Search

Previously, single classification models were mainly studied to classify human protein cell images, i.e., to identify a certain protein based on a set of different cells. However, a classifier can identify only one protein, in fact, a single cell usually consists of multiple proteins, and the proteins are not completely independent of each other. In this paper, we build a human protein cell classification model by multi-label learning. The logical relationship and distribution characteristics among the labels are analyzed to determine the different proteins contained in a set of different cells (i.e., containing multiple elements in the output space). In this paper, using human protein image data, we conducted comparison experiments on pre-trained Xception and InceptionResnet V2 to optimize the two models in terms of data augmentation, channel settings, and model structure. The results show that the Optimized InceptionResnet V2 model achieves high performance in the classification task. The final accuracy of the Optimized InceptionResnet V2 model we obtained reached 96.1%, which is a 2.82% improvement relative to that before the optimized model. [ABSTRACT FROM AUTHOR]

Nowadays, deep neural network has become the prime approach for enhancing speech signals as it yields good results compared to the traditional methods. This paper describes the transformation in the enhanced speech signal by applying the deep convolutional neural network (Deep CNN), which can model nonlinear relationships and compare it with the Wiener filtering method, which is the best technique for speech enhancement among the traditional methods. Denoising is performed in the frequency domain and converted back to the time domain to analyze performance metrics such as speech quality and speech intelligibility. The speech quality is analyzed based on the signal to noise ratio (SNR) and perceptual evaluation of speech quality (PESQ). Speech intelligibility is analyzed by short-time objective intelligibility (STOI). Both the methods evaluated the denoised speech, and the analysis made on the results shows that the SNR of the conventional Wiener filtering method is much improved when compared with Deep CNN. However, the PESQ and STOI of Deep CNN-based enhanced speech outperform the Wiener filtering method. The performance metrics indicate that Deep CNN achieves better results than the conventional technique. [ABSTRACT FROM AUTHOR]

Recognition of finger vein patterns is essential technique that analyses the finger vein patterns to enable accurate authentication of an individual. A proper, accurate and quick learning of patterns is essentially required for improving the classification pattern. It is essential in developing an intelligent algorithm to effectively study and classify the patterns. In this paper, we develop an improved deep learning hybrid model for feature extraction and classification. A dimensional reduction deep neural network (DR-DNN) model has included a dimensional reduction model for extracting the essential features by reducing the dimensionality of feature datasets. A convolutional neural network (CNN) helps in classifying the benign vein patterns from the malignant vein patterns. The effectiveness is compared against existing deep learning classifiers to measure how effective the deep learning model is used for classifying finger vein patterns for biometric authentication. The results shows that the proposed method achieves an accuracy rate of 97.16% for the proposed method, where the other existing methods including CNN, Recurrent Neural Network (RNN) and Deep Neural Nets (DNN) has an accuracy rate of 86%, 80.66% and 88.31%, respectively. [ABSTRACT FROM AUTHOR]

Conventional practices of bridge visual inspection present several limitations, including a tedious process of analyzing images manually to identify potential damages. Vision-based techniques, particularly Deep Convolutional Neural Networks, have been widely investigated to automatically identify, localize, and quantify defects in bridge images. However, massive datasets with different annotation levels are required to train these deep models. This paper presents a dataset of more than 6900 images featuring three common defects of concrete bridges (i.e., cracks, efflorescence, and spalling). To overcome the challenge of limited training samples, three Transfer Learning approaches in fine-tuning the state-of-the-art Visual Geometry Group network were studied and compared to classify the three defects. The best-proposed approach achieved a high testing accuracy (97.13%), combined with high F1-scores of 97.38%, 95.01%, and 97.35% for cracks, efflorescence, and spalling, respectively. Furthermore, the effectiveness of interpretable networks was explored in the context of weakly supervised semantic segmentation using image-level annotations. Two gradient-based backpropagation interpretation techniques were used to generate pixel-level heatmaps and localize defects in test images. Qualitative results showcase the potential use of interpretation maps to provide relevant information on defect localization in a weak supervision framework. [ABSTRACT FROM AUTHOR]

Pedestrian Attribute Recognition (PAR) can provide valuable clues for several innovative surveillance applications. It is also a difficult task because inference of the multiple attributes at a far distance is challenging in real complex scenarios. Most existing methods improve the PAR with visual attention mechanisms or body-part detection modules, which increase the complexity of networks and require manual annotations of the human body. Also, uneven data distribution, leading to a decline in recall values, is still underestimated. This paper presents a novel multi-label optimization algorithm to mitigate these issues, named Multi-label Contrastive Focal Loss (MCFL). Specifically, we first propose a multi-label focal loss to emphasize the error-prone and minority attributes with a separated re-weighting scheme. And then, we introduce a multi-label contrastive learning strategy based on the multi-label divergences to help the deep network to distinguish the hard fine-grained attributes. We conduct extensive experiments on seven PAR benchmarks, and results indicate that the proposed MCFL with the native ResNet-50 backbone surpasses the state-of-the-art comparison methods in mean accuracy and recall. [ABSTRACT FROM AUTHOR]

MRI-Only Radiation (RT) now avoids some of the issues associated with employing Computed Tomography(CT) in RT chains, such as MRI registration to a separate CT, excess dosage administration, and the cost of recurrent imaging. The fact that MRI signal intensities are unrelated to the biological tissue's attenuation coefficient poses a problem. This raises workloads, creates uncertainty as a result of the required inter-modality image registrations, and exposes patients to needless radiation. While using only MRI would be preferable, a method for estimating a pseudo-CT (pCT)or synthetic-CT(sCT) for producing electron density maps and patient positioning reference images is required. As Deep Learning(DL) is revolutionized in so many fields these days, an effective and accurate model is required for generating pCT from MRI. So, this paper depicts an efficient DL model in which the following are the stages: a) Data Acquisition where CT and MRI images are collected b) preprocessing these to avoid the anomalies and noises using techniques like outlier elimination, data smoothening and data normalizing c) feature extraction and selection using Principal Component Analysis (PCA) & regression method d) generating pCT from MRI using Deep Convolutional Neural Network and UNET (DCNN-UNET). We here compare both feature extraction (PCA) and classification model (DCNN-UNET) with other methods such as Discrete Wavelet Tranform(DWT), Independent Component Analysis(ICA), Fourier Transform and VGG16, ResNet, AlexNet, DenseNet, CNN (Convolutional Neural Network)respectively. The performance measures used to evaluate these models are Dice Coefficient(DC), Structured Similarity Index Measure(SSIM), Mean Absolute Error(MAE), Mean Squared Error(MSE), Accuracy, Computation Time in which our proposed system outperforms better with 0.94±0.02 over other state-of-art models. [ABSTRACT FROM AUTHOR]

The fine identification of vehicle color can assist in criminal investigation or intelligent traffic management law enforcement. Since almost all vehicle-color datasets that are used to train models are collected in good weather, the existing vehicle-color recognition algorithms typically show poor performance for outdoor visual tasks. In this paper we construct a new R a i n V e h i c l e C o l o r -24 dataset by rain-image rendering using P S technology and a S y R a G A N algorithm based on the V e h i c l e C o l o r -24 dataset. The dataset contains a total of 40,300 rain images with 125 different rain patterns, which can be used to train deep neural networks for specific vehicle-color recognition tasks. Experiments show that the vehicle-color recognition algorithms trained on the new dataset R a i n V e h i c l e C o l o r -24 improve accuracy to around 72 % and 90 % on rainy and sunny days, respectively. The code is available at humingdi2005@github.com. [ABSTRACT FROM AUTHOR]

Nitrosamine is a carcinogenic chemical used as a preservative in red meat whose identification is an ordeal. This paper presents a computer vision-based non-destructive method for identifying quality disparities between preservative treated and untreated (control) red meat. To access the discrepancy in the quality of red meat, both traditional machine learning and deep learning-based methods have been used. Support vector machine (SVM) classifier and artificial neural network (ANN) models have been used to detect the presence of nitrosamine in test samples. The paper also made use of different pre-trained deep convolutional neural networks (DCNN) with transfer learning approach such as ResNet-34, ResNet-50, ResNet-101, VGG-16, VGG-19, AlexNet and MobileNetv2 to examine the presence of nitrosamine in the food samples. While the ANN classifier performed better in comparison to the SVM classifier, the highest testing accuracy and F1-score were obtained using the deep learning model, ResNet-101 with 95.45% and 96.54%, respectively. The experimental results demonstrate an improved performance in comparison to the existing methods; indicating the feasibility of the proposed work for food quality control in real-time applications. [ABSTRACT FROM AUTHOR]

In the present paper, deep convolutional neural network (DCNN) is applied to multilocus protein subcellular localization as it is more suitable for multi-class classification. There are two main problems with this application. First, the appropriate features for correlation between multiple sites are hard to find. Second, the classifier structure is difficult to determine as it is greatly affected by the distribution of classified data. To solve these problems, a self-evoluting framework using DCNNs for multilocus protein subcellular localization is proposed. It has three characteristics that the previous algorithms do not. The first is that it combines the ant colony algorithm with the DCNN to form a self-evoluting algorithm for multilocus protein subcellular localization. The second is that it randomly groups subcellular sites using a limited random k-labelsets multi-label classification method. It also solves complex problems in a divide-and-conquer approach and proposes a flexible expansion model. The third is that it realizes the random selection feature extraction method in the positioning process and avoids the defects in individual feature extraction methods. The algorithm in the present paper is tested on the human database, and the overall correct rate is 67.17%, which is higher than that for the stacked self-encoder (SAE), support vector machine (SVM), random forest classifier (RF), or single deep convolutional neural network. Graphical abstract [ABSTRACT FROM AUTHOR]

Lithium-ion batteries are widely used as effective energy storage and have become the main component of power supply systems. Accurate battery state prediction is key to ensuring reliability and has significant guidance for optimizing the performance of battery power systems and replacement. Due to the complex and dynamic operations of lithium-ion batteries, the state parameters change with either the working condition or the aging process. The accuracy of online state prediction is difficult to improve, which is an urgent issue that needs to be solved to ensure a reliable and safe power supply. Currently, with the emergence of artificial intelligence (AI), battery state prediction methods based on data-driven methods have high precision and robustness to improve state prediction accuracy. The demanding characteristics of test time are reduced, and this has become the research focus in the related fields. Therefore, the convolutional neural network (CNN) was improved in the data modeling process to establish a deep convolutional neural network ensemble transfer learning (DCNN-ETL) method, which plays a significant role in battery state prediction. This paper reviews and compares several mathematical DCNN models. The key features are identified on the basis of the modeling capability for the state prediction. Then, the prediction methods are classified on the basis of the identified features. In the process of deep learning (DL) calculation, specific criteria for evaluating different modeling accuracy levels are defined. The identified features of the state prediction model are taken advantage of to give relevant conclusions and suggestions. The DCNN-ETL method is selected to realize the reliable state prediction of lithium-ion batteries. [ABSTRACT FROM AUTHOR]

Phenotype analysis of leafy green vegetables in planting environment is the key technology of precision agriculture. In this paper, deep convolutional neural network is employed to conduct instance segmentation of leafy greens by weakly supervised learning based on box-level annotations and Excess Green (ExG) color similarity. Then, weeds are filtered based on area threshold, K-means clustering and time context constraint. Thirdly, leafy greens tracking is achieved by bipartite graph matching based on mask IoU measure. Under the framework of phenotype tracking, some time-context-dependent phenotype analysis tasks such as growth monitoring can be performed. Experiments show that the proposed method can achieve 0.95 F1-score and 76.3 sMOTSA (soft multi-object tracking and segmentation accuracy) by using weakly supervised annotation data. Compared with the fully supervised approach, the proposed method can effectively reduce the requirements for agricultural data annotation, which has more potential in practical applications. [ABSTRACT FROM AUTHOR]

Pest recognition in the agriculture field plays a critical issue for the farmers which diminishes economic growth. So far, traditional practices were followed by farmers to increase yield production. Nowadays, researchers execute a deep learning approach to classify various kinds of images practically. In this paper, Deep convolutional neural networks (DCNN) are used to recognise ten kinds of pests present in the paddy crop. The data repository contains around 3549 pest images that affect the paddy crops, Since Deep Learning supports well for larger data-set so the data augmentation process is carried out. The neural model is build using various kinds of DCNN architecture, interpretation was made over the models based on the accuracy rate and the performance. The transfer learning approach is applied over the pest data set by fine-tuning the hyperparameters and the layers of the ResNet-50 model. By comparing the resultant value, the fine-tuned ResNet-50 model produced better accuracy of 95.012% among other models. The obtained resultant value describes the effective performance of the model in pest disease classification. [ABSTRACT FROM AUTHOR]

The optimization of the problems significantly improves the solution of the complex problems. The reduction in the feature dimensionality is enormously salient to reduce the redundant features and improve the system accuracy. In this paper, an amalgamation of different concepts is proposed to optimize the features and improve the system classification. The experiment is performed on the facial expression detection application by proposing the amalgamation of deep neural network models with the variants of the gravitational search algorithm. Facial expressions are the movement of the facial components such as lips, nose, eyes that are considered as the features to classify human emotions into different classes. The initial feature extraction is performed with the local binary pattern. The extracted feature set is optimized with the variants of gravitational search algorithm (GSA) as standard gravitational search algorithm (SGSA), binary gravitational search algorithm (BGSA) and fast discrete gravitational search algorithm (FDGSA). The deep neural network models of deep convolutional neural network (DCNN) and extended deep convolutional neural network (EDCNN) are employed for the classification of emotions from imagery datasets of JAFFE and KDEF. The fixed pose images of both the datasets are acquired and comparison based on average recognition accuracy is performed. The comparative analysis of the mentioned techniques and state-of-the-art techniques illustrates the superior recognition accuracy of the FDGSA with the EDCNN technique. [ABSTRACT FROM AUTHOR]

This paper reports a feasible alternative to compile a landslide inventory map (LIM) from remote sensing datasets using the application of an artificial intelligence–driven methodology. A deep convolutional neural network model, called LanDCNN, was developed to generate segmentation maps of landslides, and its performance was compared with the benchmark model, named U-Net, and other conventional object-based methods. The landslides that occurred in Lantau Island, Hong Kong, were taken as the case study, in which the pre- and post-landslide aerial images, and a rasterized digital terrain model (DTM) were used. The assessment reveals that LanDCNN trained with bitemporal images and DTM yields the smoothest and most semantically meaningfully LIM, compared to other methods. This LIM is the most balanced segmentation results, represented by the highest F1 measure among all analyzed cases. With the encoding capability of LanDCNN, the application of DTM as the input renders better LIM production, especially when the landslide signatures are relatively subtle. With the computational setup used in this study, LanDCNN requires ~ 3 min to map landslides from the datasets of approximately 25 km2 in area and with a resolution of 0.5 m. In short, the proposed landslide mapping framework, featured LanDCNN, is scalable to handle the vast amount of remote sensing data from different types of measurements within a short processing period. [ABSTRACT FROM AUTHOR]

Purpose: Early identification of ischemic stroke lesion regions plays a vital role in its treatments like thrombolytic therapy and patients' recovery. Noncontrast computed tomography (ncCT) is the most widespread imaging modality in emergency departments. Unfortunately, it is extremely hard to distinguish the lesion from healthy tissue during the hyper‐acute phase of stroke. In this paper, a two‐stage convolutional neural network‐based method was proposed to identify the invisible ischemic stroke from ncCT. Methods: In order to combine the global and local information of images effectively, a cascaded structure with two coordinated networks was used to detect the suspicious stroke regions on the whole and optimize the detailed localization. In the first stage, an end‐to‐end U‐net with adaptive threshold was proposed to integrate global position, symmetry and gray texture information to detect the suspicious regions. After reducing the interference from most normal regions, a ResNet‐based patch classification network was used to eliminate some false positive samples on suspicious regions by mining deeper image features, contributing to a more precise localization of stroke. Finally, a MAP model was used to optimize the result by combining the classification results of each patch with their spatial constraint information. Results: Three independent experiments, that is, training and testing on dataset from one hospital, on the combination of two, and on the two respectively, were performed on a total of 277 cases from two hospitals to validate the proposed model, The proposed method achieved identification accuracy of 91.89%, 87.21%, and 85.71% in the three experiments, and the final localization accuracy in terms of precise localization of stroke were 82.35%, 83.02%, and 81.40%, respectively, which indicated the robustness and clinical values of the method. Conclusions: There are some deep image feature differences between stroke region and normal region on ncCT images. The proposed two‐stage convolutional neural network model can well seize these features and use them to effectively identify and locate stroke. [ABSTRACT FROM AUTHOR]

In recent years, deep convolutional neural networks (CNNs) have shown record-shattering performance in a variety of computer vision problems, such as visual object recognition, detection and segmentation. These methods have also been utilised in medical image analysis domain for lesion segmentation, anatomical segmentation and classification. We present an extensive literature review of CNN techniques applied in brain magnetic resonance imaging (MRI) analysis, focusing on the architectures, pre-processing, data-preparation and post-processing strategies available in these works. The aim of this study is three-fold. Our primary goal is to report how different CNN architectures have evolved, discuss state-of-the-art strategies, condense their results obtained using public datasets and examine their pros and cons. Second, this paper is intended to be a detailed reference of the research activity in deep CNN for brain MRI analysis. Finally, we present a perspective on the future of CNNs in which we hint some of the research directions in subsequent years. [ABSTRACT FROM AUTHOR]

• In this paper, we propose a variation of deep residual convolutional neural networks with robustness and efficiency in both learning and testing. • More importantly, we propose multiple strategies for model adaptation to the internal contents of the lowresolution input image and analyze their strong points and weaknesses. • Our adaptation especially favors images with repetitive structures or high resolutions. • We hope to arouse the interests of communities in focusing on internal priors, which are limited but have been proved effective and highly relevant. In recent years, impressive advances have been made in single-image super-resolution. Deep learning is behind much of this success. Deep(er) architecture design and external prior modeling are the key ingredients. The internal contents of the low-resolution input image are neglected with deep modeling, despite earlier works that show the power of using such internal priors. In this paper, we propose a variation of deep residual convolutional neural networks, which has been carefully designed for robustness and efficiency in both learning and testing. Moreover, we propose multiple strategies for model adaptation to the internal contents of the low-resolution input image and analyze their strong points and weaknesses. By trading runtime and using internal priors, we achieve improvements from 0.1 to 0.3 dB PSNR over the reported results on standard datasets. Our adaptation especially favors images with repetitive structures or high resolutions. It indicates a more practical usage when our adaption approach applies to sequences or videos in which adjacent frames are strongly correlated in their contents. Moreover, the approach can be combined with other simple techniques, such as back-projection and enhanced prediction, to realize further improvements. [ABSTRACT FROM AUTHOR]

• A new method of accident detection and classification is proposed. • The new method is based on DCNN using the multi-vehicle trajectory data. • Six types of traffic accident are recognized and classified by the proposed model. • The new model can significantly improve the detection and classification accuracy. • The method will help to judge who is liable for an accident. The freeway accident detection and classification have attracted much attention of researchers in the past decades. With the popularity of Global Navigation Satellite System (GNSS) on mobile phones and onboard equipment, increasing amounts of real-time vehicle trajectory data can be obtained more and more easily, which provides a potential way to use the multi-vehicle trajectory data to detect and classify an accident on freeways. The data has the advantages of low cost, high penetration, high real-time performance, and being robust to the outdoor environment. Therefore, this paper proposes a new method for accident detection and classification based on the multi-vehicle trajectory data. Different from the existing methods using GNSS positioning data, the proposed method not only uses the position information of the related vehicles but also tries to capture the development tendencies of the trajectories of accident vehicles over a period of time. A Deep Convolutional Neural Network model is developed to recognize an accident from the normal driving of vehicles and also identify the type of the accident, and the six types of traffic accidents are considered in this study. To train and test the proposed model, the simulated trajectory data is generated based on PC-Crash, including the normal driving trajectories and the trajectories before, in, and after an accident. The results indicate that the detection accuracy of the proposed method can reach up to 100%, and the classification accuracy can reach up to 95%, which both outperform the existing methods using other data. In addition, to ensure the robustness of the detection accuracy, at least 1 s of duration and 5 Hz of frequency for the trajectory data should be adopted in practice. The study will help to accurately and fastly detect an accident, recognize the accident type, and future judge who is liable for the accident. [ABSTRACT FROM AUTHOR]

This paper proposes a data-driven method-based fault diagnosis method using the deep convolutional neural network (DCNN). The DCNN is used to deal with sensor and actuator faults of robot joints, such as gain error, offset error, and malfunction for both sensors and actuators, and different fault types are diagnosed using the trained neural network. In order to achieve the above goal, the fused data of sensors and actuators are used, where both types of fault are described in one formulation. Then, the deep convolutional neural network is applied to learn characteristic features from the merged data to try to find discriminative information for each kind of fault. After that, the fully connected layer does prediction work based on learned features. In order to verify the effectiveness of the proposed deep convolutional neural network model, different fault diagnosis methods including support vector machine (SVM), artificial neural network (ANN), conventional neural network (CNN) using the LeNet-5 method, and long-term memory network (LTMN) are investigated and compared with DCNN method. The results show that the DCNN fault diagnosis method can realize high fault recognition accuracy while needing less model training time. [ABSTRACT FROM AUTHOR]

This paper proposes a deep convolutional neural network model with encoder-decoder architecture to extract road network from satellite images. We employ ResNet-18 and Atrous Spatial Pyramid Pooling technique to trade off between the extraction precision and running time. A modified cross entropy loss function is proposed to train our deep model. A PointRend algorithm is used to recover a smooth, clear and sharp road boundary. The augmentated DeepGlobe dataset is used to train our deep model and the asynchronous training method is applied to accelerate the training process. Five salellite images covering Xiaomu village are taken as input to evaluate our model. The proposed E-Road model has fewer number of parameters and shorter training time. The experiments show E-Road outperforms other state-of-the-art deep models with 5.84% to 59.09% improvement, and can give the accurate predictions for the images with complex environment. [ABSTRACT FROM AUTHOR]