Search

Photometric Stereo (PS) under outdoor illumination remains a challenging, ill-posed problem due to insufficient variability in illumination. Months-long capture sessions are typically used in this setup, with little success on shorter, single-day time intervals. In this paper, we investigate the solution of outdoor PS over a single day, under different weather conditions. First, we investigate the relationship between weather and surface reconstructability in order to understand when natural lighting allows existing PS algorithms to work. Our analysis reveals that partially cloudy days improve the conditioning of the outdoor PS problem while sunny days do not allow the unambiguous recovery of surface normals from photometric cues alone. We demonstrate that calibrated PS algorithms can thus be employed to reconstruct Lambertian surfaces accurately under partially cloudy days. Second, we solve the ambiguity arising in clear days by combining photometric cues with prior knowledge on material properties, local surface geometry and the natural variations in outdoor lighting through a CNN-based, weakly-calibrated PS technique. Given a sequence of outdoor images captured during a single sunny day, our method robustly estimates the scene surface normals with unprecedented quality for the considered scenario. Our approach does not require precise geolocation and significantly outperforms several state-of-the-art methods on images with real lighting, showing that our CNN can combine efficiently learned priors and photometric cues available during a single sunny day. [ABSTRACT FROM AUTHOR]

The Internet of vehicles (IoV) is a large information interaction network that collects information on vehicles, roads and pedestrians. One of the important uses of vehicle networks is to meet the entertainment needs of driving users through communication between vehicles and roadside units (RSUs). Due to the limited storage space of RSUs, determining the content cached in each RSU is a key challenge. With the development of 5G and video editing technology, short video systems have become increasingly popular. Current widely used cache update methods, such as partial file precaching and content popularity- and user interest-based determination, are inefficient for such systems. To solve this problem, this paper proposes a QoE-driven edge caching method for the IoV based on deep reinforcement learning. First, a class-based user interest model is established. Compared with the traditional file popularity- and user interest distribution-based cache update methods, the proposed method is more suitable for systems with a large number of small files. Second, a quality of experience (QoE)-driven RSU cache model is established based on the proposed class-based user interest model. Third, a deep reinforcement learning method is designed to address the QoE-driven RSU cache update issue effectively. The experimental results verify the effectiveness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

This paper proposes a cloud-assisted joint charging scheduling and energy management framework for unmanned aerial vehicle (UAV) networks. For charging the UAVs those are extremely power hungry, charging towers are considered for plug-and-play charging during run-time operations. The charging towers should be cost-effective, thus it is equipped with photovoltaic power generation and energy storage systems functionalities. Furthermore, the towers should be cooperative for more cost-effectiveness by intelligent energy sharing. Based on the needs and setting, this paper proposes 1) charging scheduling between UAVs and towers and 2) cooperative energy managements among towers. For charging scheduling, the UAVs and towers should be scheduled for maximizing charging energy amounts and the scheduled pairs should determine charging energy allocation amounts. Here, two decisions are correlated, i.e., it is a non-convex problem. We re-formulate the non-convex to convex for guaranteeing optimal solutions. Lastly, the cooperative energy sharing among towers is designed and implemented with multi-agent deep reinforcement learning and then intelligent energy sharing can be realized. We can observe that the two methods are related and it should be managed, coordinated, and harmonized by a centralized orchestration manager under the consideration of fairness, energy-efficiency, and cost-effectiveness. Our data-intensive performance evaluation verifies that our proposed framework achieves desired performance. [ABSTRACT FROM AUTHOR]

Plant species identification represents an extraordinary challenge for machine learning due to visual interspecies similarities and large intraspecies variations. Furthermore, research literature reports that plant species identification usually lacks sufficiently large datasets for training classification models. In this paper, we address this problem with a model that simplifies the VGG-16 architecture, the N-VGG model. The idea behind N-VGG is to reduce experimentally observed overfitting on VGG-16 by using as few trainable parameters as possible. To do this, we substitute the flattening layer on the VGG architecture with a global average pooling layer. This reduces the size of the feature vector. In addition, we eliminate one of the two fully-connected layers and use a new hyper-parameter, N, to indicate the number of nodes on the remaining layer. To show the robustness of the N-VGG model, we conducted extensive experimentation. We trained N-VGG on five datasets for plant species identification. Four of these datasets are publicly available and have been widely used as benchmarks for plant identification models. For all datasets, we compare the accuracy of N-VGG to that of the VGG-16, Inception-v4, and EfficienNet-B3 models. The experimental results show that the N-VGG model achieved the best classification performance for all but one datasets, whereas all the models showed a remarkable performance for the remaining dataset. This evidence supports our initial idea that, for plant species classification, some accuracy might be lost due to overfitting and that having fewer trainable parameters helps in producing a more robust model. [ABSTRACT FROM AUTHOR]

This paper proposes a robust method to screen patients with sleep apnea syndrome (SAS) using a single-lead electrocardiogram (ECG). This method consists of minute-by-minute abnormal breathing detection and apnea-hypopnea index (AHI) estimation. Heartbeat interval and ECG-derived respiration (EDR) are calculated using the single-lead ECG and used to train the models, including ResNet18, ResNet34, and ResNet50. The proposed method, using data from 1232 subjects, was developed with two open datasets and experimental data and evaluated using two additional open datasets and data acquired from an abdomen-attached wearable device (in total, data from 189 subjects). ResNet18 showed the best results, having an average Cohen's kappa coefficient of 0.57, in the abnormal breathing detection. Moreover, SAS patient classification, with 15 as the AHI threshold, yielded an average Cohen's kappa coefficient of 0.71. The results of patient classification were biased toward data from the wearable patch-type device, which may be influenced by different ECG waveforms. The proposed method is tuned with a sample of the data from the device, and the performance result of Cohen's kappa increased from 0.54 to 0.91 for SAS patient classification. Our method, proposed in this paper, achieved equivalent performance results with data recorded using an abdomen-attached wearable device and two open datasets used in previous studies, although the method had not used those data during model training. The proposed method could reduce the development costs of commercial software, as it was developed using open datasets, has robust performance throughout all datasets. [ABSTRACT FROM AUTHOR]

As a novel deep learning method, deep forest has achieved excellent classification performance on many small-scale datasets, thus providing a new opportunity to accurately classify brain networks (BNs) on limited fMRI data. Though there are a few explorations about classifying BNs using deep forest, they only adopt sliding windows to extract adjacent features of BNs and fail to use prior knowledge to strengthen the features more relevant to brain diseases. In this paper, we propose a deep forest framework with multi-channel message passing and neighborhood aggregation mechanisms (DF-MCMPNA) to extract and aggregate long-range multi-channel topological features. Firstly, we use the three intrinsic connectivity networks (ICNs) and the whole-brain to form four feature extraction channels. Secondly, we present a multi-channel message passing mechanism and a channel-shared neighborhood aggregation mechanism to recursively extract long-range multi-channel topological features, where the first mechanism can learn local topological features in each channel and the second mechanism can fuse multi-channel topological features. Finally, the extracted features are fed into the casForst to perform further feature learning and classification. Experimental results on ABIDE I, ABIDE II, and ADHD-200 datasets show that the DF-MCMPNA outperforms several state-of-the-art methods on classification performance and accurately identifies abnormal brain regions. [ABSTRACT FROM AUTHOR]

Automatic seizure detection algorithms are necessary for patients with refractory epilepsy. Many excellent algorithms have achieved good results in seizure detection. Still, most of them are based on discontinuous intracranial electroencephalogram (iEEG) and ignore the impact of different channels on detection. This study aimed to evaluate the proposed algorithm using continuous, long-term iEEG to show its applicability in clinical routine. In this study, we introduced the ability of the transformer network to calculate the attention between the channels of input signals into seizure detection. We proposed an end-to-end model that included convolution and transformer layers. The model did not need feature engineering or format transformation of the original multi-channel time series. Through evaluation on two datasets, we demonstrated experimentally that the transformer layer could improve the performance of the seizure detection algorithm. For the SWEC-ETHZ iEEG dataset, we achieved 97.5% event-based sensitivity, 0.06/h FDR, and 13.7 s latency. For the TJU-HH iEEG dataset, we achieved 98.1% event-based sensitivity, 0.22/h FDR, and 9.9 s latency. In addition, statistics showed that the model allocated more attention to the channels close to the seizure onset zone within 20 s after the seizure onset, which improved the explainability of the model. This paper provides a new method to improve the performance and explainability of automatic seizure detection. [ABSTRACT FROM AUTHOR]

The goal of image steganography is to hide a full-sized image, termed secret, into another, termed cover. Prior image steganography algorithms can conceal only one secret within one cover. In this paper, we propose an adaptive local image steganography (AdaSteg) system that allows for scale- and location-adaptive image steganography. By adaptively hiding the secret on a local scale, the proposed system makes the steganography more secured, and further enables multi-secret steganography within one single cover. Specifically, this is achieved via two stages, namely the adaptive patch selection stage and secret encryption stage. Given a pair of secret and cover, first, the optimal local patch for concealment is determined adaptively by exploiting deep reinforcement learning with the proposed steganography quality function and policy network. The secret image is then converted into a patch of encrypted noises, resembling the process of generating adversarial examples, which are further encoded to a local region of the cover to realize a more secured steganography. Furthermore, we propose a novel criterion for the assessment of local steganography, and also collect a challenging dataset that is specialized for the task of image steganography, thus contributing to a standardized benchmark for the area. Experimental results demonstrate that the proposed model yields results superior to the state of the art in both security and capacity. [ABSTRACT FROM AUTHOR]

As deep learning models are usually massive and complex, distributed learning is essential for increasing training efficiency. Moreover, in many real-world application scenarios like healthcare, distributed learning can also keep the data local and protect privacy. Recently, the asynchronous decentralized parallel stochastic gradient descent (ADPSGD) algorithm has been proposed and demonstrated to be an efficient and practical strategy where there is no central server, so that each computing node only communicates with its neighbors. Although no raw data will be transmitted across different local nodes, there is still a risk of information leak during the communication process for malicious participants to make attacks. In this paper, we present a differentially private version of asynchronous decentralized parallel SGD framework, or A(DP) $^2$ 2 SGD for short, which maintains communication efficiency of ADPSGD and prevents the inference from malicious participants. Specifically, Rényi differential privacy is used to provide tighter privacy analysis for our composite Gaussian mechanisms while the convergence rate is consistent with the non-private version. Theoretical analysis shows A(DP) $^2$ 2 SGD also converges at the optimal $\mathcal {O}(1/\sqrt{T})$ O (1 / T) rate as SGD. Empirically, A(DP) $^2$ 2 SGD achieves comparable model accuracy as the differentially private version of Synchronous SGD (SSGD) but runs much faster than SSGD in heterogeneous computing environments. [ABSTRACT FROM AUTHOR]

Knowledge distillation (KD) is a popular method to train efficient networks (“student”) with the help of high-capacity networks (“teacher”). Traditional methods use the teacher’s soft logits as extra supervision to train the student network. In this paper, we argue that it is more advantageous to make the student mimic the teacher’s features in the penultimate layer. Not only the student can directly learn more effective information from the teacher feature, feature mimicking can also be applied for teachers trained without a softmax layer. Experiments show that it can achieve higher accuracy than traditional KD. To further facilitate feature mimicking, we decompose a feature vector into the magnitude and the direction. We argue that the teacher should give more freedom to the student feature’s magnitude, and let the student pay more attention on mimicking the feature direction. To meet this requirement, we propose a loss term based on locality-sensitive hashing (LSH). With the help of this new loss, our method indeed mimics feature directions more accurately, relaxes constraints on feature magnitudes, and achieves state-of-the-art distillation accuracy. We provide theoretical analyses of how LSH facilitates feature direction mimicking, and further extend feature mimicking to multi-label recognition and object detection. [ABSTRACT FROM AUTHOR]

Modern methods for counting people in crowded scenes rely on deep networks to estimate people densities in individual images. As such, only very few take advantage of temporal consistency in video sequences, and those that do only impose weak smoothness constraints across consecutive frames. In this paper, we advocate estimating people flows across image locations between consecutive images and inferring the people densities from these flows instead of directly regressing them. This enables us to impose much stronger constraints encoding the conservation of the number of people. As a result, it significantly boosts performance without requiring a more complex architecture. Furthermore, it allows us to exploit the correlation between people flow and optical flow to further improve the results. We also show that leveraging people conservation constraints in both a spatial and temporal manner makes it possible to train a deep crowd counting model in an active learning setting with much fewer annotations. This significantly reduces the annotation cost while still leading to similar performance to the full supervision case. [ABSTRACT FROM AUTHOR]

This tutorial paper surveys provably optimal alternatives to end-to-end backpropagation (E2EBP) — the de facto standard for training deep architectures. Modular training refers to strictly local training without both the forward and the backward pass, i.e., dividing a deep architecture into several nonoverlapping modules and training them separately without any end-to-end operation. Between the fully global E2EBP and the strictly local modular training, there are weakly modular hybrids performing training without the backward pass only. These alternatives can match or surpass the performance of E2EBP on challenging datasets such as ImageNet, and are gaining increasing attention primarily because they offer practical advantages over E2EBP, which will be enumerated herein. In particular, they allow for greater modularity and transparency in deep learning workflows, aligning deep learning with the mainstream computer science engineering that heavily exploits modularization for scalability. Modular training has also revealed novel insights about learning and has further implications on other important research domains. Specifically, it induces natural and effective solutions to some important practical problems such as data efficiency and transferability estimation. [ABSTRACT FROM AUTHOR]

The growing availability of maritime IoT traffic data and continuous expansion of the maritime traffic volume, serving as the driving fuel, propel the latest Artificial Intelligence (AI) studies in the maritime domain. Among the most recent advancements, vessel trajectory prediction is one of the most essential topics for assuring maritime transportation safety, intelligence, and efficiency. This paper presents an up-to-date review of existing approaches, including state-of-the-art deep learning, for vessel trajectory prediction. We provide a detailed explanation of data sources and methodologies used in the vessel trajectory prediction studies, highlight a discussion regarding the auxiliary techniques, complexity analysis, benchmarking, performance evaluation, and performance improvement for vessel trajectory prediction research, and finally summarize the current challenges and future research directions in this field. [ABSTRACT FROM AUTHOR]

This paper proposes a multi-source data fusion algorithm for rail surface defect detection in both camera-based rail inspection images and ultrasound B-scan images. First, we design a rail surface segmentation algorithm based on image bilateral filtering, Sobel edge detection, and rail surface edge detection to extract the rail surface area. Second, we build a camera and ultrasound data fusion (CUFuse) model for rail surface defect detection, including two main networks: multi-source data feature extraction and multi-scale feature fusion networks. The multi-source data feature extraction network consists of two BoTNet 50 networks as feature extraction networks to extract five stages of features in camera-based images and ultrasound B-scan images. The multi-scale feature fusion network consists of five feature fusion modules to fuse the feature information output by the multi-source data feature extraction network. Finally, we use the CUFuse model to detect the rail surface defect dataset, and output five rail surface state types, including Light, Moderate, Severe, Normal, and Joint. The results show that the accuracy of the CUFuse model is 96.97%, which can accomplish the task of rail surface defect detection on railway sites. [ABSTRACT FROM AUTHOR]

As power systems are undergoing a significant transformation with more uncertainties, less inertia and closer to operation limits, there is increasing risk of large outages. Thus, there is an imperative need to enhance grid emergency control to maintain system reliability and security. Towards this end, great progress has been made in developing deep reinforcement learning (DRL) based grid control solutions in recent years. However, existing DRL-based solutions have two main limitations: 1) they cannot handle well with a wide range of grid operation conditions, system parameters, and contingencies; 2) they generally lack the ability to fast adapt to new grid operation conditions, system parameters, and contingencies, limiting their applicability for real-world applications. In this paper, we mitigate these limitations by developing a novel deep meta-reinforcement learning (DMRL) algorithm. The DMRL combines the meta strategy optimization together with DRL, and trains policies modulated by a latent space that can quickly adapt to new scenarios. We test the developed DMRL algorithm on the IEEE 300-bus system. We demonstrate fast adaptation of the meta-trained DRL polices with latent variables to new operating conditions and scenarios using the proposed method, which achieves superior performance compared to the state-of-the-art DRL and model predictive control (MPC) methods. [ABSTRACT FROM AUTHOR]

Due to the diversity of power consumption patterns, the false positive rate (FPR) of data-driven electricity theft detection (ETD) methods is too high to meet practical needs, which severely restricts the engineering application of data-based methods. To reduce FPR of ETD methods based on advanced metering infrastructure (AMI), a deep neural network with low FPR (LFPR-DNN) is proposed in this paper. First, a deep model is constructed based on one-dimensional convolution and residual network, which can automatically extract features from consumption data. Then, a two-stage training scheme is used to train the network. In the first stage, the conventional gradient descent algorithm is used to update the network weights. To minimize the impact of data imbalance on detection performance, focal loss is used. Besides, grid search is used to optimize the hyper-parameters of the model. In the second stage, with FPR as the optimization objective, the particle swarm optimization (PSO) algorithm is used to train the network. Finally, the proposed LFPR-DNN is verified by using the open Irish data set. Compared to other state-of-the-art classifiers, LFPR-DNN has the lowest FPR with 0.29% and the highest AUC with 99.42%. The FPR is reduced by an order of magnitude, which verifies the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

The ongoing digitalization enables stable control processes and smooth operations of Industrial Control Systems (ICSs). A direct consequence of the highly interconnected architecture of ICSs is the introduced cyber vulnerability and increasing cyber security threats to ICSs. Numerous researches pay attention to the security problem of ICSs. However, most current studies face two challenges. First, the interaction problem between the cyber layer and the physical layer of ICSs may result in incorrect attack response strategies. Second, ICSs are real-time systems, but existing defense decision algorithms based on game theory or reinforcement learning techniques have high computational complexity, which prevents them from making decisions quickly. In this paper, we design a new multi-attribute based method for quantifying rewards and propose a multi-attribute based Q-learning algorithm to resolve the interaction problem. In addition, to overcome the limitation of slow convergence, we develop an effective parallel Q-learning (PQL) algorithm to quickly find the optimal strategy. The experimental results show the effectiveness of the PQL algorithm. Compared with the Q-learning algorithm (QL) and the deep Q-network (DQN) algorithm, our proposed solution can reduce the average completion time by 12.5 to 37 percent. [ABSTRACT FROM AUTHOR]

The conventional design of wireless communication systems typically relies on established mathematical models that capture the characteristics of different communication modules. Unfortunately, such design cannot be easily and directly applied to future wireless networks, which will be characterized by large-scale ultra-dense networks whose design complexity scales exponentially with the network size. Furthermore, such networks will vary dynamically in a significant way, which makes it intractable to develop comprehensive analytical models. Recently, deep learning-based approaches have emerged as potential alternatives for designing complex and dynamic wireless systems. However, existing learning-based methods have limited capabilities to scale with the problem size and to generalize with varying network settings. In this paper, we propose a scalable and generalizable neural calibration framework for future wireless system design, where a neural network is adopted to calibrate the input of conventional model-based algorithms. Specifically, the backbone of a traditional time-efficient algorithm is integrated with deep neural networks to achieve a high computational efficiency, while enjoying enhanced performance. The permutation equivariance property, carried out by the topological structure of wireless systems, is furthermore utilized to develop a generalizable neural network architecture. The proposed neural calibration framework is applied to solve challenging resource management problems in massive multiple-input multiple-output (MIMO) systems. Simulation results will show that the proposed neural calibration approach enjoys significantly improved scalability and generalization compared with the existing learning-based methods. [ABSTRACT FROM AUTHOR]

In conventional multi-user multiple-input multiple-output (MU-MIMO) systems with frequency division duplexing (FDD), channel acquisition and precoder optimization processes have been designed separately although they are highly coupled. This paper studies an end-to-end design of downlink MU-MIMO systems which include pilot sequences, limited feedback, and precoding. To address this problem, we propose a novel deep learning (DL) framework which jointly optimizes the feedback information generation at users and the precoder design at a base station (BS). Each procedure in the MU-MIMO systems is replaced by intelligently designed multiple deep neural networks (DNN) units. At the BS, a neural network generates pilot sequences and helps the users obtain accurate channel state information. At each user, the channel feedback operation is carried out in a distributed manner by an individual user DNN. Then, another BS DNN collects feedback information from the users and determines the MIMO precoding matrices. A joint training algorithm is proposed to optimize all DNN units in an end-to-end manner. In addition, a training strategy which can avoid retraining for different network sizes for a scalable design is proposed. Numerical results demonstrate the effectiveness of the proposed DL framework compared to classical optimization techniques and other conventional DNN schemes. [ABSTRACT FROM AUTHOR]

Accurate and rapid identification of distribution system fault causes is essential for power system reliability enhancement. Manual fault cause identification requires extensive human resources that leads to extended power outage time. To this end, this paper proposes a dual-channel convolutional neural network (DC-CNN)-based method for distribution system fault cause identification using realistic data from waveform measurement units. The fault mechanism and waveform characteristics of different fault causes are investigated by analyzing large amounts of field waveform data. The short-time Fourier transform (STFT) is advocated to extract the frequency-domain features, which are used together with the time-domain data for constructing the time-frequency feature images. This leads to improved feature extraction via the proposed DC-CNN-enabled multimodal information fusion. A fully connected layer with a maxout unit (FCM layer) is constructed to enhance the mapping ability of high-level features and improve classification accuracy. Extensive test results using field data demonstrate the superiority of the proposed method over other methods. [ABSTRACT FROM AUTHOR]

Resilience becomes vital for power grids facing the increasingly frequent extreme weather events. Microgrid formation is a promising way to achieve resilient distribution networks (RDN) when the utility power is unavailable. This paper proposes a RDN-oriented microgrid formation (RoMF) method based on the deep reinforcement learning (DRL) technique, which integrates the OpenDSS as an interaction object and searches for optimal control policies in a model-free fashion. Specifically, we formulate the microgrid formation problem as a Markov decision process, taking into account complex factors such as unbalanced three-phase power flow and microgrid operation constraints. Next, a simulator-based RoMF environment is constructed and integrated into the OpenAI Gym, providing a standard agent-environment interface for applying DRL algorithms. Then, the deep Q-network is used to search for optimal microgrid formation strategies, and an offline-training and online-application framework of the DRL-based RoMF is given. Finally, extensive numerical results validate the effectiveness of our proposed method. [ABSTRACT FROM AUTHOR]

The separation of the data capture and analysis in modern vision systems has led to a massive amount of data transfer between the end devices and cloud computers, resulting in long latency, slow response, and high power consumption. Efficient hardware architectures are under focused development to enable Artificial Intelligence (AI) at the resource-limited sensing devices. One of the most promising solutions is to enable Processing-in-Pixel (PIP) scheme. However, the conventional schemes suffer from the low fill-factor issue. This paper proposes a PIP based Complementary Metal-Oxide-Semiconductor (CMOS) sensor architecture, which allows convolution operation before the column readout circuit to significantly reduce the overall power consumption while improving the resource utilization of the succeeding deep learning accelerator. The simulation results show that the proposed architecture could support the computing efficiency up to 3.37 TOPS/W at the 8-bit weight configuration, which is four times as high as the conventional schemes after normalization. The transistors required for each pixel are only 3.5T, significantly improving the fill-factor. [ABSTRACT FROM AUTHOR]

Convolutional neural networks (CNN) have demonstrated their ability to segment 2D cardiac ultrasound images. However, despite recent successes according to which the intra-observer variability on end-diastole and end-systole images has been reached, CNNs still struggle to leverage temporal information to provide accurate and temporally consistent segmentation maps across the whole cycle. Such consistency is required to accurately describe the cardiac function, a necessary step in diagnosing many cardiovascular diseases. In this paper, we propose a framework to learn the 2D+time apical long-axis cardiac shape such that the segmented sequences can benefit from temporal and anatomical consistency constraints. Our method is a post-processing that takes as input segmented echocardiographic sequences produced by any state-of-the-art method and processes it in two steps to (i) identify spatio-temporal inconsistencies according to the overall dynamics of the cardiac sequence and (ii) correct the inconsistencies. The identification and correction of cardiac inconsistencies relies on a constrained autoencoder trained to learn a physiologically interpretable embedding of cardiac shapes, where we can both detect and fix anomalies. We tested our framework on 98 full-cycle sequences from the CAMUS dataset, which are available alongside this paper. Our temporal regularization method not only improves the accuracy of the segmentation across the whole sequences, but also enforces temporal and anatomical consistency. [ABSTRACT FROM AUTHOR]

With the popularity of the wireless body sensor network, real-time and continuous collection of single-lead electrocardiogram (ECG) data becomes possible in a convenient way. Data mining from the collected single-lead ECG waves has therefore aroused extensive attention worldwide, where early detection of atrial fibrillation (AF) is a hot research topic. In this paper, a two-channel convolutional neural network combined with a data augmentation method is proposed to detect AF from single-lead short ECG recordings. It consists of three modules, the first module denoises the raw ECG signals and produces 9-s ECG signals and heart rate (HR) values. Then, the ECG signals and HR rate values are fed into the convolutional layers for feature extraction, followed by three fully connected layers to perform the classification. The data augmentation method is used to generate synthetic signals to enlarge the training set and increase the diversity of the single-lead ECG signals. Validation experiments and the comparison with state-of-the-art studies demonstrate the effectiveness and advantages of the proposed method. [ABSTRACT FROM AUTHOR]

Hospitals can predetermine the admission rate and facilitate resource allocation based on valid emergency requests and bed capacity estimation. The excess unoccupied beds can be determined with the help of forecasting the number of discharged patients. Extracting predictive features and mining the temporal patterns from historical observations are crucial for accurate and reliable forecasts. Machine learning algorithms have demonstrated the ability to learn temporal knowledge and make predictions for unseen inputs. This paper utilizes several machine learning algorithms to forecast the inpatient discharges of Singapore hospitals and compare them with statistical methods. A novel ensemble deep learning algorithm based on random vector functional links is established to predict inpatient discharges. The ensemble deep learning framework is optimized in a greedy layer-wise fashion. Several forecasting metrics and statistical tests are utilized to demonstrate the proposed method’s superiority. The proposed algorithm statistically outperforms the benchmark with a ranking of 1.875. Finally, practical implications and future directions are discussed. [ABSTRACT FROM AUTHOR]

One of the most prominent attributes of Neural Networks (NNs) constitutes their capability of learning to extract robust and descriptive features from high dimensional data, like images. Hence, such an ability renders their exploitation as feature extractors particularly frequent in an abundance of modern reasoning systems. Their application scope mainly includes complex cascade tasks, like multi-modal recognition and deep Reinforcement Learning (RL). However, NNs induce implicit biases that are difficult to avoid or to deal with and are not met in traditional image descriptors. Moreover, the lack of knowledge for describing the intra-layer properties -and thus their general behavior- restricts the further applicability of the extracted features. With the paper at hand, a novel way of visualizing and understanding the vector space before the NNs’ output layer is presented, aiming to enlighten the deep feature vectors’ properties under classification tasks. Main attention is paid to the nature of overfitting in the feature space and its adverse effect on further exploitation. We present the findings that can be derived from our model’s formulation and we evaluate them on realistic recognition scenarios, proving its prominence by improving the obtained results. [ABSTRACT FROM AUTHOR]

In this paper, we consider how to incorporate psychophysical measurements of human visual perception into the loss function of a deep neural network being trained for a recognition task, under the assumption that such information can reduce errors. As a case study to assess the viability of this approach, we look at the problem of handwritten document transcription. While good progress has been made towards automatically transcribing modern handwriting, significant challenges remain in transcribing historical documents. Here we describe a general enhancement strategy, underpinned by the new loss formulation, which can be applied to the training regime of any deep learning-based document transcription system. Through experimentation, reliable performance improvement is demonstrated for the standard IAM and RIMES datasets for three different network architectures. Further, we go on to show feasibility for our approach on a new dataset of digitized Latin manuscripts, originally produced by scribes in the Cloister of St. Gall in the the 9th century. [ABSTRACT FROM AUTHOR]

Autonomous Vehicles (AVs) are a significant part of Vehicular Adhoc NETwork (VANET) as they increase transportation accessibility. However, the presence of unpredictably sized potholes on road surfaces hampers the comfort and safety of autonomous navigation. Existing pothole avoidance mechanisms cannot dynamically adapt in unpredictable environments and do not comfort the traveler well in VANET. This paper proposes a novel Smart Pothole-Avoidance Strategy (SPAS) for safe navigation in a pothole-intensive environment. Potholes are avoided using the Deep Deterministic Policy Gradient (DDPG) algorithm as it performs best in continuous action space tasks and has a faster convergence speed. A Hybrid Recognition Model using the Speech and Gesture mechanism (HRM-SG) is proposed in this paper to collect the traveler’s real-time audio and visual feedback for the DDPG reward function. The received feedback aids in fine-tuning the model to avoid the pothole efficiently than the previous pothole. Traveler’s feedback is coupled with the vehicle’s sensor data and used to decide the time, speed, and angle at which lane change and speed change are executed. Finally, the SPAS continuously optimizes lane change parameters in VANET to achieve maximal traveler comfort during the operation. The result analysis indicates that SPAS achieves a 10-15% improvement in the accuracy of pothole avoidance, 10-12% higher comfort, and 8-10% faster convergence than the existing state-of-the-art techniques. [ABSTRACT FROM AUTHOR]

Trajectory planning is essential for self-driving vehicles and has stringent requirements for accuracy and efficiency. The existing trajectory planning methods have limitations in the feasibility of planned trajectories and computational efficiency. This paper proposes a life-long learning framework to achieve effective and high-accuracy direct trajectory planning (DTP) tasks. Based on generative adversarial networks (GANs), this study develops a lightweight GDTP model to map the initial/final states and the control action sequence. Additionally, by embedding the GDTP into the rapidly-exploring random tree (RRT), a GDTP-RRT algorithm is further designed for long-distance and multi-stage planning tasks. Taking the tractor-trailer as an application case, we test the proposed method in multiple scenarios with varying characteristics. The experimental results show that the method can plan highly feasible trajectories in a short time, compared with the most applied algorithm – the cubic curve RRT* (CCRRT*). It is found that the tracking errors of our method are 29.1% and 44.1% lower than the CCRRT* in terms of position and heading angle. This paper provides an effective and stable vehicle trajectory planning method for complex self-driving tasks. [ABSTRACT FROM AUTHOR]

Recent advances in video processing utilizing deep learning primitives achieved breakthroughs in fundamental problems in video analysis such as frame classification and object detection enabling an array of new applications. In this paper we study the problem of interactive declarative query processing on video streams. In particular we introduce a set of approximate filters to speed up queries that involve objects of specific type (e.g., cars, trucks, etc.) on video frames with associated spatial relationships among them (e.g., car left of truck). The resulting filters are able to assess quickly if the query predicates are true to proceed with further analysis of the frame or otherwise not consider the frame further avoiding costly object detection operations. We propose two classes of filters $IC$ I C and $OD$ O D , that adapt principles from deep image classification and object detection. The filters utilize extensible deep neural architectures and are easy to deploy and utilize. In addition, we propose statistical query processing techniques to process aggregate queries involving objects with spatial constraints on video streams and demonstrate experimentally the resulting increased accuracy on the resulting aggregate estimation. Finally, we introduce a framework based on extreme value theory to detect unexpected objects on video streams and experimentally demonstrate its utility. Combined these techniques constitute a robust set of video monitoring query processing techniques. We demonstrate that the application of the techniques proposed in conjunction with declarative queries on video streams can dramatically increase the frame processing rate and speed up query processing by at least two orders of magnitude. We present the results of a thorough experimental study utilizing benchmark video data sets at scale demonstrating the performance benefits and the practical relevance of our proposals. [ABSTRACT FROM AUTHOR]

This paper investigates the stochastic optimization problem focusing on developing scalable parallel algorithms for deep learning tasks. Our solution involves a reformation of the objective function for stochastic optimization in neural network models, along with a novel parallel computing strategy, coined the weighted aggregating stochastic gradient descent (WASGD). Following a theoretical analysis on the characteristics of the new objective function, WASGD introduces a decentralized weighted aggregating scheme based on the performance of local workers. Without any center variable, the new method automatically gauges the importance of local workers and accepts them by their contributions. Furthermore, we have developed an enhanced version of the method, WASGD+, by (1) implementing a designed sample order and (2) upgrading the weight evaluation function. To validate the new method, we benchmark our pipeline against several popular algorithms including the state-of-the-art deep neural network classifier training techniques (e.g., elastic averaging SGD). Comprehensive validation studies have been conducted on four classic datasets: CIFAR-100, CIFAR-10, Fashion-MNIST, and MNIST. Subsequent results have firmly validated the superiority of the WASGD scheme in accelerating the training of deep architecture. Better still, the enhanced version, WASGD+, is shown to be a significant improvement over its prototype. [ABSTRACT FROM AUTHOR]

Emotion Cause Extraction (ECE) aims to reveal the cause clauses behind a given emotion expressed in a text, which has become an emerging topic in broad research communities, such as affective computing and natural language processing. Despite the fact that current methods about the ECE task have made great progress in text semantic understanding from lexicon- and sentence-level, they always ignore the certain causal narratives of emotion text. Significantly, these causal narratives are presented in the form of semantic structure and highly helpful for structure-level emotion cause understanding. Nevertheless, causal narrative is just an abstract narratological concept and its involving semantics is quite different from the common sequential information. Thus, how to properly model and utilize such particular narrative information to boost the ECE performance still remains an unresolved challenge. To this end, in this paper, we propose a novel Causal Narrative Comprehension Model (CNCM) for emotion cause extraction, which learns and leverages causal narrative information smartly to address the above problem. Specifically, we develop a Narrative-aware Causal Association (NCA) unit, which mines the narrative cue about emotional results and uses the semantic correlation between causes and results to model causal narratives of documents. Besides, we design a Result-aware Emotion Attention (REA) unit to make full use of the known result of causal narrative for multiple understanding about emotional causal associations. Through the ingenious combination and collaborative utilization of these two units, we could better identify the emotion cause in the text with causal narrative comprehension. Extensive experiments on the public English and Chinese benchmark datasets of ECE task have validated the effectiveness of CNCM with significant margin by comparing with the state-of-the-art baselines, which demonstrates the potential of narrative information in long text understanding. [ABSTRACT FROM AUTHOR]

Automatic speech emotion recognition (SER) has gained popularity over the last decade and numerous Challenges have emerged. While the latest Challenges have shown that deep neural networks achieve the best results, existing input features are still a bottleneck and cause severe performance degradation in realistic “in-the-wild” scenarios. In this paper, we propose two innovations to tackle this issue. First, we propose to combine the bag-of-audio-words methodology with modulation spectrum features for environmental robustness. Second, we take advantage of the inherent quality-awareness properties of modulation spectrum and propose the use of a quality feature as an additional feature to be used by the speech emotion recognizer. Experiments are conducted with three multi-lingual speech datasets used in recent SER Challenges degraded by different noise sources and levels, and room reverberation. Experimental results show the proposed features i) consistently outperforming benchmark systems, ii) providing complementary information to classical features, hence improving performance with feature fusion, and iii) showing robustness against environment and language mismatch. Moreover, we show that when the proposed system is provided with quality information, further improvements are obtained. Overall, the proposed bag of modulation spectrum features are shown to be a promising candidate for “in-the-wild” SER. [ABSTRACT FROM AUTHOR]

In an aerial hybrid massive multiple-input multiple-output (MIMO) and orthogonal frequency division multiplexing (OFDM) system, how to design a spectral-efficient broadband multi-user hybrid beamforming with a limited pilot and feedback overhead is challenging. To this end, by modeling the key transmission modules as an end-to-end (E2E) neural network, this paper proposes a data-driven deep learning (DL)-based unified hybrid beamforming framework for both the time division duplex (TDD) and frequency division duplex (FDD) systems with implicit channel state information (CSI). For TDD systems, the proposed DL-based approach jointly models the uplink pilot combining and downlink hybrid beamforming modules as an E2E neural network. While for FDD systems, we jointly model the downlink pilot transmission, uplink CSI feedback, and downlink hybrid beamforming modules as an E2E neural network. Different from conventional approaches separately processing different modules, the proposed solution simultaneously optimizes all modules with the sum rate as the optimization object. Therefore, by perceiving the inherent property of air-to-ground massive MIMO-OFDM channel samples, the DL-based E2E neural network can establish the mapping function from the channel to the beamformer, so that the explicit channel reconstruction can be avoided with reduced pilot and feedback overhead. Besides, practical low-resolution phase shifters (PSs) introduce the quantization constraint, leading to the intractable gradient backpropagation when training the neural network. To mitigate the performance loss caused by the phase quantization error, we adopt the transfer learning strategy to further fine-tune the E2E neural network based on a pre-trained network that assumes the ideal infinite-resolution PSs. Numerical results show that our DL-based schemes have considerable advantages over state-of-the-art schemes. [ABSTRACT FROM AUTHOR]

The need of solar power uncertainty quantification in the power system has inspired probabilistic solar power forecasting. This paper proposes a novel multi-step parametric method for intra-day probabilistic solar power forecasting. First, statistical analysis on solar power distribution is done using four forecasting methods in real-world data. Fat tails are clearly found in solar power distribution, which could not be modelled by the widely-used normal distribution. In light of this discovery, two fat-tailed distributions, i.e., Laplace and two-sided power distributions, along with their generalized variants are then proposed to better model the conditional distribution of solar power output. Second, a recently proposed DeepAR model for time series probabilistic forecasting based on deep recurrent neural network is used to map various predictors into parameters of the fat-tailed distribution. Moreover, a novel loss function based on the continuous ranked probability score is proposed, and its closed-form formula over the proposed fat-tailed distributions is derived for efficient model training. Numerical results on public real-world data show that our method is very effective and the proposed model can provide intra-day probabilistic solar power forecasting with high quality and reliability. [ABSTRACT FROM AUTHOR]

mmWave communication requires accurate and continuous beam steering to overcome the severe propagation loss and user mobility. In this paper, we leverage a self-supervised deep learning approach to exploit sub-6 GHz channels and propose a novel method to predict beamforming vectors in the mmWave band for a single access point– user link. This complex channel-beam mapping is learned via data issued from the DeepMIMO dataset. We then compare our proposed method with existing supervised deep learning and classic reinforcement learning methods. Our simulations show that choosing an appropriate beam steering method depends on the target application and is a tradeoff between data rate and computational complexity. We also investigate tuning the size of our neural network depending on the number of transmit and receive antennas at the access point. Finally, we extend our method to the case of multiple links and introduce a federated learning (FL) approach to efficiently predict their mmWave beams by sharing only the weights of the locally trained neural networks (and not the local data). We investigate both synchronous and asynchronous FL methods. Our numerical simulations show the high potential of our approach, especially when the local available data is scarce or imperfect. [ABSTRACT FROM AUTHOR]

Deep autoencoder-based approaches have achieved significant improvements on restoring damaged images, yet they still suffer from artifacts due to the inadequate representation and inaccurate regularization of existing features. In this paper, we propose a dual-pyramidal inpainting framework called DPNet to address these two limitations, which seamlessly integrates sufficient feature learning and dynamic regularization within an autoencoder network. Specifically, to exhaustively extract multi-scale features, we adopt layer-wise pyramidal convolution in encoder, which provides an arbitrary combination pool of various receptive fields. Subsequently, to tackle the patch deterioration problem in previous cross-scale non-local schemes, we further propose a Pyramidal Attention Mechanism (PAM) in decoder to acquire finer patches directly from learned layers. Mutually benefited with pyramidal features extraction in encoder, the dissemination space for non-local pixels in our PAM is notably enlarged to pyramidal level, thus significantly benefiting the feature representation. Moreover, to avoid the mask error accumulation in existing works, a dynamic normalization mechanism utilizing the spatial mask information updated in encoder is introduced, which further ensures the feature integrity and consistency. Such a dual-pyramidal structure along with dynamic normalization significantly improve the inpainting quality, outperforming existing competitors. Comprehensive experiments conducted on three benchmark datasets demonstrate that our DPNet performs favorably against the state-of-the-arts. [ABSTRACT FROM AUTHOR]

Multimodal, alias, guided, image restoration is the reconstruction of a degraded image from a target modality with the aid of a high quality image from another modality. A similar task is image fusion; it refers to merging images from different modalities into a composite image. Traditional approaches for multimodal image restoration and fusion include analytical methods that are computationally expensive at inference time. Recently developed deep learning methods have shown a great performance at a reduced computational cost; however, since these methods do not incorporate prior knowledge about the problem at hand, they result in a “black box” model, that is, one can hardly say what the model has learned. In this paper, we formulate multimodal image restoration and fusion as a coupled convolutional sparse coding problem, and adopt the Method of Multipliers (MM) for its solution. Then, we use the MM-based solution to design a convolutional neural network (CNN) encoder that follows the principle of deep unfolding. To address multimodal image restoration and fusion, we design two multimodal models which employ the proposed encoder followed by an appropriately designed decoder that maps the learned representations to the desired output. Unlike most existing deep learning designs comprising multiple encoding branches followed by a concatenation or a linear combination fusion block, the proposed design provides an efficient and structured way to fuse information at different stages of the network, providing representations that can lead to accurate image reconstruction. The proposed models are applied to three image restoration tasks, as well as two image fusion tasks. Quantitative and qualitative comparisons against various state-of-the-art analytical and deep learning methods corroborate the superior performance of the proposed framework. [ABSTRACT FROM AUTHOR]

The depth video contains large smooth contents with sharp edges. Since the deep learning-based color video orientated intra prediction methods pay no attention to the characteristics of depth video, they are unsuitable for optimizing the coding efficiency of depth video. In this paper, a multiple resolution prediction method with deep up-sampling is proposed to promote the coding efficiency of depth video. To efficiently encode the depth blocks of different complexity, the depth block is selectively encoded at different resolutions, including $\times 1$ , $\times 1$ /2, and $\times 1$ /4 resolutions. If the block is encoded with a low-resolution (LR), the resolution of reconstructed LR depth block is recovered by an up-sampling network. To constrain the quality of both reconstructed high-resolution depth block and its synthesized view, a view synthesis distortion guidance mechanism is proposed for the up-sampling network. In addition, a distillation-based lightweight up-sampling network is proposed to reduce the computational complexity. Experimental results demonstrate that the proposed multiple resolution prediction method obtains an average of 10.84% BD-rate saving in comparison with 3D-HEVC. [ABSTRACT FROM AUTHOR]

Most deep learning models for temporal regression directly output the estimation based on single input images, ignoring the relationships between different images. In this paper, we propose deep relation learning for regression, aiming to learn different relations between a pair of input images. Four non-linear relations are considered: “cumulative relation,” “relative relation,” “maximal relation” and “minimal relation.” These four relations are learned simultaneously from one deep neural network which has two parts: feature extraction and relation regression. We use an efficient convolutional neural network to extract deep features from the pair of input images and apply a Transformer for relation learning. The proposed method is evaluated on a merged dataset with 6,049 subjects with ages of 0–97 years using 5-fold cross-validation for the task of brain age estimation. The experimental results have shown that the proposed method achieved a mean absolute error (MAE) of 2.38 years, which is lower than the MAEs of 8 other state-of-the-art algorithms with statistical significance (p<0.05) in paired T-test (two-side). [ABSTRACT FROM AUTHOR]

Histopathological tissue classification is a simpler way to achieve semantic segmentation for the whole slide images, which can alleviate the requirement of pixel-level dense annotations. Existing works mostly leverage the popular CNN classification backbones in computer vision to achieve histopathological tissue classification. In this paper, we propose a super lightweight plug-and-play module, named Pyramidal Deep-Broad Learning (PDBL), for any well-trained classification backbone to improve the classification performance without a re-training burden. For each patch, we construct a multi-resolution image pyramid to obtain the pyramidal contextual information. For each level in the pyramid, we extract the multi-scale deep-broad features by our proposed Deep-Broad block (DB-block). We equip PDBL in three popular classification backbones, ShuffLeNetV2, EfficientNetb0, and ResNet50 to evaluate the effectiveness and efficiency of our proposed module on two datasets (Kather Multiclass Dataset and the LC25000 Dataset). Experimental results demonstrate the proposed PDBL can steadily improve the tissue-level classification performance for any CNN backbones, especially for the lightweight models when given a small among of training samples (less than 10%). It greatly saves the computational resources and annotation efforts. The source code is available at: https://github.com/linjiatai/PDBL. [ABSTRACT FROM AUTHOR]

Wi-Fi based gait recognition has many potential applications. However, the gait information derived from Wi-Fi changes with the walking path. This makes the human identification through gait really challenging, the existing Wi-Fi based gait recognition systems require the subject walking along a predetermined path. This path dependence restriction impedes Wi-Fi based gait recognition from being widely used. In this paper, a path independent gait recognition system for a single subject, Wi-PIGR, is proposed. In Wi-PIGR, the subject is identified through the gait regardless of the walking path. Specifically, an extra receiver is introduced to get CSI data in orthogonal directions. A series of signal processing techniques are proposed to eliminate the differences among signals introduced by walking along the arbitrary paths and generate a high quality path independent signal spectrogram. Furthermore, a deep learning approach is integrated into the feature extraction. The experiment results in typical indoor environment demonstrate the superior performance of Wi-PIGR, with the average recognition accuracy of 77.15 percent, when the number of subjects is 50. [ABSTRACT FROM AUTHOR]

With the remarkable recent progress on learning deep generative models, it becomes increasingly interesting to develop models for controllable image synthesis from reconfigurable structured inputs. This paper focuses on a recently emerged task, layout-to-image, whose goal is to learn generative models for synthesizing photo-realistic images from a spatial layout (i.e., object bounding boxes configured in an image lattice) and its style codes (i.e., structural and appearance variations encoded by latent vectors). This paper first proposes an intuitive paradigm for the task, layout-to-mask-to-image, which learns to unfold object masks in a weakly-supervised way based on an input layout and object style codes. The layout-to-mask component deeply interacts with layers in the generator network to bridge the gap between an input layout and synthesized images. Then, this paper presents a method built on Generative Adversarial Networks (GANs) for the proposed layout-to-mask-to-image synthesis with layout and style control at both image and object levels. The controllability is realized by a proposed novel Instance-Sensitive and Layout-Aware Normalization (ISLA-Norm) scheme. A layout semi-supervised version of the proposed method is further developed without sacrificing performance. In experiments, the proposed method is tested in the COCO-Stuff dataset and the Visual Genome dataset with state-of-the-art performance obtained. [ABSTRACT FROM AUTHOR]

In this paper, we reveal that metric learning would suffer from serious inseparable problem if without informative sample mining. Since the inseparable samples are often mixed with hard samples, current informative sample mining strategies used to deal with inseparable problem may bring up some side-effects, such as instability of objective function, etc. To alleviate this problem, we propose a novel distance metric learning algorithm, named adaptive neighborhood metric learning (ANML). In ANML, we design two thresholds to adaptively identify the inseparable similar and dissimilar samples in the training procedure, thus inseparable sample removing and metric parameter learning are implemented in the same procedure. Due to the non-continuity of the proposed ANML, we develop an ingenious function, named log-exp mean function to construct a continuous formulation to surrogate it, which can be efficiently solved by the gradient descent method. Similar to Triplet loss, ANML can be used to learn both the linear and deep embeddings. By analyzing the proposed method, we find it has some interesting properties. For example, when ANML is used to learn the linear embedding, current famous metric learning algorithms such as the large margin nearest neighbor (LMNN) and neighbourhood components analysis (NCA) are the special cases of the proposed ANML by setting the parameters different values. When it is used to learn deep features, the state-of-the-art deep metric learning algorithms such as Triplet loss, Lifted structure loss, and Multi-similarity loss become the special cases of ANML. Furthermore, the log-exp mean function proposed in our method gives a new perspective to review the deep metric learning methods such as Prox-NCA and N-pairs loss. At last, promising experimental results demonstrate the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Cameras currently allow access to two image states: (i) a minimally processed linear raw-RGB image state (i.e., raw sensor data); or (ii) a highly-processed nonlinear image state (e.g., sRGB). There are many computer vision tasks that work best with a linear image state, such as image deblurring and image dehazing. Unfortunately, the vast majority of images are saved in the nonlinear image state. Because of this, a number of methods have been proposed to “unprocess” nonlinear images back to a raw-RGB state. However, existing unprocessing methods have a drawback because raw-RGB images are sensor-specific. As a result, it is necessary to know which camera produced the sRGB output and use a method or network tailored for that sensor to properly unprocess it. This paper addresses this limitation by exploiting another camera image state that is not available as an output, but it is available inside the camera pipeline. In particular, cameras apply a colorimetric conversion step to convert the raw-RGB image to a device-independent space based on the CIE XYZ color space before they apply the nonlinear photo-finishing. Leveraging this canonical image state, we propose a deep learning framework, CIE XYZ Net, that can unprocess a nonlinear image back to the canonical CIE XYZ image. This image can then be processed by any low-level computer vision operator and re-rendered back to the nonlinear image. We demonstrate the usefulness of the CIE XYZ Net on several low-level vision tasks and show significant gains that can be obtained by this processing framework. Code and dataset are publicly available at https://github.com/mahmoudnafifi/CIE_XYZ_NET. [ABSTRACT FROM AUTHOR]

3D human pose and shape estimation from monocular images has been an active research area in computer vision. Existing deep learning methods for this task rely on high-resolution input, which however, is not always available in many scenarios such as video surveillance and sports broadcasting. Two common approaches to deal with low-resolution images are applying super-resolution techniques to the input, which may result in unpleasant artifacts, or simply training one model for each resolution, which is impractical in many realistic applications. To address the above issues, this paper proposes a novel algorithm called RSC-Net, which consists of a Resolution-aware network, a Self-supervision loss, and a Contrastive learning scheme. The proposed method is able to learn 3D body pose and shape across different resolutions with one single model. The self-supervision loss enforces scale-consistency of the output, and the contrastive learning scheme enforces scale-consistency of the deep features. We show that both these new losses provide robustness when learning in a weakly-supervised manner. Moreover, we extend the RSC-Net to handle low-resolution videos and apply it to reconstruct textured 3D pedestrians from low-resolution input. Extensive experiments demonstrate that the RSC-Net can achieve consistently better results than the state-of-the-art methods for challenging low-resolution images. [ABSTRACT FROM AUTHOR]

The detection and recognition of traffic signs is an important topic in intelligent transportation systems. The automatic detection and recognition of traffic signs during driving is the basis for realizing the unmanned driving. Therefore, the work on the detection and recognition of traffic signs has a potential value and application prospect. In the traditional detection and recognition methods, they often detect and recognize traffic signs image by image. In this case, only the information of the current image is used, and the relationship between the image sequences is not considered. To end this issue, we propose a novel model that can use the relationship in multi-images to detect and recognize traffic signs in a driving video sequence quickly and accurately. The model proposed in this paper is a fusion model based on YOLO-V3 and VGG19 network. Finally, we test this proposed model on a public dataset and compare it to the baseline method, and results show that this proposed model achieves accuracy over 90% and outperforms the baseline method for all types of traffic signs in different conditions. Thus, we can conclude this proposed model is efficient and accurate. [ABSTRACT FROM AUTHOR]

Pedestrian Detection is the most critical module of an Autonomous Driving system. Although a camera is commonly used for this purpose, its quality degrades severely in low-light night time driving scenarios. On the other hand, the quality of a thermal camera image remains unaffected in similar conditions. This paper proposes an end-to-end multimodal fusion model for pedestrian detection using RGB and thermal images. Its novel spatio-contextual deep network architecture is capable of exploiting the multimodal input efficiently. It consists of two distinct deformable ResNeXt-50 encoders for feature extraction from the two modalities. Fusion of these two encoded features takes place inside a multimodal feature embedding module (MuFEm) consisting of several groups of a pair of Graph Attention Network and a feature fusion unit. The output of the last feature fusion unit of MuFEm is subsequently passed to two CRFs for their spatial refinement. Further enhancement of the features is achieved by applying channel-wise attention and extraction of contextual information with the help of four RNNs traversing in four different directions. Finally, these feature maps are used by a single-stage decoder to generate the bounding box of each pedestrian and the score map. We have performed extensive experiments of the proposed framework on three publicly available multimodal pedestrian detection benchmark datasets, namely KAIST, CVC-14, and UTokyo. The results on each of them improved the respective state-of-the-art performance. A short video giving an overview of this work along with its qualitative results can be seen at https://youtu.be/FDJdSifuuCs. Our source code will be released upon publication of the paper. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel deep learning architecture to classify unsafe driving maneuvers from dashcam and IMU data. Such architecture processes the output of an object detection algorithm in combination with raw video frames and GPS/IMU data. At the core of the architecture there is a novel Spatio-Temporal Attention Selector (STAS) module, which (1) extracts features describing the evolution of each object in the scene over time and (2) leverages multi-head dot product attention to select the relevant ones, i.e., the dangerous ones or the ones in danger, to perform classification. We also introduce a simple but effective methodology to increase the benefit of fine-tuning the backbone network. Our method is shown to achieve higher performance than other approaches in the literature applying attention over single frames. [ABSTRACT FROM AUTHOR]

With the new feature of multi-energy coupling and the advancement of the energy market, Energy Internet (EI) has higher requirements for the efficiency and applicability of integrated energy response. This paper proposes an indirect multi-energy transaction (IMET) to promote multi-energy collaborative optimization in local energy market (LEM) and improve energy utilization through personalized responses from We-Energies (WEs). Firstly, an indirect customer-to-customer multi-energy transaction is modeled for local multi-energy coupling market which can satisfy privacy, preference and autonomy of users. The efficiency of energy matching can be promoted through the participation of conversion devices. In addition, multi-time scale hybrid trading mechanism is constructed with the consideration of the transmission speed of different energy sources. Meanwhile, energy transaction process is built as a Markov decision process (MDP) with deep reinforcement learning algorithm so that the system modeling error can be successfully avoided. Furthermore, a distributed training structure is utilized to obtain more experience for a wider range of scenarios. The results of numerical simulations demonstrate the performance of the proposed method. [ABSTRACT FROM AUTHOR]