Search

The internet of things provides a convenient life for all of us. Physical devices with locational systems connected to the internet can provide navigation and recommendation services in cooperation with the Location Based Services (LBS). The nearest neighbor query is the most common query type in the LBS research area. On the other hand, due to privacy protection or inaccuracies in measurement instructions, data uncertainties are typical in the IoT environment. This uncertainty will affect the results of nearest neighbor queries. The existence of plane obstacles also brings the challenge to the spatial data query. In this paper, the obstacles and data uncertainties in continuous nearest query are studied. We also designed a pruning strategy that significantly reduced the number of objects to be calculated. In addition, we propose a concept of safe region and an algorithm to generate a safe region. We also designed an index method for saving safe regions. The experimental results show that our approach outperforms the state-of-the-art one in efficiency and scalability.

In planetary science, it is an important basic work to recognize and classify the features of topography and geomorphology from the massive data of planetary remote sensing. Therefore, this article proposes a lightweight model based on VGG-16, which can selectively extract some features of remote sensing images, remove redundant information, and recognize and classify remote sensing images. This model not only ensures the accuracy, but also reduces the parameters of the model. According to our experimental results, our model has a great improvement in remote sensing image classification, from the original accuracy of 85%–98% now. At the same time, the model has a great improvement in convergence speed and classification performance. By inputting the remote sensing image data of ultra-low pixels (64 * 64) into our model, we prove that our model still has a high accuracy rate of 95% for the remote sensing image with ultra-low pixels and less feature points. Therefore, the model has a good application prospect in remote sensing image fine classification, very low pixel, and less image classification.

EEG emotion recognition plays a significant role in various mental health services. Deep learning-based methods perform excellently, but still suffer from interpretability. Although methods such as Gradient-weighted Class Activation Mapping(Grad-CAM) can cope with the above problem, their coarse granularity cannot accurately reveal the mechanism to promote emotional intelligence. In this paper, fine-grained interpretability is proposed, called Concat-aided Grad-CAM. Specifically, the multi-level feature mapping before the fully connected layer is concatenated to obtain the gradients of the target concept so that the discriminant information can be directly located in the high-precision area. Unlike coarse-grained interpretability methods applied in EEG emotion recognition, it can accurately highlight the EEG channels related to emotion rather than an obscure area. In addition, a systematic brain functional network is proposed to reveal the relationship between those channels and to further improve emotion recognition performance. The channels with greater contributions are connected, and those connections are learned by dynamic graph convolutional networks, while the others are independent to eliminate interference. Experiments on four EEG emotion recognition datasets manifest that Concat-aided Grad-CAM can be interpreted by the fine-grained. In addition, it has been shown that the learned brain functional network can improve the performance of the baselines. Significantly, the experiment results achieve state-of-the-art performance in multiple experiments. [ABSTRACT FROM AUTHOR]

When a multi-modal affective analysis model generalizes from a bimodal task to a trimodal or multi-modal task, it is usually transformed into a hierarchical fusion model based on every two pairwise modalities, similar to a binary tree structure. This easily leads to large growth in model parameters and computation as the number of modalities increases, which limits the model's generalization. Moreover, many multi-modal fusion methods ignore that different modalities contribute differently to affective analysis. To tackle these challenges, this article proposes a general multi-modal fusion model that supports trimodal or multi-modal affective analysis tasks, called Multi-modal Interactive Attention Network (MIA-Net). Instead of treating different modalities equally, MIA-Net takes the modality that contributes the most to emotion as the main modality and the others as auxiliary modalities. MIA-Net introduces multi-modal interactive attention modules to adaptively select the important information of each auxiliary modality one by one to improve the main-modal representation. Moreover, MIA-Net enables quick generalization to trimodal or multi-modal tasks through stacking multiple MIA modules, which maintains efficient training and only requires linear computation and stable parameter counts. Experimental results of the transfer, generalization, and efficiency experiments on the widely-used datasets demonstrate the effectiveness and generalization of the proposed method. [ABSTRACT FROM AUTHOR]

Under the multiscale distribution, due to dramatic aspect ratio variance leading to prominent arbitrary-oriented character of ships in very high-resolution (VHR) optical remote sensing imagery, how to generate accurate oriented bounding box (OBB) becomes a hot research topic for arbitrary-oriented ship detection. Consequently, in this letter, a concise and effective one-stage anchor-free contour modeling detector called CMDet is proposed for accurate arbitrary-oriented ship detection. Different from currently existed methods via carefully decoupling several independently characteristic parameters for OBB modeling and regression, we resolve the OBB modeling by jointly regressing the contour information. Specifically, the contour information is expressed as a series of Fourier transform coefficients, which are generated by setting up the mapping relation of 1-D Fourier contour coefficients and spatial OBB contour. In addition, a new inherent geometry loss is designed to make detector better learn the geometry information in training phase. After that, the proposed CMDet only needs to predict the correct center point of ships and regress the corresponding entire 1-D Fourier contour coefficients to generate accurate OBB for ship detection. Finally, extensive experiments are carried out on two public OBB ship detection datasets (e.g., HRSC2016 and DIOR-ship), and comparison results demonstrate that the proposed CMDet can obtain the competitive result than the state-of-the-art (SOTA) detectors. [ABSTRACT FROM AUTHOR]

Graph convolutional neural network (GCN) has effectively boosted the multi-label image recognition task by modeling correlation among labels. In previous methods, label correlation is computed based on statistical information through label diffusion, and therefore the same for all samples. This, however, makes graph inference on labels insufficient to handle huge variations among numerous image instances. In this paper, we propose an instance-aware graph convolutional neural network (IA_GCN) framework for the multi-label classification. As a whole, two fused branches of sub-networks are involved in the framework: a global branch modeling the whole image and a local branch exploring dependencies among regions of interests (ROIs). For both the branches, an image-dependent label correlation matrix (ID_LCM), fusing both the statistical label correlation matrix (LCM) and an individual one of each image instance, is constructed to inject adaptive information of label-awareness into the learned features of the model through graph convolution. Specifically, the individual LCM of each image is obtained by mining the label dependencies based on the predicted label scores of those detected ROIs. In this process, considering the contribution differences of ROIs to multi-label classification, variational inference is introduced to learn adaptive scaling factors for those ROIs by considering their complex distribution. Finally, extensive experiments on MS-COCO and VOC datasets show that our proposed approach outperforms existing state-of-the-art methods. [ABSTRACT FROM AUTHOR]

This article presents a structure constraint matrix factorization framework for different behavior segmentation of the human behavior sequential data. This framework is based on the structural information of the behavior continuity and the high similarity between neighboring frames. Due to the high similarity and high dimensionality of human behavior data, the high-precision segmentation of human behavior is hard to achieve from the perspective of application and academia. By making the behavior continuity hypothesis, first, the effective constraint regular terms are constructed. Subsequently, the clustering framework based on constrained non-negative matrix factorization is established. Finally, the segmentation result can be obtained by using the spectral clustering and graph segmentation algorithm. For illustration, the proposed framework is applied to the Weiz dataset, Keck dataset, mo_86 dataset, and mo_86_9 dataset. Empirical experiments on several public human behavior datasets demonstrate that the structure constraint matrix factorization framework can automatically segment human behavior sequences. Compared to the classical algorithm, the proposed framework can ensure consistent segmentation of sequential points within behavior actions and provide better performance in accuracy. [ABSTRACT FROM AUTHOR]

In this study, a flexible capacitive pressure sensor based on filter paper substrate is proposed. The electric double layer (EDL) structure was constructed through the introduction of ionic liquid (IL), and the pressure-sensing was realized by using the change of ion-electron interface contact. The paper-based iontronic pressure sensor possesses a high sensitivity of 221.9 kPa−1, which is hundreds of times higher than that of the capacitive pressure sensors with conventional parallel plate structure, as well as an ultra-low detection limit of 2 Pa. The sensor exhibits an enormous application potential in healthcare wearable electronics and human-machine interface equipment. [ABSTRACT FROM AUTHOR]

A preliminary system for microwave thorax imaging is designed and experiments are conducted. A compact low-profile symmetrical dipole antenna operating at 915 MHz is designed for the system. An acrylic rectangular box is fabricated as the experiment phantom to mimic an ordinary human thorax. Graduated cylinders with different diameters are used as imaging targets. During measurement, each antenna acts in turn as a transmitter and other antennas act as the receivers. One-step supervised descent method (SDM) is adopted as the imaging algorithm. Results under different scenarios indicate that structural information can be reconstructed with the one-step SDM. This study verifies the feasibility of microwave thorax imaging. [ABSTRACT FROM AUTHOR]

In this work, strongly hydrophilic ionic liquid (IL) was introduced into the metal organic frameworks (MOFs) by the solvent-assisted linker exchange (SALE) method. Low humidity sensors based on IL functionalized MOF-801 materials were prepared. The as-prepared sensor shows a high response of 20.3 (in the humidity range of 0% RH to 35% RH, 0 ppmv to 8138 ppmv), small hysteresis (~1% RH) and good long-term stability (>100 days). In particular, the optimized sensor shows fast response (~400 ms) and high resolution (1% RH). This work provides a potential humidity sensitive material for preparing high performance low humidity sensors. [ABSTRACT FROM AUTHOR]

Semantic segmentation plays a critical role in scene understanding for self-driving vehicles. A line of efforts has proven that global context matters in urban scene segmentation due to massive scale changes. However, we find that existing methods suffer from local ambiguities when dissipating continuous local context, i.e. scrambling to a huge receptive field of global cues by coarse pooling. To this end, this paper proposes a new Context Aggregation Module (CAM) that consists of two primary components: context encoding using no coarse pooling but encoder-decoders with appropriate sampling scales and gated fusion that extends gate attention mechanism to balance different-scale context during feature fusion. Weeding out coarse pooling and applying the encoder-decoder inherits the merits of exploring global context while avoiding the drawback of losing local contextual continuity. We then construct a Context Aggregation Network (CANet) and conduct extensive evaluations on challenging autonomous driving benchmarks of Cityscapes, CamVid and BDD100K. Consistently improved results evidence the effectiveness. Notably, we attain competitive mIoU 82.7% on Cityscapes and optimal mIoU 80.5% on CamVid. [ABSTRACT FROM AUTHOR]

In recent years, the appearance of the broad learning system (BLS) is poised to revolutionize conventional artificial intelligence methods. It represents a step toward building more efficient and effective machine-learning methods that can be extended to a broader range of necessary research fields. In this survey, we provide a comprehensive overview of the BLS in data mining and neural networks for the first time, focusing on summarizing various BLS methods from the aspects of its algorithms, theories, applications, and future open research questions. First, we introduce the basic pattern of BLS manifestation, the universal approximation capability, and essence from the theoretical perspective. Furthermore, we focus on BLS’s various improvements based on the current state of the theoretical research, which further improves its flexibility, stability, and accuracy under general or specific conditions, including classification, regression, semisupervised, and unsupervised tasks. Due to its remarkable efficiency, impressive generalization performance, and easy extendibility, BLS has been applied in different domains. Next, we illustrate BLS’s practical advances, such as computer vision, biomedical engineering, control, and natural language processing. Finally, the future open research problems and promising directions for BLSs are pointed out. [ABSTRACT FROM AUTHOR]

Road link speed is often employed as an essential measure of traffic state in the operation of an urban traffic network. Not only real-time traffic demand but also signal timings and other local planning factors are major influential factors. This paper proposes a short-term traffic speed prediction approach, called PL-WGAN, for urban road networks, which is considered an important part of a novel parallel learning framework for traffic control and operation. The proposed method applies Wasserstein Generative Adversarial Nets (WGAN) for robust data-driven traffic modeling using a combination of generative neural network and discriminative neural network. The generative neural network models the road link features of the adjacent intersections and the control parameters of intersections using a hybrid graph block. In addition, the spatial-temporal relations are captured by stacking a graph convolutional network (GCN), a recurrent neural network (RNN), and an attention mechanism. A comprehensive computational experiment was carried out including comparing model prediction and computational performances with several state-of-the-art deep learning models. The proposed approach has been implemented and applied for predicting short-term link traffic speed in a large-scale urban road network in Hangzhou, China. The results suggest that it provides a scalable and effective traffic prediction solution for urban road networks. [ABSTRACT FROM AUTHOR]

Missing data imputation is an essential component of a robust traffic surveillance system. Despite the progress of data imputation technologies in intelligent transportation systems (ITS), only limited efforts have been devoted to tackling data missing issues on signalized roads, which present distinct missing patterns due to the effect of traffic signal timing on traffic flow. Unlike most studies that try to impute missing data at the granularity of road segment and aggregated time intervals, we impute missing data for individual traffic lanes at the granularity of signal cycle. We develop a data-driven fine-grained imputation approach based on a novel gated attentional generative adversarial network (GaGAN), which is highly responsive to the dynamic traffic environments of signalized road networks. The advantage of the network lies in that it can automatically learn inter-lane spatio-temporal correlations during each signal cycle. To model the spatial correlations, we jointly leverage spatial attention mechanisms and graph convolutional operations to quantify inter-lane influences within each signal cycle. To model the temporal correlations, we propose to integrate self-attention mechanisms into gated recurrent units (termed as SA-GRU). Two sub-discriminators are developed to model lane-level complete and missing data distributions, respectively, with the goal to improve the consistency between imputed data and overall data distribution. Experimental results demonstrate that the proposed approach is superior to other state-of-the-art methods, achieving robust performance over different data missing types. [ABSTRACT FROM AUTHOR]

The analysis of over-parameterized neural networks has drawn significant attention in recent years. It was shown that such systems behave like convex systems under various restricted settings, such as for two-layer neural networks, and when learning is only restricted locally in the so-called neural tangent kernel space around specialized initializations. However, there is a lack of powerful theoretical techniques that can analyze fully trained deep neural networks under general conditions. This paper considers this fundamental problem by investigating such overparameterized deep neural networks when fully trained. Specifically, we characterize a deep neural network by its features’ distributions and propose a metric to intuitively measure the usefulness of feature representations. Under certain regularizers that bounds the metric, we show deep neural networks can be reformulated as a convex optimization and the system can guarantee effective feature representations in terms of the metric. Our new analysis is more consistent with empirical observations that deep neural networks are capable of learning efficient feature representations. Empirical studies confirm that predictions of our theory are consistent with results observed in practice. [ABSTRACT FROM AUTHOR]

Sentiment analysis uses a series of automated cognitive methods to determine the author’s or speaker’s attitudes toward an expressed object or text’s overall emotional tendencies. In recent years, the growing scale of opinionated text from social networks has brought significant challenges to humans’ sentimental tendency mining. The pretrained language model designed to learn contextual representation achieves better performance than traditional learning word vectors. However, the existing two basic approaches for applying pretrained language models to downstream tasks, feature-based and fine-tuning methods, are usually considered separately. What is more, different sentiment analysis tasks cannot be handled by the single task-specific contextual representation. In light of these pros and cons, we strive to propose a broad multitask transformer network (BMT-Net) to address these problems. BMT-Net takes advantage of both feature-based and fine-tuning methods. It was designed to explore the high-level information of robust and contextual representation. Primarily, our proposed structure can make the learned representations universal across tasks via multitask transformers. In addition, BMT-Net can roundly learn the robust contextual representation utilized by the broad learning system due to its powerful capacity to search for suitable features in deep and broad ways. The experiments were conducted on two popular datasets of binary Stanford Sentiment Treebank (SST-2) and SemEval Sentiment Analysis in Twitter (Twitter). Compared with other state-of-the-art methods, the improved representation with both deep and broad ways is shown to achieve a better $F1$ -score of 0.778 in Twitter and accuracy of 94.0% in the SST-2 dataset, respectively. These experimental results demonstrate the abilities of recognition in sentiment analysis and highlight the significance of previously overlooked design decisions about searching contextual features in deep and broad spaces. [ABSTRACT FROM AUTHOR]

This work proposes humidity sensors based on ionic liquid loaded in situ crosslinked ionogels. Stable ionogels were constructed by the synergistic effect of k-carrageenan and gelatin to ensure the uniformly dispersion of ionic liquid, which is conducive to the stability of humidity sensors. The humidity sensitive electrolyte with different contents were introduced into the ionogels. By controlling the ratio of ionic liquid in the crosslinked ionogels, the optimal sensor exhibits a high sensitivity in the low humidity range (5% - 35% RH). The resultant sensors exhibit excellent repeatability, and possess good stability in long-term tests up to 60 days. The introduction of ionic liquid to the sensing film is beneficial for enhancing the water adsorption capacity and ionic conductivity, which is of great significance for high-performance humidity sensors. [ABSTRACT FROM AUTHOR]

Reducing uplift payments has been a challenging problem for most wholesale markets in the U.S. The main difficulty comes from the discrete decision-making and non-linear objective function in the unit commitment (UC) problem. Recently, the convex hull pricing approach has shown promises to reduce the uplift payments, in which efficient algorithms are available when i) the convex hull description for each unit and ii) the convex envelope for the objective function are available. Following this framework, in this paper, we provide network-flow-based compact extended formulations for each UC considering ramping constraints, different initial statuses, and maximum start-up restrictions. Meanwhile, by using a piece-wise linear approximation of a quadratic cost curve in the objective function, we show that the corresponding piece-wise linear convex envelope converges to the quadratic envelope as the number of pieces increases in the convex hull pricing problem. The final computational experiments on a revised IEEE 118-bus system indicates the effectiveness of the proposed approach. The trade-off between the cost-saving and computational time improvement is also reported as a reference for further usage. [ABSTRACT FROM AUTHOR]

In intelligent driving, situational assessment (SA) is an important technology, which helps to improve the cognitive ability of intelligent vehicles in the environment. Uncertainty analysis is very significant in situation assessment. This article proposes an SA method based on uncertainty risk analysis. Under uncertain conditions, according to the random environment model and Gaussian distribution model, the collision probability between multiple vehicles is estimated by comprehensive trajectory prediction. The proposed method considers collision probabilities of different prediction points within and outside the prediction range and obtains long-term accurate prediction results. The method is suitable for the situation risk assessment of sensor systems in the presence of unexpected dynamic obstacles, sensor failures or communication losses in traffic, and different environmental sensing accuracy. The experimental results show that in the dynamic traffic environment, the proposed scenario assessment method can not only accurately predict and assess the situation risks within the prediction range, but also provide accurate scenario risk assessment outside the prediction range. [ABSTRACT FROM AUTHOR]

Cross-database micro-expression recognition (CDMER) is one of recently emerging and interesting problem in micro-expression analysis. CDMER is more challenging than the conventional micro-expression recognition (MER), because the training and testing samples in CDMER come from different micro-expression databases, resulting in inconsistency of the feature distributions between the training and testing sets. In this paper, we contribute to this topic from three aspects. First, we establish a CDMER experimental evaluation protocol aiming to allow the researchers to conveniently work on this topic and evaluate their proposed methods under the same standard. Second, we conduct benchmark experiments by using NINE state-of-the-art domain adaptation (DA) methods and SIX popular spatiotemporal descriptors for investigating CDMER problem from two different perspectives. Third, we propose a novel DA method called region selective transfer regression (RSTR) to deal with the CDMER task. The overall superior performance of RSTR over the state-of-the-art DA methods demonstrates that taking into consideration the facial local region information used in RSTR contributes to developing effective DA methods for dealing with CDMER problem. [ABSTRACT FROM AUTHOR]

The traditional collaborative fuzzy clustering can effectively perform data clustering in distributed peer-to-peer networks, which is an impossible task to complete for the centralized clustering methods due to privacy and security requirements or network transmission technology constraints. But it will increase the number of clustering iterations and lead to lower efficiency of the clustering. Moreover, the collaborative mechanism hidden in the iterative process of clustering cannot be well revealed and explained. In this article, a novel series of transfer collaborative fuzzy clustering algorithms are proposed to solve these issues. In the first basic algorithm, the transfer learning among neighbor nodes vividly expresses the collaborative mechanism and enhances the information collaboration to accelerate the convergence of fuzzy clustering. Meanwhile, neighbor nodes can learn the knowledge from each other to further promote their respective clustering performance. Then, an improved version, with the learning-rate-adjustable strategy instead of fixed values, is designed to highlight the different influence between neighbor nodes, and the appropriate learning rates between neighbor nodes are achieved to ensure the stable clustering accuracy. Finally, two extended versions with the attribute-weight-entropy regularization technique are presented for the clustering of high dimensional sparse data and the extraction of important subspace features. Experiments show the efficiency of the proposed algorithms compared with the related prototype-based clustering methods. [ABSTRACT FROM AUTHOR]

Scalable video coding (SVC) has received much attention for video transmission over wireless due to its flexibility. However, most previous work only considered SVC video streaming from a single base station (BS). At present, the densification of BSs enables a user equipment (UE) to connect to multiple BSs in ultra-dense networks (UDNs). In this paper, we consider the problem of SVC video streaming in a UDN, which allows different layers of a video block to be downloaded from different BSs. An optimization problem is formulated aiming to maximize the quality of experience (QoE) of users by selecting the optimal connection strategy and optimal number of video layers. Considering the complexity, to efficiently solve the problem in a distributed manner, the problem of choosing connection strategy is formulated as a multi-agent multi-armed bandit (MA-MAB) problem with only few information exchange. Each user can adapt its connection strategy in a distributed self-learning system. To obtain the optimal arm for the MA-MAB problem, we propose a multi-user arm decision algorithm. To avoid large computation and handover costs, we adopt the same connection strategy for the entire video sequence. Then for each video block, with the given connection strategy, the number of video layers is adjusted adaptively according to dynamic network conditions. Finally, based on the above designs, we provide the SVC-based video downloading scheme to obtain an approximate optimal solution to the original optimization problem. Extensive simulations and comparisons show the feasibility and superiority of the proposed scheme. [ABSTRACT FROM AUTHOR]

Human perception is of great research and application value. Thermopile infrared array sensor (TPAS) is an available solution without privacy invasion. In specific indoor environment like apartment and office, there are inevitable interfering thermal sources except human. Extracting human from the dynamically changing background i.e. background removal is a critical process. Based on the hardware platform built by a thermopile infrared array sensor MLX90640 with an output of ${24}\times {32}$ pixels, this paper proposes an adaptive Gaussian background removal algorithm applying a priori map (AGBR-PM) for indoor single human perception. For each static thermal source, an a priori map is established containing its location and thermal radiation feature in the way of support degree matrix. We build a Gaussian background model consisting of mean and standard deviation matrix. Each frame of thermal image is segmented into foreground and background based on $2\sigma $ rule. A state and cross detection algorithm is proposed to compensate the error caused by interfering static thermal sources, and an erosion-connected component analysis and foreground complement algorithm is adopted to reduce the random noise as well. A regional update strategy is designed to adapt to the emergence of random thermal sources in background. The experimental results have shown that AGBR-PM has an excellent adaptability to dynamically changing environment, and can remove the background correctly. [ABSTRACT FROM AUTHOR]

In recent years, emotion recognition has become a research focus in the area of artificial intelligence. Due to its irregular structure, EEG data can be analyzed by applying graphical based algorithms or models much more efficiently. In this work, a Graph Convolutional Broad Network (GCB-net) was designed for exploring the deeper-level information of graph-structured data. It used the graph convolutional layer to extract features of graph-structured input and stacks multiple regular convolutional layers to extract relatively abstract features. The final concatenation utilized the broad concept, which preserves the outputs of all hierarchical layers, allowing the model to search features in broad spaces. To improve the performance of the proposed GCB-net, the broad learning system (BLS) was applied to enhance its features. For comparison, two individual experiments were conducted to examine the efficiency of the proposed GCB-net based on the SJTU emotion EEG dataset (SEED) and DREAMER dataset respectively. In SEED, compared with other state-of-art methods, the GCB-net could better promote the accuracy (reaching 94.24 percent) on the DE feature of the all-frequency band. In DREAMER dataset, GCB-net performed better than other models with the same setting. Furthermore, the GCB-net reached high accuracies of 86.99, 89.32 and 89.20 percent on dimensions of Valence, Arousal and Dominance respectively. The experimental results showed the robust classifying ability of the GCB-net and BLS in EEG emotion recognition. [ABSTRACT FROM AUTHOR]

Flexible pressure sensor with excellent sensing performance and wearability is a major research focus for wearable electronic devices. In this study, polyporrole (PPy) wrapped cotton pads and silver coated wrinkle papers are stacked together to construct a novel piezoresistive sensor, and a bimaterial conductivity-conversion mechanism is presented. The PPy-cotton pads are prepared by an in-situ vapor growth process to ensure the strong adhesion and uniform distribution of PPy, which is beneficial for the stability of pressure sensors. The optimal flexible pressure sensor exhibits fast response speed (about 50 ms) and ultra-low detection limit (0.09 Pa). The potential applications of sensors as wearable e-skin for human activity and physiological signals monitoring are also demonstrated. [ABSTRACT FROM AUTHOR]

Neural architecture search (NAS) is a challenging problem in the design of deep learning due to its nonconvexity. To address this problem, an adaptive scalable NAS method (AS-NAS) is proposed based on the reinforced I-Ching divination evolutionary algorithm (IDEA) and variable-architecture encoding strategy. First, unlike the typical reinforcement learning (RL)-based and evolutionary algorithm (EA)-based NAS methods, a simplified RL algorithm is developed and used as the reinforced operator controller to adaptively select the efficient operators of IDEA. Without the complex actor–critic parts, the reinforced IDEA based on simplified RL can enhance the search efficiency of the original EA with lower computational cost. Second, a variable-architecture encoding strategy is proposed to encode neural architecture as a fixed-length binary string. By simultaneously considering variable layers, channels, and connections between different convolution layers, the deep neural architecture can be scalable. Through the integration with the reinforced IDEA and variable-architecture encoding strategy, the design of the deep neural architecture can be adaptively scalable. Finally, the proposed AS-NAS are integrated with the ${L}_{1/2}$ regularization to increase the sparsity of the optimized neural architecture. Experiments and comparisons demonstrate the effectiveness and superiority of the proposed method. [ABSTRACT FROM AUTHOR]

These days, physiological signals have been studied more broadly for emotion recognition to realize emotional intelligence in human–computer interaction. However, due to the complexity of emotions and individual differences in physiological responses, how to design reliable and effective models has become an important issue. In this article, we propose a regularized deep fusion framework for emotion recognition based on multimodal physiological signals. After extracting the effective features from different types of physiological signals, we construct ensemble dense embeddings of multimodal features using kernel matrices, and then utilize a deep network architecture to learn task-specific representations for each kind of physiological signal from these ensemble dense embeddings. Finally, a global fusion layer with a regularization term, which can efficiently explore the correlation and diversity among all of the representations in a synchronous optimization process, is designed to fuse generated representations. Experiments on two benchmark datasets show that this framework can improve the performance of subject-independent emotion recognition compared to single-modal classifiers or other fusion methods. Data visualization also demonstrates that the final fusion representation exhibits higher class-separability power for emotion recognition. [ABSTRACT FROM AUTHOR]

Memcached is a widely used in-memory caching solution in large-scale searching scenarios. The most crucial metric of Memcached systems is the response time, which is affected by various factors such as workload, service rate, unbalanced load distribution, and cache miss ratio. This article aims to quantify the influence of each factor on the response time of Memcached systems. First, we establish a theoretical model for Memcached systems that captures their main features, including burst and concurrent key arrival, unbalanced load distribution, and cache miss process. By solving this model using queuing and stochastic theories, we obtain an estimate of the response time in Memcached systems. Intensive experiments based on real-world components demonstrate that the estimate always matches perfectly with the actual value. Furthermore, we obtain a comprehensive and quantitative understanding of all factors. The main insights are threefold. 1) There exists an optimum range of utilization at Memcached servers in which the response time is kept at a low level with a small penalty. 2) The influence of the cache miss ratio on the response time is logarithmic rather than linear. 3) The number of keys generated from an end-user request has the greatest impact in Memcached systems. [ABSTRACT FROM AUTHOR]

The advances made in predicting visual saliency using deep neural networks come at the expense of collecting large-scale annotated data. However, pixel-wise annotation is labor-intensive and overwhelming. In this paper, we propose to learn saliency prediction from a single noisy labelling, which is easy to obtain (e.g., from imperfect human annotation or from unsupervised saliency prediction methods). With this goal, we address a natural question: Can we learn saliency prediction while identifying clean labels in a unified framework? To answer this question, we call on the theory of robust model fitting and formulate deep saliency prediction from a single noisy labelling as robust network learning and exploit model consistency across iterations to identify inliers and outliers (i.e., noisy labels). Extensive experiments on different benchmark datasets demonstrate the superiority of our proposed framework, which can learn comparable saliency prediction with state-of-the-art fully supervised saliency methods. Furthermore, we show that simply by treating ground truth annotations as noisy labelling, our framework achieves tangible improvements over state-of-the-art methods. [ABSTRACT FROM AUTHOR]

The task of video object segmentation is a fundamental but challenging problem in the field of computer vision. To deal with large variations in target objects and background clutter, we propose an online adaptive video object segmentation (VOS) framework, named Meta-VOS, that learns to adapt the target-specific segmentation. Meta-VOS builds an online adaptive learning process by exploiting cumulative expertise after searching for confidence patterns across different videos/frames, and then dynamically improves the model learning from two aspects: Meta-seg learner (i.e., module updating) and Meta-seg criterion (i.e., rule of expertise). As our goal is to rapidly determine which patterns best represent the essential characteristics of specific targets in a video, Meta-seg learner is introduced to adaptively learn to update the parameters and hyperparameters of segmentation network in very few gradient descent steps. Furthermore, a Meta-seg criterion of learned expertise, which is constructed to evaluate the Meta-seg learner for the online adaptation of the segmentation network, can confidently online update positive/negative patterns under the guidance of motion cues, object appearances and learned knowledge. Comprehensive evaluations on several benchmark datasets demonstrate the superiority of our proposed Meta-VOS when compared with other state-of-the-art methods applied to the VOS problem. [ABSTRACT FROM AUTHOR]

Vehicle detection in aerial images is an important and challenging task in the field of remote sensing. Recently, deep learning technologies have yielded superior performance for object detection in remote sensing images. However, the detection results of the existing methods are horizontal bounding boxes that ignore vehicle orientations, thereby having limited applicability in scenes with dense vehicles or clutter backgrounds. In this article, we propose a one-stage, anchor-free detection approach to detect arbitrarily oriented vehicles in high-resolution aerial images. The vehicle detection task is transformed into a multitask learning problem by directly predicting high-level vehicle features via a fully convolutional network. That is, a classification subtask is created to look for vehicle central points and three regression subtasks are created to predict vehicle orientations, scales, and offsets of vehicle central points. First, coarse and fine feature maps outputted from different stages of a residual network are concatenated together by a feature pyramid fusion strategy. Upon the concatenated features, four convolutional layers are attached in parallel to predict high-level vehicle features. During training, task uncertainty learned from the training data is used to weight loss function in the multitask learning setting. For inferencing, oriented bounding boxes are generated using the predicted vehicle features, and oriented nonmaximum suppression (NMS) postprocessing is used to reduce redundant results. Experiments on two public aerial image data sets have shown the effectiveness of the proposed approach. [ABSTRACT FROM AUTHOR]

Convex hull pricing has been introduced recently to increase transparency and reduce uplift payments for the U.S. wholesale markets. A convex primal formulation approach is one of the most efficient methods to obtain a high-quality convex hull price. Even though significant progress has been made, the co-optimization of energy and ancillary services is much more challenging due to the discrete nature in formulating ancillary services, for example, the regulating reserve commitment variables, which are binary introduced by some Independent System Operators (ISOs), such as Midcontinent ISO (MISO), to capture the special characteristics of certain generators, such as combined-cycle units. In this paper, we propose convex primal formulations for convex hull pricing considering regulating, spinning, and online/offline-supplemental reserves, in which the regulating reserve commitment variables are considered. Accordingly, we can solve a linear program, instead of a mixed-integer program, which is much harder to solve, to derive the minimum uplift payments and exact convex hull price for the case without general ramping constraints. For the case with general ramping constraints, an upper bound of the minimum uplift payment can also be derived. The final computational experiments on MISO cases verify the effectiveness of our approach in solution quality and computational time. [ABSTRACT FROM AUTHOR]

Deep learning has received considerable empirical success in recent years. However, while many ad hoc tricks have been discovered by practitioners, until recently, there has been a lack of theoretical understanding for tricks invented in the deep learning literature. Known by practitioners that overparameterized neural networks (NNs) are easy to learn, in the past few years, there have been important theoretical developments in the analysis of overparameterized NNs. In particular, it was shown that such systems behave like convex systems under various restricted settings, such as for two-layer NNs, and when learning is restricted locally in the so-called neural tangent kernel space around specialized initializations. This article discusses some of these recent signs of progress leading to a significantly better understanding of NNs. We will focus on the analysis of two-layer NNs and explain the key mathematical models, with their algorithmic implications. We will then discuss challenges in understanding deep NNs and some current research directions. [ABSTRACT FROM AUTHOR]

For the two-user multiple-input multiple-output (MIMO) broadcast channel with delayed channel state information at the transmitter (CSIT) and arbitrary antenna configurations, all the degrees-of-freedom (DoF) regions are obtained. However, for the three-user MIMO broadcast channel with delayed CSIT and arbitrary antenna configurations, the DoF region of order-2 messages is still unclear and only a partial achievable DoF region of order-1 messages is obtained, where the order-2 messages and order-1 messages are desired by two receivers and one receiver, respectively. In this paper, for the three-user MIMO broadcast channel with delayed CSIT and arbitrary antenna configurations, we first design transmission schemes for order-2 messages and order-1 messages. Next, we propose to analyze the achievable DoF region of transmission scheme by transformation approach. In particular, we transform the decoding condition of transmission scheme w.r.t. phase duration into the achievable DoF region w.r.t. achievable DoF, through achievable DoF tuple expression connecting phase duration and achievable DoF. As a result, the DoF region of order-2 messages is characterized and an achievable DoF region of order-1 messages is completely expressed. Besides, for order-1 messages, we derive the sufficient condition, under which the proposed achievable DoF region is the DoF region. [ABSTRACT FROM AUTHOR]

In this paper, an online foot position compensator (FPC) is proposed for improving the robustness of humanoid walking based on orbital energy conservation and discrete control Lyapunov function (DCLF), with which the asymptotic stability of the humanoid system can be maintained and, thus, the foot placement control is achieved. The online FPC is developed based on linear model predictive control (MPC) by replanning the trajectories of the center of mass (CoM) and properly placing the footsteps to resist external disturbances and recover the walking posture. To further improve the robustness of the humanoid robots to suppress strong external disturbance, a strategy of upper body posture control is proposed. The presented controller stabilizes the humanoid robot by utilizing hip joints to modulate the upper body posture online. Webots simulations and real experiments on a full-body NAO humanoid robot verify the effectiveness of the proposed methods. [ABSTRACT FROM AUTHOR]

Two new dynamic-state switching phenomena are experimentally observed in a vertical-cavity surface-emitting laser with polarization-preserved external-cavity optical feedback. One is switching between a steady state and a quasi-periodic state, and the other is switching between two different steady states. Both switching phenomena occur in the same polarization and the switching period is equal to the round-trip time in the external feedback cavity. The evolution of the two switching phenomena is experimentally investigated in detail. This work not only enriches the understanding of laser nonlinear dynamics but also provides an all-optical alternative for generation of special signals for possible applications. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel neural network model, called bi-hemisphere domain adversarial neural network (BiDANN) model, for electroencephalograph (EEG) emotion recognition. The BiDANN model is inspired by the neuroscience findings that the left and right hemispheres of human's brain are asymmetric to the emotional response. It contains a global and two local domain discriminators that work adversarially with a classifier to learn discriminative emotional features for each hemisphere. At the same time, it tries to reduce the possible domain differences in each hemisphere between the source and target domains so as to improve the generality of the recognition model. In addition, we also propose an improved version of BiDANN, denoted by BiDANN-S, for subject-independent EEG emotion recognition problem by lowering the influences of the personal information of subjects to the EEG emotion recognition. Extensive experiments on the SEED database are conducted to evaluate the performance of both BiDANN and BiDANN-S. The experimental results have shown that the proposed BiDANN and BiDANN models achieve state-of-the-art performance in the EEG emotion recognition. [ABSTRACT FROM AUTHOR]

To alleviate the backhaul congestion in future hybrid heterogenous networks, this paper investigates the potential benefits of implementing storages in small base stations (SBSs) operating at frequency range 2 (FR2) bands that co-exist with a tier of massive multiple input multiple output (MIMO) macro BSs (MBSs) operating at frequency range 1 (FR1) bands. We develop a unified analytical framework and derive theoretical bounds for such a cache-enabled FR1–FR2 hybrid network under limited backhaul scenario to analyze the exact and approximate latency, average success probability of file delivery, and average data rate considering two open-access user association policies: i) location-based and ii) content-based association. Numerical results demonstrate that wireless edge caching (WEC) can improve the performance of hybrid wireless networks, albeit certain trade-offs, e.g., increasing cache-enabled SBSs cannot always improve the network performance and there exists an optimal SBS density that provides the best latency and throughput performance. Furthermore, we compare the performance of the network with respect to other key network design parameters such as cache size, content popularity, backhaul capacity, and blockages for both the user associations. Our results show that latency under content-based user association is less than that of location-based user association, and although the difference in the average rates under the two user associations is not obvious, content-based association can extricate more backhaul capacity and thus reduce installation cost significantly. [ABSTRACT FROM AUTHOR]

In lifelong machine learning (LML) systems, consecutive new tasks from changing circumstances are learned and added to the system. However, sufficiently labeled data are indispensable for extracting intertask relationships before transferring knowledge in classical supervised LML systems. Inadequate labels may deteriorate the performance due to the poor initial approximation. In order to extend the typical LML system, we propose a novel hierarchical lifelong learning algorithm (HLLA) consisting of two following layers: 1) the knowledge layer consisted of shared representations and integrated knowledge basis at the bottom and 2) parameterized hypothesis functions with features at the top. Unlabeled data is leveraged in HLLA for pretraining of the shared representations. We also have considered a selective inherited updating method to deal with intertask distribution shifting. Experiments show that our HLLA method outperforms many other recent LML algorithms, especially when dealing with higher dimensional, lower correlation, and fewer labeled data problems. [ABSTRACT FROM AUTHOR]

Generative adversarial networks (GAN) are trained through a minimax game between a generator and a discriminator to generate data that mimics observations. While being widely used, GAN training is known to be empirically unstable. This paper presents a new theory for generative adversarial methods that does not rely on the traditional minimax formulation. Our theory shows that with a strong discriminator, a good generator can be obtained by composite functional gradient learning, so that several distance measures (including the KL divergence and the JS divergence) between the probability distributions of real data and generated data are simultaneously improved after each functional gradient step until converging to zero. This new point of view leads to stable procedures for training generative models. It also gives a new theoretical insight into the original GAN. Empirical results on image generation show the effectiveness of our new method. [ABSTRACT FROM AUTHOR]

The broad learning system (BLS) has been proved to be effective and efficient lately. In this article, several deep variants of BLS are reviewed, and a new adaptive incremental structure, Stacked BLS, is proposed. The proposed model is a novel incremental stacking of BLS. This invariant inherits the efficiency and effectiveness of BLS that the structure and weights of lower layers of BLS are fixed when the new blocks are added. The incremental stacking algorithm computes not only the connection weights between the newly stacking blocks but also the connection weights of the enhancement nodes within the BLS block. The Stacked BLS is considered as the increment of “layers” and “neurons” dynamically during the training for multilayer neural networks. The proposed architecture along with the training algorithms that utilizes the residual characteristic is very versatile in comparison with traditional fixed architecture. Finally, experimental results on UCI datasets, MNIST dataset, NORB dataset, CIFAR-10 dataset, SVHN dataset, and CIFAR-100 dataset indicate that the proposed method outperforms the selected state-of-the-art methods on both accuracy and training speed, such as deep residual networks. The results also imply that the proposed structure could highly reduce the number of nodes and the training time of the original BLS in the classification task of some datasets. [ABSTRACT FROM AUTHOR]

In this paper, we will investigate skeleton-based action recognition by employing high-order statistics feature and first-order statistics feature, where the high-order statistics feature is characterized by symmetric positive definite (SPD) matrices. Noting that SPD matrices are theoretically embedded on Riemannian manifolds, we propose an end-to-end deep manifold-to-manifold transforming network (DMT-Net), which can make SPD matrices flow from one Riemannian manifold to another one for facilitating the action recognition task. To learn discriminative SPD features from both spatial and temporal dependencies, we propose a neural network model with three novel layers on manifolds: i.e., (1) the local SPD convolutional layer, (2) the non-linear SPD activation layer, and (3) the Riemannian-preserved recursive layer. The SPD property is preserved through all layers without the singular value decomposition (SVD) operation, which has to be conducted in the existing methods with expensive computation cost. Furthermore, a diagonalizing SPD layer is designed to efficiently calculate the final metric for the classification task. Finally, DMT-Net is further fused with a first order layer to capture temporal evolution information. To evaluate our proposed method, we conduct extensive experiments on the task of action recognition, where the input signals are represented as SPD matrices. The experimental results demonstrate that the proposed method is competitive over state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Human neural motor system has the intelligence to learn new skills, and then to generalize these skills naturally. But it is not easy for a robot to demonstrate such intelligent behaviors. Inspired by the neural motor behaviors, a framework of broad learning based novel adaptive neural control is proposed in this article, such that in the presence of dynamic disturbance, robots can learn a set of basic skills and then generalize these skills to the neighboring movements naturally as our human motor system. This is achieved by incorporating the deterministic learning with the broad learning system that can accumulate and reuse the learned knowledge. The broad learning enabled adaptive neural control has been rigorously established in theory and tested in both simulation and experimental studies. Simulation results and performance of the Baxter robot in the experiments have shown the effectiveness and superiority of the proposed method in comparison to the conventional adaptive neural control. [ABSTRACT FROM AUTHOR]

Fuel-powered UAVs have long endurance of flight, heavy payload and adaptation to extreme environment. The mechanical operation and communication power are supported independently by fuel and batteries. In the paper, we study the energy efficiency of the communication system with a fuel-powered UAV relay. We consider a three-node communication network, consisting of a mobile relay, a source node, and a destination node. The UAV relay is able to change its 3-D trajectory to maintain high probability of LoS channels, receiving information from the fixed source node and transmitting it to the fixed destination node. The power allocation scheme and UAV’s trajectory are designed to maximize the system energy efficiency, considering the constraints of speeds, UAV’s altitudes, communication and mechanical energy consumption, the required data rates of the destination node and information-causality. We solve the power allocation sub-problem by splitting the domain of variables and transforming it into a convex optimization problem. And then a suboptimal scheme is provided to design the trajectory based on successive convex approximation method. Numerical results show the convergence of the proposed schemes and the performance of the proposed algorithms. The influences of time slots, constraints of fuel, communication power and required data rates are discussed. [ABSTRACT FROM AUTHOR]

In in-utero MRI, motion correction for fetal body and placenta poses a particular challenge due to the presence of local non-rigid transformations of organs caused by bending and stretching. The existing slice-to-volume registration (SVR) reconstruction methods are widely employed for motion correction of fetal brain that undergoes only rigid transformation. However, for reconstruction of fetal body and placenta, rigid registration cannot resolve the issue of misregistrations due to deformable motion, resulting in degradation of features in the reconstructed volume. We propose a Deformable SVR (DSVR), a novel approach for non-rigid motion correction of fetal MRI based on a hierarchical deformable SVR scheme to allow high resolution reconstruction of the fetal body and placenta. Additionally, a robust scheme for structure-based rejection of outliers minimises the impact of registration errors. The improved performance of DSVR in comparison to SVR and patch-to-volume registration (PVR) methods is quantitatively demonstrated in simulated experiments and 20 fetal MRI datasets from 28–31 weeks gestational age (GA) range with varying degree of motion corruption. In addition, we present qualitative evaluation of 100 fetal body cases from 20–34 weeks GA range. [ABSTRACT FROM AUTHOR]

Recently, a method based on multiple histograms modification (MHM) is proposed for reversible data hiding (RDH), in which a sequence of prediction-error histograms are generated and two expansion bins are selected in each histogram for expansion embedding. However, although efficient, it only chooses a single pair of expansion bins which limits the embedding capacity. On the other hand, the exhaustive expansion-bin-selection procedure in MHM takes huge computation time, so that it cannot be extended for high capacity RDH. In order to overcome the aforementioned drawbacks, an optimal RDH scheme based on MHM for high capacity embedding is proposed in this paper. First, to improve the embedding capacity, instead of a single pair of expansion bins, multiple pairs of expansion bins are utilized for each histogram, and the multiple-expansion-bin-selection for optimal embedding is formulated as an optimization problem. Then, unlike the exhaustive searching way used in MHM, a computationally efficient algorithm is proposed to solve the optimization problem, so that the optimal expansion bins can be adaptively determined to optimize the embedding performance. By the proposed approach, high embedding capacity can be achieved with good marked image quality, and the experimental results show that it is better than the original MHM and some other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

This paper proposes a brain–robot interface (BRI)-based control strategy in combination with the simultaneous localization and mapping (SLAM) to achieve the navigation and control of a mobile robot in uncertain environments. The BRI is based on steady state visually evoked potentials, utilizing the multivariate synchronization index classification algorithm to analyze the human electroencephalograph (EEG) signals in such a manner that human intentions can be recognized and motion commands can be produced for the brain controlled robot. The entire system is semi-autonomous since the navigation of mobile robot is commanded by the BRI, and the low-level motion of the mobile robot is autonomous with a designed kinematic controller. By utilizing vanishing points and door plates as the environmental features, a global metric map of the environment has been built by a sequential SLAM algorithm. The main contribution of this paper is the combination of an artificial potential field (APF) and the brain signals, which builds up the relationship between the strength of EEG signals and the intensity of the potential field. Through the proposed EEG-APF method, motion commands that would plan an obstacle-free trajectory in un-structured environments, can be obtained. The entire system has been tested with eight volunteer subjects, and all subjects are able to successfully fulfill manipulating mobile robot in the experiments. [ABSTRACT FROM AUTHOR]

In recent years, the growth in popularity of mobile video streaming services is unbroken. There are tremendous demands for video streaming over wireless networks. Currently, most video streaming is over HTTP. Up to now, HTTP-based adaptive video streaming is standardized as DASH, where a client-side video player can dynamically pick the bitrate level according to the perceived network conditions. Actually, not only the available bandwidth drastically varies due to wireless network properties, but also the chunk sizes in the same bitrate level significantly fluctuate, which also influences the bitrate adaptation. However, existing bitrate adaptation algorithms mostly focus on available bandwidth but do not involve chunk size variation, leading to performance losses. In this paper, we theoretically analyze the influence of chunk size variation on bitrate adaptation performance in wireless networks. Based on DASH system features, we build a general model describing playback buffer evolution. Applying stochastic theories, we respectively analyze the influence of the chunk size variation on rebuffering probability, average bitrate, and bitrate switching interval. Furthermore, based on theoretical insights, we provide several suggestions for algorithm designing and rate encoding, and also design a simple bitrate adaptation algorithm. Extensive simulations verify our insights, suggestions, and designed algorithm effectiveness. [ABSTRACT FROM AUTHOR]

Pixel-value-ordering (PVO) is an efficient technique of reversible data hiding (RDH). By PVO, the maximum and minimum in each cover image block are first predicted and then modified to embed data. Actually, many PVO-based methods are essentially based on high-dimensional histogram modification. For these methods, a two-dimensional (2D) prediction-error histogram (PEH) is first generated and then modified based on a 2D mapping. However, these methods have two drawbacks. On one hand, the generated 2D PEH is irregular so that it is difficult to design suitable histogram modification strategy. On the other hand, the employed 2D mapping is empirically designed, and thus the embedding performance is far from optimal. Based on these considerations, a new PVO-based RDH scheme is proposed in this paper. By considering both pixel value orders and pixel locations, a new predictor is proposed so that the generated 2D PEH is regular in shape and suitable for reversible embedding. Moreover, instead of manually designing 2D mappings, to optimize the embedding performance, a self-learning mechanism is proposed to adaptively select the 2D mapping according to the image content. With the new predictor and the self-learning mechanism for 2D mapping selection, the proposed method works well with a good marked image quality, e.g., the PSNR of the image Lena is as high as 61.53 dB for an embedding capacity of 10 000 bits. Besides, compared with some state-of-the-art RDH methods, the superiority of the proposed method is experimentally verified. [ABSTRACT FROM AUTHOR]

The development of the smart ocean requires that various features of the ocean be explored and understood. The Underwater Internet of Things (UIoT), an extension of the Internet of Things (IoT) to the underwater environment, constitutes powerful technology for achieving the smart ocean. This article provides an overview of the UIoT with emphasis on current advances, future system architecture, applications, challenges, and open issues. The UIoT is enabled by the most recent developments in autonomous underwater vehicles, smart sensors, underwater communication technologies, and underwater routing protocols. In the coming years, the UIoT is expected to bridge diverse technologies for sensing the ocean, allowing it to become a smart network of interconnected underwater objects that has self-learning and intelligent computing capabilities. This article first provides a horizontal overview of the UIoT. Then, we present a five-layer system architecture for the future UIoT, which consists of a sensing, communication, networking, fusion, and application layer. Finally, we suggest the current challenges and the future UIoT research trends, in which cloud computing, fog computing, and artificial intelligence are combined. [ABSTRACT FROM AUTHOR]