Search

The article reports that With the continued growth of IoT devices and their deployment, manually managing and connecting them is impractical and presents multiple challenges. To that end, Zero Touch Networks that rely on software-based modules instead of dedicated propriety hardware become a viable potential solution. The overall aim of zero-touch networks is for machines to learn how to become more autonomous so that we can delegate complex, mundane tasks to them.

Radio signal recognition has a wide application in future communication systems and the vehicular communication, whose core is the extraction of signal features such as electromagnetic fingerprints. With the rapid development of artificial intelligence technology, deep learning has made amazing breakthroughs in image recognition, speech recognition and other fields. Deep learning is applied to electromagnetic fingerprint extraction in this paper. Firstly, thousands of the downlink aircraft communications addressing and reporting system (ACARS) signals used for communication between civil aircraft and airport tower are collected and generated. Then a pre-transformation network suitable for electromagnetic signals is constructed to convert one-dimensional signals into two-dimensional feature maps, and afterwards the feature maps are input into the convolutional neural network (CNN) for classification. By adopting the attention modules, the classification results were improved by a few percentage points over the baseline with a little cost. The method proposed in this paper achieves an accuracy rate of 94.1% and can obtain the aircraft type in a shorter time than traditional method. Moreover, the robustness of the proposed model in response to additive Gaussian white noise (AWGN) and phase deviation is studied and tested. [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]

Low level image restoration is an integral component of modern artificial intelligence (AI) driven camera pipelines. Most of these frameworks are based on deep neural networks which present a massive computational overhead on resource constrained platform like a mobile phone. In this paper, we propose several lightweight low-level modules which can be used to create a computationally low cost variant of a given baseline model. Recent works for efficient neural networks design have mainly focused on classification. However, low-level image processing falls under the ‘image-to-image’ translation genre which requires some additional computational modules not present in classification. This paper seeks to bridge this gap by designing generic efficient modules which can replace essential components used in contemporary deep learning based image restoration networks. We also present and analyse our results highlighting the drawbacks of applying depthwise separable convolutional kernel (a popular method for efficient classification network) for sub-pixel convolution based upsampling (a popular upsampling strategy for low-level vision applications). This shows that concepts from domain of classification cannot always be seamlessly integrated into ‘image-to-image’ translation tasks. We extensively validate our findings on three popular tasks of image inpainting, denoising and super-resolution. Our results show that proposed networks consistently output visually similar reconstructions compared to full capacity baselines with significant reduction of parameters, memory footprint and execution speeds on contemporary mobile devices. [ABSTRACT FROM AUTHOR]

Artificial Intelligence (AI) has attracted a great deal of attention in recent years. However, alongside all its advancements, problems have also emerged, such as privacy violations, security issues and model fairness. Differential privacy, as a promising mathematical model, has several attractive properties that can help solve these problems, making it quite a valuable tool. For this reason, differential privacy has been broadly applied in AI but to date, no study has documented which differential privacy mechanisms can or have been leveraged to overcome its issues or the properties that make this possible. In this paper, we show that differential privacy can do more than just privacy preservation. It can also be used to improve security, stabilize learning, build fair models, and impose composition in selected areas of AI. With a focus on regular machine learning, distributed machine learning, deep learning, and multi-agent systems, the purpose of this article is to deliver a new view on many possibilities for improving AI performance with differential privacy techniques. [ABSTRACT FROM AUTHOR]

Image classification is a fundamental artificial intelligence task that labels images into one of some predefined classes. However, training complex image classification models requires a large amount of computation resources and data in order to reach state-of-the-art performance. This demand drives the growth of distributed deep learning, where multiple agents cooperatively train global models with their individual datasets. Among such learning systems, decentralized learning is particularly attractive, as it can improve the efficiency and fault tolerance by eliminating the centralized parameter server, which could be the single point of failure or performance bottleneck. Although the agents do not need to disclose their training image samples, they exchange parameters with each other at each iteration, which can put them at the risk of data privacy leakage. Past works demonstrated the possibility of recovering training images from the exchanged parameters. One common defense direction is to adopt Differential Privacy (DP) to secure the optimization algorithms such as Stochastic Gradient Descent (SGD). Those DP-based methods mainly focus on standalone systems, or centralized distributed learning. How to enforce and optimize DP protection in decentralized learning systems is unknown and challenging, due to their complex communication topologies and distinct learning characteristics. In this paper, we design TOP- DP, a novel solution to optimize the differential privacy protection of decentralized image classification systems. The key insight of our solution is to leverage the unique features of decentralized communication topologies to reduce the noise scale and improve the model usability. (1) We enhance the DP-SGD algorithm with this topology-aware noise reduction strategy, and integrate the time-aware noise decay technique. (2) We design two novel learning protocols (synchronous and asynchronous) to protect systems with different network connectivities and topologies. We formally analyze and prove the DP requirement of our proposed solutions. Experimental evaluations demonstrate that our solution achieves a better trade-off between usability and privacy than prior works. To the best of our knowledge, this is the first DP optimization work from the perspective of network topologies. [ABSTRACT FROM AUTHOR]

This paper proposes the design of two coordinated wide-area damping controllers (CWADCs) for damping low frequency oscillations (LFOs), while accounting for the uncertainties present in the power system. The controllers based on Deep Neural Network (DNN) and Deep Reinforcement Learning (DRL), respectively, coordinate the operation of different local damping controls such as power system stabilizers (PSSs), static VAr compensators (SVCs), and supplementary damping controllers for DC lines (DC-SDCs). The DNN-CWADC learns to make control decisions using supervised learning; the training dataset consisting of polytopic controllers designed with the help of linear matrix inequality (LMI)-based mixed $H_2/H_\infty$ optimization. The DRL-CWADC learns to adapt to the system uncertainties based on its continuous interaction with the power system environment by employing an advanced version of the state-of-the-art deep deterministic policy gradient (DDPG) algorithm referred to as bounded exploratory control-based DDPG (BEC-DDPG). The studies performed on a 33 machine, 127 bus equivalent model of the Western Electricity Coordinating Council (WECC) system-embedded with different types of damping controls demonstrate the effectiveness of the proposed CWADCs. [ABSTRACT FROM AUTHOR]

Portfolio Selection is an important real-world financial task and has attracted extensive attention in artificial intelligence communities. This task, however, has two main difficulties: (i) the non-stationary price series and complex asset correlations make the learning of feature representation very hard; (ii) the practicality principle in financial markets requires controlling both transaction and risk costs. Most existing methods adopt handcraft features and/or consider no constraints for the costs, which may make them perform unsatisfactorily and fail to control both costs in practice. In this paper, we propose a cost-sensitive portfolio selection method with deep reinforcement learning. Specifically, a novel two-stream portfolio policy network is devised to extract both price series patterns and asset correlations, while a new cost-sensitive reward function is developed to maximize the accumulated return and constrain both costs via reinforcement learning. We theoretically analyze the near-optimality of the proposed reward, which shows that the growth rate of the policy regarding this reward function can approach the theoretical optimum. We also empirically evaluate the proposed method on real-world datasets. Promising results demonstrate the effectiveness and superiority of the proposed method in terms of profitability, cost-sensitivity and representation abilities. [ABSTRACT FROM AUTHOR]

Traditional Artificial Intelligence (AI) based fault detection approaches need a large amount of data for the model learning. However, in a real-world system, it is very difficult and expensive to obtain massive labeled fault data. In addition, the working conditions of a motor are usually variable, conventional fault diagnosis models with weak generalization ability can only be used for fault detection under constant working condition. The performance of traditional AI based approaches decreases when the working condition changes. To this end, a novel deep Gaussian process (GP) kernel transfer based few-shot learning method (RNGPT) is proposed in this paper for the fault detection of electric machines. First, a deep residual network (ResNet) is used to extract the features of the raw data. Then, the encoded latent feature vector is fed into the GP with kernel transfer ability to make the motor fault detection and classification. The proposed method uses much less data than the traditional AI based method to achieve fault diagnosis under variable working condition, and does not cause an overfitting problem. Experimental results of two case studies demonstrate that the proposed RNGPT model can accurately and effectively detect motor faults with limited labeled data under different working conditions. Experimental results of RNGPT with radial basis function (RBF) kernel model on simulation data present that the fault detection accuracy of the proposed method is about 16% higher than the conventional deep learning methods, 6% higher than other few-shot learning based methods in 5-shot and 4% higher in 1-shot. Finally, experimental on a real-world dataset, the RNGPT-RBF model still has the highest fault diagnosis accuracy in 5-shot (99.39 $ \pm $ 0.09%) and 1-shot (98.55 $ \pm $ 0.16%). [ABSTRACT FROM AUTHOR]

As a follow-up to the first IEEE Transactions on Medical Imaging (TMI) special issue on the theme of deep tomographic reconstruction, the second special issue is assembled to reflect the status and momentum of this rapidly emerging field. In this editorial, we provide a brief background illustrating the motivation for the development of network-based, data-driven, and learning-oriented reconstruction methods, summarize the included papers, and report our verification of the shared deep learning codes. Finally, we discuss several important research topics to facilitate further investigation and collaboration. [ABSTRACT FROM AUTHOR]

In this paper, we propose a channel-wise interaction based binary convolutional neural networks (CI-BCNN) approach for efficient inference. Conventional binary convolutional neural networks usually apply the xnor and bitcount operations in the binary convolution with notable quantization errors, which obtain opposite signs of pixels in binary feature maps compared to their full-precision counterparts and lead to significant information loss. In our proposed CI-BCNN method, we exploit the channel-wise interactions with the prior knowledge which aims to alleviate inconsistency of signs in binary feature maps and preserves the information of input samples during inference. Specifically, we mine the channel-wise interactions by using a reinforcement learning model, and impose channel-wise priors on the intermediate feature maps to correct inconsistent signs through the interacted bitcount. Since CI-BCNN mines the channel-wise interactions in a large search space where each channel may correlate with others, the search deficiency caused by sparse interactions obstacles the agent to obtain the optimal policy. To address this, we further present a hierarchical channel-wise interaction based binary convolutional neural networks (HCI-BCNN) method to shrink the search space via hierarchical reinforcement learning. Moreover, we propose a denoising interacted bitcount operation in binary convolution by smoothing the channel-wise interactions, so that noise in channel-wise priors can be alleviated. Extensive experimental results on the CIFAR-10 and ImageNet datasets demonstrate the effectiveness of the proposed CI-BCNN and HCI-BCNN. [ABSTRACT FROM AUTHOR]

Resilience of a distribution system can be enhanced by efficient restoration of critical load following a major outage. Existing models include optimization approaches that consider available information without incorporating the inherent asynchrony of data arrival during execution of the restoration plan. Failure to consider the asynchronous nature of information arrival can lead to underutilization of critical resources. Moreover, analytical models become computationally inefficient for large scale systems. On the other hand, artificial intelligence (AI)-based tools have demonstrated efficient results for power system applications. In this paper, it is proposed a Reinforcement Learning (RL) model that learns how to efficiently restore a distribution system after a major outage. The proposed approach is based on a Monte Carlo Tree Search to expedite the training process. The proposed model strategy provides a robust decision-making tool for asynchronous and partial information scenarios. The results, validated with the IEEE 13-bus test feeder and IEEE 8500-node distribution test feeder, demonstrate the effectiveness and scalability of the proposed method. [ABSTRACT FROM AUTHOR]

In this paper, we aim to address issues of joint spatial-temporal modeling and side information injection for deep-learning based in-loop filter. For , we design a deep network with both progressive rethinking and collaborative learning mechanisms to improve quality of the reconstructed intra-frames and inter-frames, respectively. For intra coding, a Progressive Rethinking Network (PRN) is designed to simulate the human decision mechanism for effective spatial modeling. Our designed block introduces an additional inter-block connection to bypass a high-dimensional informative feature before the bottleneck module across blocks to review the complete past memorized experiences and rethinks progressively. For inter coding, the current reconstructed frame interacts with reference frames (peak quality frame and the nearest adjacent frame) collaboratively at the feature level. For , we extract both intra-frame and inter-frame side information for better context modeling. A coarse-to-fine partition map based on HEVC partition trees is built as the intra-frame side information. Furthermore, the warped features of the reference frames are offered as the inter-frame side information. Our PRN with intra-frame side information provides 9.0% BD-rate reduction on average compared to HEVC baseline under All-intra (AI) configuration. While under Low-Delay B (LDB), Low-Delay P (LDP) and Random Access (RA) configuration, our PRN with inter-frame side information provides 9.0%, 10.6% and 8.0% BD-rate reduction on average respectively. Our project webpage is https://dezhao-wang.github.io/PRN-v2/. [ABSTRACT FROM AUTHOR]

With the development of artificial intelligence(AI), unmanned vehicles can relieve traffic jamming and decrease the risk of traffic accidents, where deep neural networks (DNNs) play an important role and have become one of the most critical technologies. Nevertheless, DNNs are still susceptible to adversarial examples. Even worse, they also show severe performance degradation when the system needs DNNs to learn new knowledge without forgetting the old one. As unmanned vehicles travel on the road, they need to frequently learn new categories and different representations. Learning all data after the new sample arrives will expend a lot of time and space. As a result, it will affect the deployment of artificial intelligence in unmanned scenes. In recent years, it has been observed that incremental learning technology can solve the above challenges. However, previously reported works mainly focused on batch learning. It is not clear how much impact the adversarial attack will have on the deep learning model when performing incremental learning tasks. This issue exposes the hidden safety risks of unmanned driving and increases discuss opportunities. Therefore, we propose an adversarial attack based on incremental learning techniques for unmanned scenes in this paper. Specifically, it can retain information previously learned by the model. At the same time, it can renew the old model to learn new model, thereby continually adding small perturbation to legitimate examples. A couple of experiments on the Pascal VOC 2012 dataset has been conducted, and the experiment results show that the adversarial attack based on incremental learning techniques has a higher attack success rate. Further, it can improve the successful attack rate by 8.43%. [ABSTRACT FROM AUTHOR]

This paper proposes a novel intelligent fault diagnosis method to automatically identify different health conditions of wind turbine (WT) gearbox. Unlike traditional approaches, where feature extraction and classification are separately designed and performed, this paper aims to automatically learn effective fault features directly from raw vibration signals while classify the type of faults in a single framework, thus providing an end-to-end learning-based fault diagnosis system for WT gearbox without additional signal processing and diagnostic expertise. Considering the multiscale characteristics inherent in vibration signals of a gearbox, a new multiscale convolutional neural network (MSCNN) architecture is proposed to perform multiscale feature extraction and classification simultaneously. The proposed MSCNN incorporates multiscale learning into the traditional CNN architecture, which has two merits: 1) high-level fault features can be effectively learned by the hierarchical learning structure with multiple pairs of convolutional and pooling layers; and 2) multiscale learning scheme can capture complementary and rich diagnosis information at different scales. This greatly improves the feature learning ability and enables better diagnosis performance. The proposed MSCNN approach is evaluated through experiments on a WT gearbox test rig. Experimental results and comprehensive comparison analysis with respect to the traditional CNN and traditional multiscale feature extractors have demonstrated the superiority of the proposed method. [ABSTRACT FROM AUTHOR]

Automatic transmissions are a core component of modern vehicles, and achieving good shift quality is critical to enhance the driving experience. In companies that manufacture transmissions, expert engineers take great care in calibrating parameters for controlling hydraulic pressure with the goal of achieving targeted shift quality. Because we need human experts to evaluate shift quality, it is hard to shorten the time taken to calibrate the systems controlling hydraulic pressure. In this paper, to reduce such development time, we propose a novel framework of a Classifier of Shift Quality; it applies the standard Supervised Deep Learning techniques (CSQ-SDL) to time-series measurement data. The framework consists of five procedures: measurement data collection, labeling by experts, data augmentation, data standardization, and the training of deep convolutional neural networks. Moreover, we also carry out driving experiments in which CSQ-SDL is used to assess the engagement of the lock-up clutch of a specific transmission model. By using raw time-series data measured by ordinary sensors in advance, and labels written later by an expert engineer looking at the raw data, we build binary classifiers and test their performance. It turns out that the accuracy of predicting expert's judgment is high; the area under the curve is 0.94. The result indicates that the proposed method is capable shortening product development times and thus meeting the demands of today's competitive automotive market. [ABSTRACT FROM AUTHOR]

In this paper, we experimentally and analytically evaluate the reliability of two state-of-the-art neural networks for linear regression and pattern recognition (multilayer perceptron and single-layer perceptron) implemented in a system-on-chip composed of a field-programmable gate array (FPGA) and a microprocessor. We have considered, for each neural network, three different activation function complexities, to evaluate how the implementation affects FPGAs reliability. As we show in this paper, higher complexity increases the exposed area but reduces the probability of one failure to impact the network output. In addition, we propose to distinguish between critical and tolerable errors in artificial neural networks. Experiments using a controlled heavy-ions beam show that, for both networks, only about 30% of the observed output errors actually affect the outputs correctness. We identify the causes of critical errors through fault injection, and found that faults in initial layers are more likely to significantly affect the output. [ABSTRACT FROM PUBLISHER]

This paper proposes a demand response method to reduce the long-term charging cost of single plug-in electric vehicles (PEV) while overcoming obstacles such as the stochastic nature of the user's driving behaviour, traffic condition, energy usage, and energy price. The problem is formulated as a Markov Decision Process (MDP) with an unknown transition probability matrix and solved using deep reinforcement learning (RL) techniques. The proposed method does not require any initial data on the PEV driver's behaviour and shows improvement on learning speed when compared to a pure model-free reinforcement learning method. A combination of model-based and model-free learning methods called Dyna-Q reinforcement learning is utilized in our strategy. Every time a real experience is obtained, the model is updated, and the RL agent will learn from both the real experience and “imagined” experiences from the model. Due to the vast amount of state space, a table-lookup method is impractical, and a value approximation method using deep neural networks is employed for estimating the long-term expected reward of all state-action pairs. An average of historical price and a long short-term memory (LSTM) network are used to predict future price. Simulation results demonstrate the effectiveness of this approach and its ability to reach an optimal policy quicker while avoiding state of charge (SOC) depletion during trips when compared to existing PEV charging schemes. [ABSTRACT FROM AUTHOR]

COVID-19 has caused a global pandemic and become the most urgent threat to the entire world. Tremendous efforts and resources have been invested in developing diagnosis, prognosis and treatment strategies to combat the disease. Although nucleic acid detection has been mainly used as the gold standard to confirm this RNA virus-based disease, it has been shown that such a strategy has a high false negative rate, especially for patients in the early stage, and thus CT imaging has been applied as a major diagnostic modality in confirming positive COVID-19. Despite the various, urgent advances in developing artificial intelligence (AI)-based computer-aided systems for CT-based COVID-19 diagnosis, most of the existing methods can only perform classification, whereas the state-of-the-art segmentation method requires a high level of human intervention. In this paper, we propose a fully-automatic, rapid, accurate, and machine-agnostic method that can segment and quantify the infection regions on CT scans from different sources. Our method is founded upon two innovations: 1) the first CT scan simulator for COVID-19, by fitting the dynamic change of real patients’ data measured at different time points, which greatly alleviates the data scarcity issue; and 2) a novel deep learning algorithm to solve the large-scene-small-object problem, which decomposes the 3D segmentation problem into three 2D ones, and thus reduces the model complexity by an order of magnitude and, at the same time, significantly improves the segmentation accuracy. Comprehensive experimental results over multi-country, multi-hospital, and multi-machine datasets demonstrate the superior performance of our method over the existing ones and suggest its important application value in combating the disease. [ABSTRACT FROM AUTHOR]

Segmenting the retinal layers in optical coherence tomography (OCT) images helps to quantify the layer information in early diagnosis of retinal diseases, which are the main cause of permanent blindness. Thus, the segmentation process plays a critical role in preventing vision impairment. However, because there is a lack of practical automated techniques, expert ophthalmologists still have to manually segment the retinal layers. In this paper, we propose an automated segmentation method for OCT images based on a feature-learning regression network without human bias. The proposed deep neural network regression takes the intensity, gradient, and adaptive normalized intensity score (ANIS) of an image segment as features for learning, and then predicts the corresponding retinal boundary pixel. Reformulating the segmentation as a regression problem obviates the need for a huge dataset and reduces the complexity significantly, as shown in the analysis of computational complexity given here. In addition, assisted by ANIS, the method operates robustly on OCT images containing intensity variances, low-contrast regions, speckle noise, and blood vessels, yet remains accurate and time-efficient. In the evaluation of the method conducted using 114 images, the processing time was approximately 10.596 s per image for identifying eight boundaries, and the training phase for each boundary line took only 30 s. Further, the Dice similarity coefficient used for assessing accuracy gave a computed value of approximately 0.966. The absolute pixel distance of manual and automatic segmentation using the proposed scheme was 0.612, which is less than a one-pixel difference, on average. [ABSTRACT FROM AUTHOR]

This paper proposes a novel multidomain features-based genetic algorithm (GA) optimized artificial immune system (AIS) framework for fault detection in real systems. Different from native real-valued negative selection algorithm (RNSA) that operates in original data space, this algorithm utilizes feature space transformation and diversity factor-based GA for optimized detector distribution in nonself feature space. The proposed framework comprises three stages namely; feature extraction, unsupervised feature selection, and GA optimized AIS. In the first stage, signal processing methods are applied to extract multidomain features (time-domain statistical, frequency domain statistical, and special features) of the system. In the second stage, two unsupervised methods namely, ${k}$ -NN clustering and pretraining using deep learning neural network are proposed for dominant fault-characterizing feature selection. Finally, in the third stage, the fault-characterizing feature vectors are used for system status categorization (i.e., normal, fault) using selected (fault-characterizing) features-based AIS method. The efficacy of the proposed framework is verified through experiments on motor bearing fault detection using vibration signal. The major accomplishment of the proposed combination of space transformation, feature selection and AIS (anomaly classification) techniques is the alleviation of computational burden on RNSA implementation. Moreover, GA optimized AIS fault diagnosis based on well-established features gives improved detection performance. [ABSTRACT FROM AUTHOR]

Nowadays digital surveillance systems are universally installed for continuously collecting enormous amounts of data, thereby requiring human monitoring for the identification of different activities and events. Smarter surveillance is the need of this era through which normal and abnormal activities can be automatically identified using artificial intelligence and computer vision technology. In this paper, we propose a framework for activity recognition in surveillance videos captured over industrial systems. The continuous surveillance video stream is first divided into important shots, where shots are selected using the proposed convolutional neural network (CNN) based human saliency features. Next, temporal features of an activity in the sequence of frames are extracted by utilizing the convolutional layers of a FlowNet2 CNN model. Finally, a multilayer long short-term memory is presented for learning long-term sequences in the temporal optical flow features for activity recognition. Experiments 1 https://github.com/Aminullah6264/Activity%5fRec%5fML-LSTM. are conducted using different benchmark action and activity recognition datasets, and the results reveal the effectiveness of the proposed method for activity recognition in industrial settings compared with state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Recent advancements in artificial intelligence are providing the insurance industry with new opportunities to create tailored solutions and services based on newfound knowledge of consumers, and the execution of enhanced operations and business functions. However, insurance data are heterogeneous, and imbalanced class distribution with low frequency and high dimensions, which presents four major challenges to machine learning in real-world business. Traditional machine learning algorithms can typically apply to standard data sets, which are normally homogeneous and balanced. In this paper, we focus on an efficient cost-sensitive parallel learning framework (CPLF) to enhance insurance operations with a deep learning approach that does not require preprocessing. Our approach comprises a novel, unified, end-to-end cost-sensitive parallel neural network that learns real-world heterogeneous data. A specifically designed cost-sensitive matrix then automatically generates a robust model for learning minority classifications, and the parameters of both the cost-sensitive matrix and the hybrid neural network are alternately but jointly optimized during training. We also study the CPLF-based architecture for a real-world insurance intelligence operation system, and demonstrate fraud detection and policy renewal experiments on this system. The results of comparative experiments on real-world insurance data sets reflecting actual business cases demonstrate the effectiveness of our design. [ABSTRACT FROM AUTHOR]

In this paper, we provide a systematical overview and analysis on the joint feature and texture representation framework, which aims to smartly and coherently represent the visual information with the front-end intelligence in the scenario of video big data applications. In particular, we first demonstrate the advantages of the joint compression framework in terms of both reconstruction quality and analysis accuracy. Subsequently, the interactions between visual feature and texture in the compression process are further illustrated. Finally, the future joint coding scheme by incorporating the deep learning features is envisioned, and future challenges toward seamless and unified joint compression are discussed. The joint compression framework, which bridges the gap between visual analysis and signal-level representation, is expected to contribute to a series of applications, such as video surveillance and autonomous driving. [ABSTRACT FROM AUTHOR]

While perception tasks such as visual object recognition and text understanding play an important role in human intelligence, subsequent tasks that involve inference, reasoning, and planning require an even higher level of intelligence. The past few years have seen major advances in many perception tasks using deep learning models. For higher-level inference, however, probabilistic graphical models with their Bayesian nature are still more powerful and flexible. To achieve integrated intelligence that involves both perception and inference, it is naturally desirable to tightly integrate deep learning and Bayesian models within a principled probabilistic framework, which we call Bayesian deep learning. In this unified framework, the perception of text or images using deep learning can boost the performance of higher-level inference and in return, the feedback from the inference process is able to enhance the perception of text or images. This paper proposes a general framework for Bayesian deep learning and reviews its recent applications on recommender systems, topic models, and control. In this paper, we also discuss the relationship and differences between Bayesian deep learning and other related topics such as the Bayesian treatment of neural networks. [ABSTRACT FROM PUBLISHER]

Recently, the rapid advancement of high computing platforms has accelerated the development and applications of artificial intelligence techniques. Deep learning, which has been regarded as the next paradigm to revolutionize users' experiences, has attracted networking researchers' interests to relieve the burden due to the exponentially growing traffic and increasing complexities. Various intelligent packet transmission strategies have been proposed to tackle different network problems. However, most of the existing research just focuses on the network related improvements and neglects the analysis about the computation consumptions. In this paper, we propose a Value Iteration Architecture based Deep Learning (VIADL) method to conduct routing design to address the limitations of existing deep learning based routing algorithms in dynamic networks. Besides the network performance analysis, we also study the complexity of our proposal as well as the resource consumptions in different deployment manners. Moreover, we adopt the Heterogeneous Computing Platform (HCP) to conduct the training and running of the proposed VIADL since the theoretical analysis demonstrates the significant reduction of the time complexity with the multiple GPUs in HCPs. Furthermore, simulation results demonstrate that compared with the existing deep learning based method, our proposal can guarantee more stable network performance when network topology changes. [ABSTRACT FROM AUTHOR]

Automatic modulation recognition (AMR) is an essential and challenging topic in the development of the cognitive radio (CR), and it is a cornerstone of CR adaptive modulation and demodulation capabilities to sense and learn environments and make corresponding adjustments. AMR is essentially a classification problem, and deep learning achieves outstanding performances in various classification tasks. So, this paper proposes a deep learning-based method, combined with two convolutional neural networks (CNNs) trained on different datasets, to achieve higher accuracy AMR. A CNN is trained on samples composed of in-phase and quadrature component signals, otherwise known as in-phase and quadrature samples, to distinguish modulation modes, that are relatively easy to identify. We adopt dropout instead of pooling operation to achieve higher recognition accuracy. A CNN based on constellation diagrams is also designed to recognize modulation modes that are difficult to distinguish in the former CNN, such as 16 quadratic-amplitude modulation (QAM) and 64 QAM, demonstrating the ability to classify QAM signals even in scenarios with a low signal-to-noise ratio. [ABSTRACT FROM AUTHOR]

Image annotation aims to annotate a given image with a variable number of class labels corresponding to diverse visual concepts. In this paper, we address two main issues in large-scale image annotation: 1) how to learn a rich feature representation suitable for predicting a diverse set of visual concepts ranging from object, scene to abstract concept and 2) how to annotate an image with the optimal number of class labels. To address the first issue, we propose a novel multi-scale deep model for extracting rich and discriminative features capable of representing a wide range of visual concepts. Specifically, a novel two-branch deep neural network architecture is proposed, which comprises a very deep main network branch and a companion feature fusion network branch designed for fusing the multi-scale features computed from the main branch. The deep model is also made multi-modal by taking noisy user-provided tags as model input to complement the image input. For tackling the second issue, we introduce a label quantity prediction auxiliary task to the main label prediction task to explicitly estimate the optimal label number for a given image. Extensive experiments are carried out on two large-scale image annotation benchmark datasets, and the results show that our method significantly outperforms the state of the art. [ABSTRACT FROM AUTHOR]

This paper introduces advances in the performance of AI and deep learning inference application on the next generation Intel Xeon Scalable processor, code-named Cascade Lake, which also includes support for Intel Optane DC persistent memory, a breakthrough nonvolatile memory technology that bridges the gap between DRAM and storage. [ABSTRACT FROM AUTHOR]

In this paper, a data-driven fault diagnosis model dealing with chemical imbalanced data streams is investigated. Different faults occur with varied frequencies by continuous arrival in chemical plants, while this issue has been hardly addressed in developing a diagnosis model. A novel incremental imbalance modified deep neural network (incremental-IMDNN) is proposed to promote the fault diagnosis to the imbalanced data stream. The first step in designing the incremental-IMDNN is the employment of an imbalance modified method combined with active learning for the extraction and generation of the most valuable information keeping in view the model feedback. DNN is utilized as a basic diagnosis model to excavate potential information. Then for the continuous arrival of new fault modes, DNN is promoted in an incremental hierarchical way. Unlike the traditional model that trained on a static snapshot of data, this model inherits the existing knowledge and hierarchically expands the diagnosis model by the similarity of faults. Similar faults that are judged by fuzzy clustering merge into a superclass, and every submodel shares the same architecture that is prevalent in previous research, which can be trained in parallel. We validate the performance of the proposed method in a Tennessee Eastman (TE) dataset, and the simulation results indicate that the proposed incremental-IM-DNN is better than the existing methods and possesses significant robustness and adaptability in chemical fault diagnosis. [ABSTRACT FROM AUTHOR]

Facial expression is central to human experience, but most previous databases and studies are limited to posed facial behavior under controlled conditions. In this paper, we present a novel facial expression database, Real-world Affective Face Database (RAF-DB), which contains approximately 30 000 facial images with uncontrolled poses and illumination from thousands of individuals of diverse ages and races. During the crowdsourcing annotation, each image is independently labeled by approximately 40 annotators. An expectation–maximization algorithm is developed to reliably estimate the emotion labels, which reveals that real-world faces often express compound or even mixture emotions. A cross-database study between RAF-DB and CK+ database further indicates that the action units of real-world emotions are much more diverse than, or even deviate from, those of laboratory-controlled emotions. To address the recognition of multi-modal expressions in the wild, we propose a new deep locality-preserving convolutional neural network (DLP-CNN) method that aims to enhance the discriminative power of deep features by preserving the locality closeness while maximizing the inter-class scatter. Benchmark experiments on 7-class basic expressions and 11-class compound expressions, as well as additional experiments on CK+, MMI, and SFEW 2.0 databases, show that the proposed DLP-CNN outperforms the state-of-the-art handcrafted features and deep learning-based methods for expression recognition in the wild. To promote further study, we have made the RAF database, benchmarks, and descriptor encodings publicly available to the research community. [ABSTRACT FROM AUTHOR]

We propose a deep learning approach for directly estimating relative atmospheric visibility from outdoor photos without relying on weather images or data that require expensive sensing or custom capture. Our data-driven approach capitalizes on a large collection of Internet images to learn rich scene and visibility varieties. The relative CNN–RNN coarse-to-fine model, where CNN stands for convolutional neural network and RNN stands for recurrent neural network, exploits the joint power of relative support vector machine, which has a good ranking representation, and the data-driven deep learning features derived from our novel CNN–RNN model. The CNN–RNN model makes use of shortcut connections to bridge a CNN module and an RNN coarse-to-fine module. The CNN captures the global view while the RNN simulates human’s attention shift, namely, from the whole image (global) to the farthest discerned region (local). The learned relative model can be adapted to predict absolute visibility in limited scenarios. Extensive experiments and comparisons are performed to verify our method. We have built an annotated dataset consisting of about 40000 images with 0.2 million human annotations. The large-scale, annotated visibility data set will be made available to accompany this paper. [ABSTRACT FROM AUTHOR]

Recent advances in deep learning (DL) have stimulated increasing interests in neural networks (NN). From the perspective of operation type and network architecture, deep neural networks can be categorized into full convolution-based neural network (ConvNet), recurrent neural network (RNN), and fully-connected neural network (FCNet). Different types of neural networks are usually cascaded and combined as a hybrid neural network (Hybrid-NN) to complete real-life cognitive tasks. Such hybrid-NN implementation is memory-intensive with large number of memory accesses, hence the performance of hybrid-NN is often limited by the insufficient memory bandwidth. A “3D + 2.5D” integration system, which integrates a high-bandwidth 3D stacked DRAM side-by-side with a highly-parallel neural processing unit (NPU) on a silicon interposer, overcomes the bandwidth bottleneck in hybrid-NN acceleration. However, intensive concurrent 3D DRAM accesses produced by the NPU lead to a serious thermal problem in 3D DRAM. In this paper, we propose a neural processor called Parana for hybrid-NN acceleration in consideration of thermal problem of 3D DRAM. Parana solves the thermal problem of 3D memory by optimizing both the total number of memory accesses and memory accessing behaviors. For memory accessing behaviors, Parana balances the memory bandwidth by spatial division mapping hybrid-NN onto computing resources, which efficiently avoids that masses of memory accesses are issued in a short time period. To reduce the total number of memory accesses, we design a new NPU architecture and propose a memory-oriented tiling and scheduling mechanism to exploit the maximum utilization of on-chip buffer. Experimental results show that Parana reduces the peak temperature by up to 54.72 $^\circ$ C and the steady temperature by up to 32.27 $^\circ$ C over state-of-the-art accelerators with 3D memory without performance degradation. [ABSTRACT FROM AUTHOR]

Depth estimation from single monocular images is a key component in scene understanding. Most existing algorithms formulate depth estimation as a regression problem due to the continuous property of depths. However, the depth value of input data can hardly be regressed exactly to the ground-truth value. In this paper, we propose to formulate depth estimation as a pixelwise classification task. Specifically, we first discretize the continuous ground-truth depths into several bins and label the bins according to their depth ranges. Then, we solve the depth estimation problem as classification by training a fully convolutional deep residual network. Compared with estimating the exact depth of a single point, it is easier to estimate its depth range. More importantly, by performing depth classification instead of regression, we can easily obtain the confidence of a depth prediction in the form of probability distribution. With this confidence, we can apply an information gain loss to make use of the predictions that are close to ground-truth during training, as well as fully-connected conditional random fields for post-processing to further improve the performance. We test our proposed method on both indoor and outdoor benchmark RGB-Depth datasets and achieve state-of-the-art performance. [ABSTRACT FROM AUTHOR]

Nonorthogonal multiple access (NOMA) has been considered as an essential multiple access technique for enhancing system capacity and spectral efficiency in future communication scenarios. However, the existing NOMA systems have a fundamental limit: high computational complexity and a sharply changing wireless channel make exploiting the characteristics of the channel and deriving the ideal allocation methods very difficult tasks. To break this fundamental limit, in this paper, we propose a novel and effective deep learning (DL)-aided NOMA system, in which several NOMA users with random deployment are served by one base station. Since DL is advantageous in that it allows training the input signals and detecting sharply changing channel conditions, we exploit it to address wireless NOMA channels in an end-to-end manner. Specifically, it is employed in the proposed NOMA system to learn a completely unknown channel environment. A long short-term memory (LSTM) network based on DL is incorporated into a typical NOMA system, enabling the proposed scheme to detect the channel characteristics automatically. In the proposed strategy, the LSTM is first trained by simulated data under different channel conditions via offline learning, and then the corresponding output data can be obtained based on the current input data used during the online learning process. In general, we build, train and test the proposed cooperative framework to realize automatic encoding, decoding and channel detection in an additive white Gaussian noise channel. Furthermore, we regard one conventional user activity and data detection scheme as an unknown nonlinear mapping operation and use LSTM to approximate it to evaluate the data detection capacity of DL based on NOMA. Simulation results demonstrate that the proposed scheme is robust and efficient compared with conventional approaches. In addition, the accuracy of the LSTM-aided NOMA scheme is studied by introducing the well-known tenfold cross-validation procedure. [ABSTRACT FROM AUTHOR]

This paper presents a novel garbage pickup robot which operates on the grass. The robot is able to detect the garbage accurately and autonomously by using a deep neural network for garbage recognition. In addition, with the ground segmentation using a deep neural network, a novel navigation strategy is proposed to guide the robot to move around. With the garbage recognition and automatic navigation functions, the robot can clean garbage on the ground in places like parks or schools efficiently and autonomously. Experimental results show that the garbage recognition accuracy can reach as high as 95%, and even without path planning, the navigation strategy can reach almost the same cleaning efficiency with traditional methods. Thus, the proposed robot can serve as a good assistance to relieve dustman’s physical labor on garbage cleaning tasks. [ABSTRACT FROM AUTHOR]

A growing number of multi-view data arises naturally in many scenarios, including medical diagnosis, webpage classification, and multimedia analysis. A challenge in learning from multi-view data is that not all instances are fully represented in all views, resulting in missing view data. In this paper, we focus on feature-level completion for missing view of multi-view data. Aiming at capturing both semantic complementarity and identical distribution among different views, an Isomorphic Linear Correlation Analysis (ILCA) method is proposed to linearly map multi-view data to a feature-isomorphic subspace through learning a set of excellent isomorphic features, thereby unfolding the shared information from different views. Meanwhile, we assume that missing view obeys normal distribution. Then, the missing view data matrix can be modeled as a low-rank component plus a sparse contribution. Thus, to accomplish missing view completion, an Identical Distribution Pursuit Completion (IDPC) model based on the learned features is proposed, in which the identical distribution constraint of missing view to the other available one in the feature-isomorphic subspace is fully exploited. Comprehensive experiments on several multi-view datasets demonstrate that our proposed framework yields promising results. [ABSTRACT FROM AUTHOR]

In this paper, we seek to improve deep neural networks by generalizing the pooling operations that play a central role in the current architectures. We pursue a careful exploration of approaches to allow pooling to learn and to adapt to complex and variable patterns. The two primary directions lie in: (1) learning a pooling function via (two strategies of) combining of max and average pooling, and (2) learning a pooling function in the form of a tree-structured fusion of pooling filters that are themselves learned. In our experiments every generalized pooling operation we explore improves performance when used in place of average or max pooling. We experimentally demonstrate that the proposed pooling operations provide a boost in invariance properties relative to conventional pooling and set the state of the art on several widely adopted benchmark datasets. These benefits come with only a light increase in computational overhead during training (ranging from additional 5 to 15 percent in time complexity) and a very modest increase in the number of model parameters (e.g., additional 1, 9, and 27 parameters for mixed, gated, and 2-level tree pooling operators, respectively). To gain more insights about our proposed pooling methods, we also visualize the learned pooling masks and the embeddings of the internal feature responses for different pooling operations. Our proposed pooling operations are easy to implement and can be applied within various deep neural network architectures. [ABSTRACT FROM PUBLISHER]

Automatic skin lesion segmentation in dermoscopic images is a challenging task due to the low contrast between lesion and the surrounding skin, the irregular and fuzzy lesion borders, the existence of various artifacts, and various imaging acquisition conditions. In this paper, we present a fully automatic method for skin lesion segmentation by leveraging 19-layer deep convolutional neural networks that is trained end-to-end and does not rely on prior knowledge of the data. We propose a set of strategies to ensure effective and efficient learning with limited training data. Furthermore, we design a novel loss function based on Jaccard distance to eliminate the need of sample re-weighting, a typical procedure when using cross entropy as the loss function for image segmentation due to the strong imbalance between the number of foreground and background pixels. We evaluated the effectiveness, efficiency, as well as the generalization capability of the proposed framework on two publicly available databases. One is from ISBI 2016 skin lesion analysis towards melanoma detection challenge, and the other is the PH2 database. Experimental results showed that the proposed method outperformed other state-of-the-art algorithms on these two databases. Our method is general enough and only needs minimum pre- and post-processing, which allows its adoption in a variety of medical image segmentation tasks. [ABSTRACT FROM AUTHOR]

This paper investigates an intriguing question in the remote sensing field: “can a machine generate humanlike language descriptions for a remote sensing image?” The automatic description of a remote sensing image (namely, remote sensing image captioning) is an important but rarely studied task for artificial intelligence. It is more challenging as the description must not only capture the ground elements of different scales, but also express their attributes as well as how these elements interact with each other. Despite the difficulties, we have proposed a remote sensing image captioning framework by leveraging the techniques of the recent fast development of deep learning and fully convolutional networks. The experimental results on a set of high-resolution optical images including Google Earth images and GaoFen-2 satellite images demonstrate that the proposed method is able to generate robust and comprehensive sentence description with desirable speed performance. [ABSTRACT FROM PUBLISHER]

This August issue contains two sets of articles: the Special Issue on Artificial Intelligence: New Frontiers in Real-Time Inverse Scattering and Electromagnetic Imaging and Regular Papers. This Special Issue is motivated by the fact that, in recent years, it has become evident that artificial intelligence provides new innovative solutions for complex problems. Therefore, the Editorial Board of the IEEE Transactions on Antennas and Propagation invited applications for special issues related to how artificial intelligence, machine learning, and deep learning can assist with challenges in the field of antennas and propagation. Three special issues were accepted and this one focuses on a unified vision for the application of artificial intelligence in inverse scattering and electromagnetic imaging. [ABSTRACT FROM AUTHOR]

This June issue contains two sets of articles: the Special Issue on Artificial Intelligence in Radio Propagation for Communications and Regular Papers. This Special Issue is motivated by the fact that in recent years it has become evident that artificial intelligence provides new innovative solutions for complex problems. Therefore, the Editorial Board of the IEEE Transactions on Antennas and Propagation invited applications for special issues related to how artificial intelligence, machine learning, and deep learning can assist with challenges in the field of antennas and propagation. Three special issues were accepted and this one focuses on a unified vision for the application of artificial intelligence in the propagation of electromagnetic waves for applications related to communications. [ABSTRACT FROM AUTHOR]

The papers in this special section present the state-of-the-art technologies and the challenges of parallel and distributed computing techniques for artificial intelligence (AI), machine learning (ML), and deep learning (DL). AI, ML, and DL have established themselves in a multitude of domains because of their ability to process and model unstructured input data. [ABSTRACT FROM AUTHOR]

In recent years, inexact computing has been increasingly regarded as one of the most promising approaches for slashing energy consumption in many applications that can tolerate a certain degree of inaccuracy. Driven by the principle of trading tolerable amounts of application accuracy in return for significant resource savings—the energy consumed, the (critical path) delay, and the (silicon) area—this approach has been limited to application-specified integrated circuits (ASICs) so far. These ASIC realizations have a narrow application scope and are often rigid in their tolerance to inaccuracy, as currently designed; the latter often determining the extent of resource savings we would achieve. In this paper, we propose to improve the application scope, error resilience and the energy savings of inexact computing by combining it with hardware neural networks. These neural networks are fast emerging as popular candidate accelerators for future heterogeneous multicore platforms and have flexible error resilience limits owing to their ability to be trained. Our results in 65-nm technology demonstrate that the proposed inexact neural network accelerator could achieve 1.78– 2.67 \times savings in energy consumption (with corresponding delay and area savings being 1.23 and 1.46 \times , respectively) when compared to the existing baseline neural network implementation, at the cost of a small accuracy loss (mean squared error increases from 0.14 to 0.20 on average). [ABSTRACT FROM PUBLISHER]