means algorithm, FCM algorithm and PCNN were compared with the proposed method in this paper. The segmentation result showed that the proposed method has good resistance to change of light and complex background. The average of the proposed method is 6.5%, significantly lower than that of other four methods and the performance is better than other four methods. This method can segment cotton images in different weather conditions and different backgrounds accurately under complex natural conditions. It will contribute to the subsequent growth status determination and pest diagnosis of cotton. [ABSTRACT FROM AUTHOR]

Recent developments in speech synthesis have produced systems capable of producing speech which closely resembles natural speech, and researchers now strive to create models that more accurately mimic human voices. One such development is the incorporation of multiple linguistic styles in various languages and accents. Speech synthesis based on Hidden Markov Models (HMM) is of great interest to researchers, due to its ability to produce sophisticated features with a small footprint. Despite some progress, its quality has not yet reached the level of the current predominant unit-selection approaches, which select and concatenate recordings of real speech, and work has been conducted to try to improve HMM-based systems. In this paper, we present an application of long short-term memory (LSTM) deep neural networks as a postfiltering step in HMM-based speech synthesis. Our motivation stems from a similar desire to obtain characteristics which are closer to those of natural speech. The paper analyzes four types of postfilters obtained using five voices, which range from a single postfilter to enhance all the parameters, to a multi-stream proposal which separately enhances groups of parameters. The different proposals are evaluated using three objective measures and are statistically compared to determine any significance between them. The results described in the paper indicate that HMM-based voices can be enhanced using this approach, specially for the multi-stream postfilters on the considered objective measures. [ABSTRACT FROM AUTHOR]

Visual tracking is still a challenging fundamental task in the field of computer vision, especially in complex scenes such as long-term occlusion, nonrigid deformation and fast movement. In this paper, we presented an RGB-D tracker based on the Siamese Region Proposal Network and Depth Information. First, Siamese Network with shared parameters was constructed to perform feature extraction on the target patch and search area. Second, Region Proposal Network was constructed to estimate the target position in the RGB channels. At the same time, the depth information in the RGB-D video was used to determine the target occlusion state and fine-tune the target position. Finally, the tracker used depth information to achieve occlusion recovery when the target was fully occluded. The experimental result shows that the method has better performance in tracking accuracy and tracking speed on the large-scale Princeton RGB-D Tracking Benchmark (PTB) dataset. [ABSTRACT FROM AUTHOR]

This paper explores the performance and obtains a reasonable cleaning effect of the cleaning system of combine harvester and studies the relationship between the cleaning effect of the combine harvester cleaning system and its influencing factors. We established a neural network model between the cleaning loss rate and the clean system parameters. First, we tested the results of the cleaning performance of each group under different combinations of conditions, and analyzed the direct or indirect relationship between the cleaning loss rate and the parameters in the experiment under each working condition. Then, according to the experimental data obtained in the experiment, we predict the clearance loss rate for several sets of conditions by this model. The experimental results show that the prediction results of the model can meet the experimental requirements under the condition that the accuracy is not very high. [ABSTRACT FROM AUTHOR]

Fire is one of the most common serious disasters in human society. It is a kind of burning phenomenon that is out of control in time and space. When a fire occurs, how to detect the fire quickly and remove it in the budding state has become the key content of fire control work. Outdoor fire is very common in our daily life, and once it occurs without effective and timely control, it will cause huge losses. Therefore, it is particularly important to study an intelligent alarm system for outdoor fire. Generally, fire detection technology can be divided into sensor fire detection technology and image fire detection technology. Sensor fire detection technology is low cost and easy to design, but its application field is limited. Under the interference of many factors outside, misjudgement and missed judgement will occur. Image fire detection technology can achieve certain detection function through manual design of features and classifiers, but there are still defects in the application in the actual diversified environment. With the development of neural network technology in recent years, it has made great breakthroughs in the field of image recognition. Its judgment type is obtained through a large number of data training algorithms. Because of its automatic feature extraction and classification characteristics, it can effectively adapt to the external environment. Therefore, this paper proposes an end-to-end two-stream neural network model to detect fires, uses fire video on the network to train the algorithm, and then uses the fire database to test. Compared with the existing fire detection algorithms, it is found that the proposed method has good practicability and versatility, and provides a good reference for the development of fire detection technology. [ABSTRACT FROM AUTHOR]

Person re-identification is one of the indispensable elements for visual surveillance. It assigns consistent labeling for the same person within the field of view of the same camera or even across multiple cameras. While handcrafted feature extraction is certainly one way of approaching this problem, in many cases, these features are becoming more and more complex. Besides, training a deep convolutional neural network (CNN) from scratch is difficult because it requires a large amount of labeled training data and a great deal of expertise to ensure proper convergence. This paper explores the following three main strategies for solving the person re-identification problem: (i) using handcrafted features, (ii) using transfer learning based on a pre-trained deep CNN (trained for object categorization) and (iii) training a deep CNN from scratch. Our experiments consistently demonstrated that: (1) The handcrafted features may still have favorable characteristics and benefits especially in cases where the learning database is not sufficient to train a deep network. (2) A fully trained Siamese CNN outperforms handcrafted approaches and the combination of pre-trained CNN with different re-identification processes. (3) Moreover, our experiments demonstrated that pre-trained features and handcrafted features perform equally well. These experiments have also revealed the most discriminative parts in the human body. [ABSTRACT FROM AUTHOR]

The paper presents a novel approach for classification of faults in Extra High Voltage (EHV) transmission line with series compensation. The proposed algorithm utilizes single end currents extracted from three phases of a transmission line given to a fault detection and classification system. A detailed model is constructed to analyze fault patterns occurring on a dual feed system with multiple series compensation provided on EHV transmission line. The algorithm uses a full cycle of post-fault currents. A Multiresolution Analysis Wavelet-based decomposition technique is used to provide a joint time frequency analysis. Extensive study is done by designing different fault classifiers using Support Vector Machine (SVM) with different feature vector groups. The SVMs with different parameters are compared to show performance of SVMs in given feature space of faults. A new algorithm is proposed with Ensemble method having group of different classifiers, namely, Artificial Neural Network (ANN), K-Nearest Neighborhood (KNN) and SVM. A combination of feature selection with Ensemble Classifiers is trained and tested on a wide range of fault patterns. A significant improvement in performance is obtained with different combination of features in Ensemble Classifier using subspace partition method.The proposed Ensemble Classifier provides an accuracy of 99.5%. [ABSTRACT FROM AUTHOR]

As the practical applications in other fields, high-resolution images are usually expected to provide a more accurate assessment for the air-coupled ultrasonic (ACU) characterization of wooden materials. This paper investigated the feasibility of applying single image super-resolution (SISR) methods to recover high-quality ACU images from the raw observations that were constructed directly by the on-the-shelf ACU scanners. Four state-of-the-art SISR methods were applied to the low-resolution ACU images of wood products. The reconstructed images were evaluated by visual assessment and objective image quality metrics, including peak signal-to-noise-ratio and structural similarity. Both qualitative and quantitative evaluations indicated that the substantial improvement of image quality can be yielded. The results of the experiments demonstrated the superior performance and high reproducibility of the method for generating high-quality ACU images. Sparse coding based super-resolution and super-resolution convolutional neural network (SRCNN) significantly outperformed other algorithms. SRCNN has the potential to act as an effective tool to generate higher resolution ACU images due to its flexibility. [ABSTRACT FROM AUTHOR]

The most significant part of any autonomous intelligent robot is the localization module that gives the robot knowledge about its position and orientation. This knowledge assists the robot to move to the location of its desired goal and complete its task. Visual Odometry (VO) measures the displacement of the robots' camera in consecutive frames which results in the estimation of the robot position and orientation. Deep Learning, nowadays, helps to learn rich and informative features for the problem of VO to estimate frame-by-frame camera movement. Recent Deep Learning-based VO methods train an end-by-end network to solve VO as a regression problem directly without visualizing and sensing the label of training data in the training procedure. In this paper, a new approach to train Convolutional Neural Networks (CNNs) for the regression problems, such as VO, is proposed. The proposed method first changes the problem to a classification problem to learn different subspaces with similar observations. After solving the classification problem, the problem converts to the original regression problem to solve using the knowledge achieved by solving the classification problem. This approach helps CNN to solve regression problem globally in a local domain learned in the classification step, and improves the performance of the regression module for approximately 10%. [ABSTRACT FROM AUTHOR]

With the steady growth of the economy and the rapid development of modern industrial technology, the problem of environmental pollution has increased. To continue to develop, it is necessary to thoroughly implement the sustainable development strategy, and we must pay more attention to environmental issues. One of the important management tools implemented in China for environmental management is environmental quality monitoring and evaluation. Environmental quality monitoring can scientifically evaluate the environmental quality of a region, scientifically evaluate and forecast the environmental management and environmental engineering, and provide scientific basis for environmental management, environmental engineering, formulation of environmental standards, environmental planning, comprehensive prevention and control of environmental pollution, and ecological environment construction. This paper will discuss the basic principles of neural network and the implementation process of MATLAB and in the MATLAB software implementation and display process. At the same time, the results of different parameters are analyzed through experiments, and the network parameters are constantly adjusted to improve the accuracy of the evaluation results. Taking the regional environment as an example, two monitoring methods are proposed, and a variety of neural network models are used to analyze each prediction method. Case study results show that the latter method has a better prediction effect. [ABSTRACT FROM AUTHOR]

With the outstanding performance in 2014 at the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14), an effective convolutional neural network (CNN) model named GoogLeNet has drawn the attention of the mainstream machine learning field. In this paper we plan to take an insight into the application of the GoogLeNet in the Handwritten Chinese Character Recognition (HCCR) on the database HCL2000 and CASIA-HWDB with several necessary adjustments and also state-of-the-art improvement methods for this end-to-end approach. Through the experiments we have found that the application of the GoogLeNet for the Handwritten Chinese Character Recognition (HCCR) results into significant high accuracy, to be specific more than 99% for the final version, which is encouraging for us to further research. [ABSTRACT FROM AUTHOR]

Emotion recognition plays an indispensable role in human–machine interaction system. The process includes finding interesting facial regions in images and classifying them into one of seven classes: angry, disgust, fear, happy, neutral, sad, and surprise. Although many breakthroughs have been made in image classification, especially in facial expression recognition, this research area is still challenging in terms of wild sampling environment. In this paper, we used multi-level features in a convolutional neural network for facial expression recognition. Based on our observations, we introduced various network connections to improve the classification task. By combining the proposed network connections, our method achieved competitive results compared to state-of-the-art methods on the FER2013 dataset. [ABSTRACT FROM AUTHOR]

The fault diagnosis intelligent algorithm makes full use of the associative memory and pattern recognition function of the neural network to compare the abnormal value of various parameters of the engine fault with the reference value of the known fault mode, which can shorten the fault diagnosis time and improve the diagnosis efficiency. BP neural network model as one of the most widely used neural network models in the world is of significance to solve nonlinear complex problems. Of course, there are also some deficiencies in it, such as long training time and ease to trap into local minimum. This paper utilized the global search advantage of genetic algorithm to optimize the optimal weight and threshold value of BP neural network. Furthermore, an improved BP neural network was put forward, which is greatly improved in stability, generalization and convergence rate. Taking fault diagnosis of automobile engine as an example, a simulation experiment was carried out on the established model. The research results indicate that improved neural network model owns a higher accuracy than pure GA model or BP neural network model (with an average accuracy improved by 19.04% than traditional model), and its effect is satisfactory. [ABSTRACT FROM AUTHOR]

The lack of research on the metering characteristics of electricity power meters under complex conditions is a major obstacle to the on-site verification of electrical energy metering equipment. Establishing a predictive model for electricity power meter errors offers an effective way of dealing with this issue. Deep learning has been proven to have the capacity to reduce end-to-end dimensionality and improve recognition. Through the analysis of the back propagation process in residual networks, an improved residual network is set out in this paper. While preserving the advantages of residual network gradient propagation, it adds an adjustable shortcut and designs a convex k -parameter strategy that can be improved according to different processing objects. Experimental results show that the predicted errors produced by the proposed technique are significantly lower than in a comparable model. At the same time, the improved residual network does not increase the network's complexity. [ABSTRACT FROM AUTHOR]

At present, the application of deep learning algorithms in two-dimensional color image detection is being continuously innovated and broken. With the popularity of depth cameras, color image detection methods with depth information need to be upgraded. To solve this problem, a multi-target detection algorithm based on 3D DSF R-CNN (Double Stream Faster R-CNN, Convolution Neural Network based on Candidate Region) is proposed in this paper. The RGB information and the depth information of the image are given to two input elements of the convolution network with the same structure and weight sharing, and an optimal fusion weight algorithm is used to determine the weight of the fusion target in accordance with the recognition accuracy of the recognition targets under the single modal information, so as to ensure the most efficient fusion result. After several convolution operations, the independent features are extracted and the two networks are fused according to the optimal weights in the convolution layer. With the conducting of convolution and extract the fused features, and finally get the output through the full link layer. Compared with the previous two-dimensional convolution network algorithm, this algorithm improves the detection rate and success rate while ensuring the detection time. The experimental result shows that this method has strong robustness for complex illumination and partial occlusion, and has excellent detection results under non-restrictive conditions. [ABSTRACT FROM AUTHOR]

Neural information coding is helpful in understanding the working mechanism of the nervous system. Currently, most of the studies are based on the neural network which is based on excitatory synaptic plasticity. However, the inhibitory synaptic plasticity also plays an important role in the regulation of neural network. For presenting better biological authenticity, a spiking neural network was constructed based on the synaptic plasticity regulation mechanism in this study. The synaptic plasticity regulation mechanism contains excitatory and inhibitory synapses. The characteristics of neural information coding under AC electric field stimulation were studied from the perspective of time coding (inter-spike interval coding) and rate coding (average rate coding). The experimental results indicate that inter-spike intervals decrease and the firing rate of neurons increases under AC electric field stimulation. With the increase of the stimulation intensity, inter-spike intervals are decreased and the firing rate of neurons is increased. The neurons whose average firing rate increases can be raised as a neuron cluster to express the information. The results of this paper help us to understand the mechanism of information processing of the brain, and bring new ideas to the engineering applications such as neural computation and artificial intelligence. [ABSTRACT FROM AUTHOR]

Domain adaptation aims to generalize the classification model from a source domain to a different but related target domain. Recent studies have revealed the benefit of deep convolutional features trained on a large dataset (e.g. ImageNet) in alleviating domain discrepancy. However, literatures show that the transferability of features decreases as (i) the difference between the source and target domains increases, or (ii) the layers are toward the top layers. Therefore, even with deep features, domain adaptation remains necessary. In this paper, we propose a novel unsupervised domain adaptation (UDA) model for deep neural networks, which is learned with the labeled source samples and the unlabeled target ones simultaneously. For target samples without labels, pseudo labels are assigned to them according to their maximum classification scores during training of the UDA model. However, due to the domain discrepancy, label noise generally is inevitable, which degrades the performance of the domain adaptation model. Thus, to effectively utilize the target samples, three specific robust deep softmax regression (RDSR) functions are performed for them with high, medium and low classification confidence respectively. Extensive experiments show that our method yields the state-of-the-art results, demonstrating the effectiveness of the robust deep softmax regression classifier in UDA. [ABSTRACT FROM AUTHOR]

Mathematical morphology has been applied as a collection of nonlinear operations related to object features in images. In this paper, we present morphological layers in deep learning framework, namely MorphNet, to perform atomic morphological operations, such as dilation and erosion. For propagation of losses through the proposed deep learning framework, we approximate the dilation and erosion operations by differential and smooth multivariable functions of the softmax function, and therefore enable the neural network to be optimized. The proposed operations are analyzed by the derivative of approximation functions in the deep learning framework. Experimental results show that the output structuring element of a morphological neuron and the target structuring element are matched to confirm the efficiency and correctness of the proposed framework. [ABSTRACT FROM AUTHOR]

With the continuous expansion of the application scope of computer network technology, various malicious attacks that exist in the Internet range have caused serious harm to computer users and network resources. This paper attempts to apply artificial intelligence (AI) to computer network technology and research on the application of AI in computing network technology. Designing an intrusion detection model based on improved back propagation (BP) neural network. By studying the attack principle, analyzing the characteristics of the attack method, extracting feature data, establishing feature sets, and using the agent technology as the supporting technology, the simulation experiment is used to prove the improvement effect of the system in terms of false alarm rate, convergence speed, and false negative rate, the rate reached 86.7%. The results show that this fast algorithm reduces the training time of the network, reduces the network size, improves the classification performance, and improves the intrusion detection rate. [ABSTRACT FROM AUTHOR]

Recently, deep convolutional neural networks have resulted in noticeable improvements in image classification and have been used to transfer artistic style of images. Gatys et al. proposed the use of a learned Convolutional Neural Network (CNN) architecture VGG to transfer image style, but problems occur during the back propagation process because there is a heavy computational load. This paper solves these problems, including the simplification of the computation of chains of derivatives, accelerating the computation of adjustments, and efficiently choosing weights for different energy functions. The experimental results show that the proposed solutions improve the computational efficiency and render the adjustment of weights for energy functions easier. [ABSTRACT FROM AUTHOR]

Due to the functionality of dynamic mapping for nonlinear complex data, BP neural network (BP-NN) as a typical neural network has increasingly been applied to a variety of applications. Although it has been successfully applied, its prominent shortcoming, such as the local optimum problem and the setting problem for the initial parameter of neural network, have not been completely eliminated. In this paper, an optimization algorithm for the architecture, weights and thresholds of neural networks using an improved gene expression programming (IGEP) was presented. The algorithm effectively combines the global search ability of GEP and the local search ability of BP-NN. To obtain a better efficiency, the basic GEP was improved by the dynamic adjustment of the fitness function, genetic operators and the number of evolutionary generations. The experimental results show that the IGEP-BP algorithm is an effective method for evolving neural network. [ABSTRACT FROM AUTHOR]

Homology Continuity is a fundamental property of the nature, but few of the traditional pattern recognition algorithms were aware of it. Firstly, this paper gives a brief description to the Principle of Homology Continuity (PHC), and tries to mathematically redefine it. Then, we introduce a PHC-based pattern learning method — Geometrical Covering Learning (GCL), following the Hyper sausage neural network as an instance of GCL. Lastly, we propose a GCL solution to the “two-spirals” pattern recognition problem. The final experimental results show that the new method is feasible and efficient. [ABSTRACT FROM AUTHOR]

This paper introduces mind evolutionary algorithm (MEA) into the application of short-term traffic flow prediction, and proposes a short-term traffic flow prediction model of wavelet neural network based on mind evolutionary algorithm (MEA-WNN). The optimal connection weight and wavelet parameters of wavelet neural network (WNN) are searched globally by MEA, and the convergence capacity of wavelet neural network is improved. The experimental data show that, compared with the prediction model of the traditional WNN and the WNN based on genetic algorithm (GA-WNN), the prediction model of MEA-WNN has higher global prediction accuracy. [ABSTRACT FROM AUTHOR]

Learning vector quantization (LVQ) network and back-propagation (BP) network are constructed easily making use of MATLAB toolbox on the basis of maintaining the recognition rate. Face images are randomly selected from images set as training data of LVQ network and BP network. LVQ algorithm and BP algorithm are used to train network. The automatic recognition of face orientation is realized when the system obtains convergence network. First, all images are processed by edge detection. Then feature vectors representing position of the eye were extracted from edge detected images. Feature vectors of training set are sent to network to adjust the parameters which ensures the convergence speed and performance of the network. Experimental results show that the constructed LVQ network and BP network can judge face orientation according to feature vectors of input images. Generally, the recognition rate of LVQ network is higher than that of BP network. The LVQ network and BP network are both feasible and effective for face orientation recognition to some extent. The advantage of this work is that the recognition system is efficient and easy to promote. This paper focuses on how to use MATLAB easily to design identification network rather than the complexity of identification system. The future research will focus on the stability and robustness of recognition network. [ABSTRACT FROM AUTHOR]

Pedestrian detection provides manager of a smart city with a great opportunity to manage their city effectively and automatically. Specifically, pedestrian detection technology can improve our secure environment and make our traffic more efficient. In this paper, all of our work both modification and improvement are made based on YOLO, which is a real-time Convolutional Neural Network detector. In our work, we extend YOLO’s original network structure, and also give a new definition of loss function to boost the performance for pedestrian detection, especially when the targets are small, and that is exactly what YOLO is not good at. In our experiment, the proposed model is tested on INRIA, UCF YouTube Action Data Set and Caltech Pedestrian Detection Benchmark. Experimental results indicate that after our modification and improvement, the revised YOLO network outperforms the original version and also is better than other solutions. [ABSTRACT FROM AUTHOR]

The necessary step in the diagnosis of leukemia by the attending physician is to classify the white blood cells in the bone marrow, which requires the attending physician to have a wealth of clinical experience. Now the deep learning is very suitable for the study of image recognition classification, and the effect is not good enough to directly use some famous convolution neural network (CNN) models, such as AlexNet model, GoogleNet model, and VGGFace model. In this paper, we construct a new CNN model called WBCNet model that can fully extract features of the microscopic white blood cell image by combining batch normalization algorithm, residual convolution architecture, and improved activation function. WBCNet model has 33 layers of network architecture, whose speed has greatly been improved compared with the traditional CNN model in training period, and it can quickly identify the category of white blood cell images. The accuracy rate is 77.65% for Top-1 and 98.65% for Top-5 on the training set, while 83% for Top-1 on the test set. This study can help doctors diagnose leukemia, and reduce misdiagnosis rate. [ABSTRACT FROM AUTHOR]

Today, in the construction of smart city, the development of self-driving technology plays the key role. The explosion of convolutional neural network (CNN) technology has made it possible to utilize end-to-end tasks with images. However, today's CNN has deeper, more accurate characteristics. If we do not improve the calculation method to reduce the number of network parameters, this feature makes it very difficult for us to run neural network computing in small devices. In this paper, we further optimize the network computing methods based on MobileNets to reduce number of network parameters. At the same time, in the network structure, we add BatchNormalization and Swish activation function. We designed our own network in the end-to-end prediction for steering angle in the self-driving car task. From the final simulation results, our neural network's storage space can be reduced and the execution speed of neural network can be improved while maintaining the accuracy of the neural network. [ABSTRACT FROM AUTHOR]