Race estimation with deep networks

Predictive analysis on cellular traffic is important for the control and monitoring of wireless networks. Cellular traffic prediction is a challenging problem due to the non- stationarity and dynamic spatial-temporal correlation of the traffic. In this paper, we address the problem of accurate traffic prediction in a base station by proposing a deep neural network called RAConv. Its structure includes residual network, attention mechanism, and deep convolutional network. In the proposed architecture, a deep 3D residual convolutional network (ResConv3D) with three residual blocks are employed to learn the local spatial-temporal features. An attention-aided convolutional long short-term memory network (AConvLSTM) is then used to capture the long-term spatial-temporal dependencies. The use of the attention modules enable the network to focus on the most important spatial-temporal information. We evaluate the performance of the proposed RAConv network using a dataset provided by a Canadian wireless service provider. We consider the traffic prediction on two time scales (i.e., hourly and daily), which exhibit different spatial-temporal dependency patterns. Experimental results show that the proposed RAConv network can achieve accurate prediction under both time scales. Results also show that our proposed network provides a lower root-mean-square error (RMSE) than the conventional ConvLSTM baseline scheme.

In this paper, we propose a new image super-resolution (SR) approach based on a convolutional neural network (CNN), which jointly learns the feature extraction, upsampling, and high-resolution (HR) reconstruction modules, yielding a completely end-to-end trainable deep CNN. However, directly training such a deep network in an end-to-end fashion is challenging, which takes a longer time to converge and may lead to sub-optimal results. To address this issue, we propose to jointly train an ensemble of deep and shallow networks. The shallow network with weaker learning capability restores the main structure of the image content, while the deep network with stronger representation power captures the high-frequency details. Since the shallow network is much easier to optimize, it significantly lowers the difficulty of deep network optimization during joint training. To further ensure more accurate restoration of HR images, the high-frequency details are reconstructed in a multi-scale manner to simultaneously incorporate both short- and long-range contextual information. The proposed method is extensively evaluated on widely adopted data sets and compares favorably against state-of-the-art methods. In-depth ablation studies are conducted to verify the contributions of different network designs to image SR, providing additional insights for future research.

Electrochemical machining is a promising non-traditional manufacturing process to make high-quality parts. The benefits of minimal thermally and mechanically induced stresses, free of burr, and a low surface roughness are appealing for industry and research institutes. However, the combined chemical reaction, electric field, fluid mechanics, and material properties involve a significant number of independent parameters which are difficult to analyze in order to draw comprehensive conclusions. To our current knowledge, process responses such as the material removal rate, optimal feed rate, and cutting profile cannot be represented accurately by analytical solutions. In recent years, deep learning has had tremendous success in analyzing sophisticated systems. The improved computation efficiency and reduced size of the training dataset required for deep learning have enabled various prediction models in the manufacturing industry. In this paper, a new approach is developed using the deep convolutional network with the Bayesian optimization algorithm to predict the diameters of the drilled hole from an electrochemical machining process. The Keras application programming interface (API) was used to build the deep convolutional network; the feed rate, pulse-on time, and voltage were used as input parameters to provide a fair comparison with a neural network from previous research. Random dropout layers were added to prevent overfitting of the network. Instead of tuning the network parameter by trial and error, the Bayesian parameter optimization algorithm was implemented to find the optimal set of parameters of the deep convolutional network that yields the minimum mean square error. The proposed algorithm was compared with a previously developed neural network with partially embedded physical knowledge. Improved training speed and accuracy were observed in comparison with the traditional neural network. The prediction model using the proposed deep learning algorithm demonstrated better prediction accuracy and provided a more systematic way to select the hyperparameter for the deep convolutional network.

Large convolutional networks have achieved impressive classification performances recently. To achieve better performance, convolutional network tends to develop into deeper. However, the increase of network depth causes the linear growth of computational complexity, but cannot bring equivalent increase to the classification accuracy. To alleviate this inconsistence, we propose a cascading approach to accelerate the classification of very deep convolutional neural network. By exploiting the entropy metric to analyze the statistic differences of basic networks between the correctly and mistakenly classified images, we can assign the easily distinguished images to the shallow networks for reducing the computational complexity, and leave the difficultly classified images to the deep networks for maintaining the overall performance. Besides, the proposed cascaded networks can take advantage of the complementarity between different networks, which may boost the classification accuracy compared to the deepest network. We perform the experiments using residual networks of different depths on cifar100 dataset, on the condition of obtaining the similar accuracy to the deepest network, the results show that our cascaded ResNet32-ResNet110 and cascaded ResNet32-ResNet164 can reduce the computation time by 48.6% and 44.3% compared to ResNet110 and ResNet164, respectively. And the cascaded ResNet32-ResNet110-ResNet164 can reduce the computation time by 85.4% compared to the very deep Resnet1001.

Computer-aided diagnosis of ocular disorders like glaucoma can be effectively performed with retinal fundus images. Since the advent of machine learning and later deep learning techniques in medical image analysis, research focusing on automated and early detection of glaucoma has gained prominence. In this paper, we show how a deep Convolutional Neural Network model can be used in visualising the features related to Glaucoma that are consistent with (a subset of) those used by ophthalmologists for diagnosis. However, since the doctors do not necessarily depend entirely on these features but back them up with other important measurements such as visual field testing (HVF), any deep neural network such as CNN may not necessarily be expected to yield 100% accuracy. Further, other important parameters such as Intraocular Pressure (IOP), which may be built into a deep learning model, may not necessarily correlate well with the presence of Glaucoma. In this work, a deep CNN model has been trained and tested on a large number of high-quality fundus images, both normal and glaucomatous. We compare the results with transfer learning models such as VGG16, ResNet50, and MobileNetV2. On an average, we obtained an accuracy of 93.75% in identifying glaucoma, focusing only on the features of the fundus image.

Residual magnetic error remains after standard levelling process. The weak non-geological effect, manifesting itself as streaky noise along flight lines, creates a challenge for airborne geophysical data processing and interpretation. Microleveling is the process to eliminate this residual noise and is now a standard areogeophysical data processing step. In this paper, we propose a two-step procedure for single aerogeophysical data microleveling: a deep convolutional network is first adopted as approximator to map the original data into a low-level part with nature geological structures and a corrugated residual which still contains high-level detail geological structures; second, the mixture of Gaussian robust principal component analysis (MoG-RPCA) is then used to separate the weak energy fine structures from the residual. The final microleveling result is the addition of low-level structures from deep convolutional network and fine structures from MoG-RPCA. The deep convolutional network does not need dataset for training and the handcrafted network serves as prior (deep image prior) to capture the low-level nature geological structures in the areogeophysical data. Experiments on synthetic data and field data demonstrate that the combination of deep convolutional network and MoG-RPCA is an effective framework for single areogeophysical data microleveling.

Automatic detection of Aedes aegypti breeding grounds based on deep networks with spatio-temporal consistency

Cardiovascular MRI image analysis by using the bio inspired (sand piper optimized) fully deep convolutional network (Bio-FDCN) architecture for an automated detection of cardiac disorders

Generative models have been applied in many fields and can be evaluated with many methods. In the evaluation of generative models, the proper evaluation metric varies with the application field. Therefore, the evaluation of generative adversarial networks is inherently challenging. In this study, conditional deep convolutional generative adversarial networks were applied in mechanical fault diagnosis and then evaluated. We proposed three evaluation metrics of conditional deep convolutional generative adversarial networks: Jensen-Shannon divergence, kernel maximum mean discrepancy, and the 1-nearest neighbor classifier which were used to distinguish generated samples from real samples, test mode collapsing and detect overfitting based on the dataset of Electronic Engineering Laboratory of Case Western Reserve University and the planetary gearbox dataset measured in the laboratory. The Jensen-Shannon divergence could not well distinguish generated samples from real samples. However, the two metrics (maximum mean discrepancy and 1-nearest neighbor classifier) well-distinguished generated samples from real samples, thus verifying the applicability of conditional deep convolutional generative adversarial networks in the field of mechanical diagnosis.

Inferior temporal (IT) cortex in human and nonhuman primates serves visual object recognition. Computational object-vision models, although continually improving, do not yet reach human performance. It is unclear to what extent the internal representations of computational models can explain the IT representation. Here we investigate a wide range of computational model representations (37 in total), testing their categorization performance and their ability to account for the IT representational geometry. The models include well-known neuroscientific object-recognition models (e.g. HMAX, VisNet) along with several models from computer vision (e.g. SIFT, GIST, self-similarity features, and a deep convolutional neural network). We compared the representational dissimilarity matrices (RDMs) of the model representations with the RDMs obtained from human IT (measured with fMRI) and monkey IT (measured with cell recording) for the same set of stimuli (not used in training the models). Better performing models were more similar to IT in that they showed greater clustering of representational patterns by category. In addition, better performing models also more strongly resembled IT in terms of their within-category representational dissimilarities. Representational geometries were significantly correlated between IT and many of the models. However, the categorical clustering observed in IT was largely unexplained by the unsupervised models. The deep convolutional network, which was trained by supervision with over a million category-labeled images, reached the highest categorization performance and also best explained IT, although it did not fully explain the IT data. Combining the features of this model with appropriate weights and adding linear combinations that maximize the margin between animate and inanimate objects and between faces and other objects yielded a representation that fully explained our IT data. Overall, our results suggest that explaining IT requires computational features trained through supervised learning to emphasize the behaviorally important categorical divisions prominently reflected in IT.

Detecting drifting icebergs is an important task to avoid threats to navigation and offshore activities. Government and companies use aerial reconnaissance and shore-based observation platforms to detect these icebergs. However, in some areas with harsh weather conditions only satellite imagery can be used to monitor this risk. In this work, we propose the use of deep Convolutional Neural Networks to detect and classify these small remotely sensed targets as ships or icebergs. In this work, we use satellite radar imagery composed of two bands. The image patches have a resolution below 6K pixels and are noisy. To solve this challenge, we developed a deep convolutional network architecture and optimized its hyperparameters for this classification. The obtained results show that the proposed deep convolutional network achieves a very interesting accuracy for the classification of icebergs vs. ships with radar satellite images.

To reduce patient's dose, few-view CT reconstruction promises to be a good attempt. The key to better reconstruction is the sparse view artifacts. In recent years, DL(deep learing) has attracted a lot of attention because its outstanding performance in image processing. We propose a deep learning method for few-view CT reconstuction. Our method directly learns an end-to-end mapping between the full-view/few-view reconstruction. The mapping is represented as a deep convolutional neural network (CNN) that takes the few-view reconstruction image as the input and outputs the full-view one. We further show that traditional Dictionary Learning based reconstruction methods can also be viewed as a deep convolutional network. But unlike traditional methods that handle each component separately, our method jointly optimizes all layers. Our deep CNN has a lightweight structure, yet demonstrates state-of-the-art reconstruction quality, and achieves fast speed for practical on-line usage. We explore different network structures and parameter settings to achieve trade-offs between performance and speed.

Local binary features for texture classification: Taxonomy and experimental study

According to the National Highway Traffic Safety Administration, one in ten fatal crashes and two in ten injury crashes were reported as distracted driver accidents in the United State during 2014. In an attempt to mitigate these alarming statistics, this paper explores using a dashboard camera along with computer vision and machine learning to automatically detect distracted drivers. We consider a dataset that incorporates drivers engaging in seven different distracting behaviors using left and/or right hands. Traditional handcrafted features paired with a Support Vector Machine classifier are contrasted with deep Convolutional Neural Networks. The traditional features include a blend of Histogram of Oriented Gradients and Scale-Invariant Feature Transform descriptors used to create Bags of Words. The deep convolutional methods use transfer learning on AlexNet, VGG-16, and ResNet-152. The results yield 85% accuracy with ResNet and 82.5% accuracy with VGG-16, which outperformed AlexNet by almost 10%. Replacing the fully connected layers by a Support Vector Machine classifier did not improve the classification accuracy. The traditional features yielded much lower accuracy than the deep convolutional networks.

Vehicle logo detection based on deep convolutional networks