Context-aware Features Research Articles

Distinguished representation of identical mentions in bio-entity coreference resolution

BackgroundBio-entity Coreference Resolution (CR) is a vital task in biomedical text mining. An important issue in CR is the differential representation of identical mentions as their similar representations may make the coreference more puzzling. However, when extracting features, existing neural network-based models may bring additional noise to the distinction of identical mentions since they tend to get similar or even identical feature representations.MethodsWe propose a context-aware feature attention model to distinguish similar or identical text units effectively for better resolving coreference. The new model can represent the identical mentions based on different contexts by adaptively exploiting features, which enables the model reduce the text noise and capture the semantic information effectively.ResultsThe experimental results show that the proposed model brings significant improvements on most of the baseline for coreference resolution and mention detection on the BioNLP dataset and CRAFT-CR dataset. The empirical studies further demonstrate its superior performance on the differential representation and coreferential link of identical mentions.ConclusionsIdentical mentions impose difficulties on the current methods of Bio-entity coreference resolution. Thus, we propose the context-aware feature attention model to better distinguish identical mentions and achieve superior performance on both coreference resolution and mention detection, which will further improve the performance of the downstream tasks.

CFDIL: a context-aware feature deep interaction learning for app recommendation.

The rapid development of mobile Internet has spawned various mobile applications (apps). A large number of apps make it difficult for users to choose apps conveniently, causing the app overload problem. As the most effective tool to solve the problem of app overload, app recommendation has attracted extensive attention of researchers. Traditional recommendation methods usually use historical usage data to explore users’ preferences and then make recommendations. Although traditional methods have achieved certain success, the performance of app recommendation still needs to be improved due to the following two reasons. On the one hand, it is difficult to construct recommendation models when facing with the sparse user–app interaction data. On the other hand, contextual information has a large impact on users’ preferences, which is often overlooked by traditional methods. To overcome the aforementioned problems, we proposed a context-aware feature deep interaction learning (CFDIL) method to explore users’ preferences and then perform app recommendation by learning potential user–app relationships in different contexts. The novelty of CFDIL is as follows: (1) CFDIL incorporates contextual features into users’ preferences modeling by constructing novel user and app feature portraits. (2) The problem of data sparsity is effectively solved by the use of dense user and app feature portraits, as well as the tensor operations for label sets. (3) CFDIL trains a new deep network structure, which can make accurate app recommendation using the contextual information and attribute information of users and apps. We applied CFDIL on three real datasets and conducted extensive experiments, which shows that CFDIL outperforms the benchmark methods.

An acceptance model for sports technologies: the effects of sports motivation, sports type and context-aware characteristics

PurposeThis study explores the drivers behind sports technology use and identifies the need for a new conceptualization of sports technology adoption. To address this issue, the authors create a new construct, “context-awareness,” with four dimensions: tracking, coaching, sharing and gamification.Design/methodology/approachThe paper uses a mixed-method approach, including in-depth interviews and partial least squares structural equation modeling. The proposed model combines technology acceptance frameworks with the Sports Motivation Scale and a novel context-awareness scale. It is empirically tested with a diverse sample of 600 respondents to identify use-intention differences according to sports motivation and sport types.FindingsThe paper reveals group differences in sports type (dynamic vs nondynamic) and sports motivation (intrinsic vs extrinsic) regarding sports technology use. It also suggests that perceived technology characteristics mediate the relationship between context-aware features and intention to use.Originality/valueThis research introduces a new construct of “context-awareness” into the literature on new technology acceptance. The proposed model combines insights from information systems, sports science, sports marketing and sports medicine to explain the adoption of complex technology.

Multiple Events Detection Using Context-Intelligence Features

Event detection systems are mainly used to observe and monitor human behavior via red green blue (RGB) images and videos. Event detection using RGB images is one of the challenging tasks of the current era. Human detection, position and orientation of human body parts in RGB images is a critical phase for numerous systems models. In this research article, the detection of human body parts by extracting context-aware energy features for event recognition is described. For this, silhouette extraction, estimation of human body parts, and context-aware features are extracted. To optimize the context-intelligence vector, we applied an artificial intelligence-based self-organized map (SOM) while a genetic algorithm (GA) is applied for multiple event detection. The experimental results on challenging RGB images and video-based datasets were promising. Three datasets were used. Event recognition and body parts detection accuracy rates for the University of central Florida’s (UCF) dataset were 88.88% and 86.75% respectively. 90.0% and 87.37% for event recognition and body parts detection were achieved over the University of Texas (UT) dataset. 87.89% and 85.87% for event recognition and body parts detection were achieved for the sports videos in the wild (SVW) dataset. The proposed system performs better than other current state-of-the-art approaches in terms of body parts and event detection and recognition outcomes.

Few-Shot Object Detection via Context-Aware Aggregation for Remote Sensing Images

Few-shot object detection methods have made prodigious progress in recent years. However, these methods are designed for optical images at a single scale, which leads to significantly degraded detection performance due to object scale variation of remote sensing images. In this letter, we propose a few-shot object detection method for the problem of scale variation in remote sensing images. More specifically, our model contains two main components: a context-aware pixel aggregation (CPA) that allows the model to adapt to objects at different scales through different scale convolution and a context-aware feature aggregation (CFA) that enhances context awareness to obtain more semantic information through a graph convolution network (GCN). Experiments on the DIOR dataset demonstrate that our model can achieve a satisfying detection performance on remote sensing images, and our model performs significantly better than the state-of-the-art model.

SR-GNN: Spatial Relation-aware Graph Neural Network for Fine-Grained Image Categorization.

Over the past few years, a significant progress has been made in deep convolutional neural networks (CNNs)-based image recognition. This is mainly due to the strong ability of such networks in mining discriminative object pose and parts information from texture and shape. This is often inappropriate for fine-grained visual classification (FGVC) since it exhibits high intra-class and low inter-class variances due to occlusions, deformation, illuminations, etc. Thus, an expressive feature representation describing global structural information is a key to characterize an object/ scene. To this end, we propose a method that effectively captures subtle changes by aggregating context-aware features from most relevant image-regions and their importance in discriminating fine-grained categories avoiding the bounding-box and/or distinguishable part annotations. Our approach is inspired by the recent advancement in self-attention and graph neural networks (GNNs) approaches to include a simple yet effective relation-aware feature transformation and its refinement using a context-aware attention mechanism to boost the discriminability of the transformed feature in an end-to-end learning process. Our model is evaluated on eight benchmark datasets consisting of fine-grained objects and human-object interactions. It outperforms the state-of-the-art approaches by a significant margin in recognition accuracy.

Context-Aware Contribution Estimation for Feature Aggregation in Video Face Recognition

The difficulties in video-based face recognition, such as dramatic pose variations and low quality, can be alleviated by leveraging the rich complementary information between the frames. However, limited by the mini-batch training strategy, the current deep learning methods only utilizes the frames in each batch during training, which ignore the context of the entire video. In this paper, we propose a context-aware feature aggregation scheme to aggregate complementary information between different frames. Firstly, a two-branch structure is designed as the Context-aware feature Aggregation Network (CAN). Secondly, a context-aware training strategy using context bank is proposed, which alleviates the limitation of mini-batch samples by using the context of the entire video or several images belonging to the same ID and thus achieves global contribution estimation result. Comparative studies on benchmark datasets, such as IJB-C, YouTube Face (YTF), PaSC and COX, confirm that the proposed approach can achieve state-of-the-art level. Meanwhile, qualitative analysis on Multi-PIE dataset indicates that the contribution learned by the CAN is reasonable and beneficial to video face recognition.

RGTransformer: Region-Graph Transformer for Image Representation and Few-Shot Classification

The goal of few-shot image classification is to learn a classifier that can be well generalized to the unseen classes with a few available labeled samples. One major challenge for few-shot learning is how to conduct effective image representation for support and query images. Recently, local region-based image representation and metric learning approaches have been demonstrated effectively for few-shot classification problem. However, existing approaches generally conduct representations of image regions individually which thus lack of considering the rich spatial/structural relationships among image regions. In this paper, we propose to bridge the individual regions and exploit the structural contexts among regions via a novel Region-Graph Transformer (RGTransformer). In RGTransformer, each region aggregates the information from its neighboring regions and thus can obtain context-aware feature representations for regions. Using the proposed RGTransformer, we propose an effective metric learning model for few-shot image classification. We evaluate the proposed method on four benchmark datasets and experimental results demonstrate the effectiveness and advantages of the proposed RGTransformer.

DRGCN: Dual Residual Graph Convolutional Network for Hyperspectral Image Classification

Recently, graph convolutional network (GCN) has drawn increasing attention in hyperspectral image (HSI) classification, as it can process arbitrary non-Euclidean data. However, dynamic GCN that refines the graph heavily relies on the graph embedding in the previous layer, which will result in performance degradation when the embedding contains noise. In this letter, we propose a novel dual residual graph convolutional network (DRGCN) for HSI classification that integrates two adjacency matrices of dual GCN. In detail, one GCN applies a soft adjacency matrix to extract spatial features, the other utilizes the dynamic adjacency matrix to extract global context-aware features. Subsequently, the features extracted by dual GCN are fused to make full use of the complementary and correlated information among two graph representations. Moreover, we introduce residual learning to optimize graph convolutional layers during the training process, to alleviate the over-smoothing problem. The advantage of dual GCN is that it can extract robust and discriminative features from HSI. Extensive experiments on four HSI data sets, including Indian Pines, Pavia University, Salinas, and Houston University, demonstrate the effectiveness and superiority of our proposed DRGCN, even with small-sized training data.

TBNet: a context-aware graph network for tuberculosis diagnosis

Background and objectiveTuberculosis (TB) is an infectious bacterial disease. It can affect the human lungs, brain, bones, and kidneys. Pulmonary tuberculosis is the most common. This airborne bacterium can be transmitted with the droplets by coughing and sneezing. So far, the most convenient and effective method for diagnosing TB is through medical imaging. Computed tomography (CT) is the first choice for lung imaging in clinics because the conditions of the lungs can be interpreted from CT images. However, manual screening poses an enormous burden for radiologists, resulting in high inter-observer variances. Hence, developing computer-aided diagnosis systems to implement automatic TB diagnosis is an emergent and significant task for researchers and practitioners. This paper proposed a novel context-aware graph neural network called TBNet to detect TB from chest CT images MethodsTraditional convolutional neural networks can extract high-level image features to achieve good classification performance on the ImageNet dataset. However, we observed that the spatial relationships between the feature vectors are beneficial for the classification because the feature vector may share some common characteristics with its neighboring feature vectors. To utilize this context information for the classification of chest CT images, we proposed to use a feature graph to generate context-aware features. Finally, a context-aware random vector functional-link net served as the classifier of the TBNet to identify these context-aware features as TB or normal ResultsThe proposed TBNet produced state-of-the-art classification performance for detecting TB from healthy samples in the experiments ConclusionsOur TBNet can be an accurate and effective verification tool for manual screening in clinical diagnosis.

LGCNet: A local-to-global context-aware feature augmentation network for salient object detection

Recent works on salient object detection (SOD) mainly focus on pixel-level classification by leveraging fully convolutional network (FCN)-based encoder-decoder models. In this paper, considering that the context relation plays a critical role in defining a salient object appearing in a scene, we propose a local-to-global context-aware feature augmentation network, namely LGCNet. A two-branch attention-based context relation modeling structure is designed by considering global context-aware information based on foreground/background cues and global feature representations. A pixel-wise self-attention mechanism is then incorporated for both branches to propagate global context information to local feature representations. As a result, a coarse-to-fine salient object detection model is formulated. The whole framework can be trained in an end-to-end manner under a deeply supervised framework. Experimental results demonstrate the effectiveness of key components proposed in our LGCNet. Our LGCNet achieves promising results in comparison with 18 state-of-the-art methods on six widely-used benchmark datasets.

Salient object detection network with multi-scale feature refinement and boundary feedback

Benefiting from the development of convolutional neural networks, salient object detection has achieved prominent progress in recent years. However, there are still two limitations when handling challenging scenarios. On the one hand, upsampling and pooling operations might cause blurry boundaries. On the other hand, multi-level features having different characteristics might incur fusion problems. To address these issues, we propose a novel pixel-wise salient object detection method equipped with multi-scale feature refinement and boundary feedback in this paper. Firstly, a feature interaction scheme is designed to depict the multi-scale representation of side-output features and the interactions between intra-layer features. Secondly, we design a context-aware feature refinement module to adaptively select useful side-output information for generating coarse saliency features. Finally, we obtain the predicted saliency maps with the help of extracted boundary information in a coarse-to-fine manner. Extensive experimental results on four benchmark datasets show that our proposed model performs favorably against state-of-the-art methods.

Attentive and context-aware deep network for saliency prediction on omni-directional images

Understanding visual attention of observers on omni-directional images gains interest along with the booming trend of virtual reality applications. In this paper, we propose a novel attentive and context-aware network for saliency prediction on omni-directional images, which is named as ACSalNet. In this architecture, considering the problem of insufficient receptive fields of high-level features, a Deformable Attention Bottleneck (DAB) is first proposed to strengthen the high-level feature extractor and effectively focus the limited receptive field of the model to the key areas. Then, to reduce the semantic gap between features of different levels and introduce context-aware information, we further design a Context-aware Feature Pyramid Module (CFPM). In the testing phase, in order to reduce the error of prediction directly on the equirectangular images while retaining their integrity, a novel projection method called Multiple Sphere Rotation (MSR) is proposed. Extensive experiments illustrate that the proposed method outperforms the state-of-the-art models under different evaluation metrics on the public saliency benchmarks.

Predicting traffic noise using land-use regression\u2014a scalable approach

BackgroundIn modern societies, noise is ubiquitous. It is an annoyance and can have a negative impact on human health as well as on the environment. Despite increasing evidence of its negative impacts, spatial knowledge about noise distribution remains limited. Up to now, noise mapping is frequently inhibited by the necessary resources and therefore limited to selected areas.ObjectiveBased on the assumption, that prevalent noise is determined by the arrangement of sources and the surrounding environment in which the sound propagates, we build a geostatistical model representing these parameters. Aiming for a large-scale noise mapping approach, we utilize publicly available data, context-aware feature engineering and a linear land-use regression (LUR) model.MethodsCompliant to the European Noise Directive 2002/49/EG, we work at a high spatial granularity of 10 × 10-m resolution. As reference, we use the day–evening–night noise level indicator Lden. Therewith, we carry out 2000 virtual field campaigns simulating different sampling schemes and introduce spatial cross-validation concepts to test the transferability to new areas.ResultsThe experimental results suggest the necessity for more than 500 samples stratified over the different noise levels to produce a representative model. Eventually, using 21 selected variables, our model was able to explain large proportions of the yearly averaged road noise (Lden) variability (R2 = 0.702) with a mean absolute error of 4.24 dB(A), 3.84 dB(A) for build-up areas, respectively. In applying this best performing model for an area-wide prediction, we spatially close the blank spots in existing noise maps with continuous noise levels for the entire range from 24 to 106 dB(A).SignificanceThis data is new, particular for small communities that have not been mapped sufficiently in Europe so far. In conjunction, our findings also supplement conventionally sampled studies using physical microphones and spatially blocked cross-validations.

Looking Wider for Better Adaptive Representation in Few-Shot Learning

Building a good feature space is essential for the metric-based few-shot algorithms to recognize a novel class with only a few samples. The feature space is often built by Convolutional Neural Networks (CNNs). However, CNNs primarily focus on local information with the limited receptive field, and the global information generated by distant pixels is not well used. Meanwhile, having a global understanding of the current task and focusing on distinct regions of the same sample for different queries are important for the few-shot classification. To tackle these problems, we propose the Cross Non-Local Neural Network (CNL) for capturing the long-range dependency of the samples and the current task. CNL extracts the task-specific and context-aware features dynamically by strengthening the features of the sample at a position via aggregating information from all positions of itself and the current task. To reduce losing important information, we maximize the mutual information between the original and refined features as a constraint. Moreover, we add a task-specific scaling to deal with multi-scale and task-specific features extracted by CNL. We conduct extensive experiments for validating our proposed algorithm, which achieves new state-of-the-art performances on two public benchmarks.

COMPASS: Unsupervised and online clustering of complex human activities from smartphone sensors

Modern mobile devices are able to provide context-aware and personalized services to the users, by leveraging on their sensing capabilities to infer the activity and situation in which a person is currently involved. Current solutions for context-recognition rely on annotated data and experts’ knowledge to predict the user context. In addition, their prediction ability is strongly limited to the set of situations considered during the model training or definition. However, in a mobile environment, the user context continuously evolves, and it cannot be merely restricted to a set of predefined classes. To overcome these limitations, we propose COMPASS, a novel unsupervised and online clustering algorithm aimed at identifying the user context in mobile environments based on the stream of high-dimensional data generated by smartphone sensors. COMPASS can distinguish an arbitrary number of user’s contexts from the sensors’ data, without defining a priori the collection of expected situations. This key feature makes it a general-purpose solution to provide context-aware features to mobile devices, supporting a broad set of applications. Experimental results on 18 synthetic and 2 real-world datasets show that COMPASS correctly identifies the user context from the sensors’ data stream, and outperforms the state-of-the-art solutions in terms of both clusters configuration and purity. Eventually, we evaluate its performances in terms of execution time and the results show that COMPASS can process 1000 high-dimensional samples in less than 20 s, while the reference solutions require about 60 min to evaluate the entire dataset.

Adaptive Pose Estimation for Gait Event Detection Using Context-Aware Model and Hierarchical Optimization

To understand daily events accurately, adaptive pose estimation (APE) systems require a robust context-aware model and optimal feature selection methods. In this paper, we propose a novel gait event detection (GED) system that consists of saliency silhouette detection, a robust body parts model and a 2D stick-model followed by a hierarchical optimization algorithm. Furthermore, the most prominent context-aware features such as energy, 0–180° intensity and distinct moveable features are proposed by focusing on invariant and localized characteristics of human postures in different event classes. Finally, we apply Grey Wolf optimization and a genetic algorithm to discriminate complex postures and to provide appropriate labels to each event. In order to evaluate the performance of proposed GED, two public benchmark datasets, UCF101 and YouTube, are examined via the n-fold cross validation method. For the two benchmark datasets, our proposed method detects the human body key points with 82.4% and 83.2% accuracy respectively. Also, it extracts the context-aware features and finally recognizes the gait events with 82.6% and 85.0% accuracy, respectively. Compared with other well-known statistical and state-of-the-art methods, our proposed method outperforms other similarly tasked methods in terms of posture detection and recognition accuracy.

SETUCOM: Secure and Trustworthy Context Management for Context-Aware Security and Privacy in the Internet of Things

IoT technologies facilitate the development and the improvement of pervasive computing by enabling effective context-awareness features. These features enable the IoT applications to detect the user’s situation and adapt their behavior. They also enable context-aware security and privacy, which consist in adapting security and privacy mechanisms’ deployment to the user’s situation. Research studies on context-aware security and privacy focus on security and privacy mechanisms’ implementation but do not consider the secure and trustworthy context management. In this paper, we introduce a new secure and trustworthy context management system for context-aware security and privacy in the smart city: “SETUCOM.” SETUCOM is the implementation of the DTM (Device Trust Management) module of the CASPaaS (Context-Aware Security and Privacy as a Service) architecture. It secures context information exchange by using a lightweight hybrid encryption system adapted to IoT devices and manages trust through artificial intelligence techniques such as Bayesian networks and fuzzy logic. A detailed description of the proposed system is provided, and its main performances are evaluated. The results prove SETUCOM feasibility in context-aware security and privacy for the smart city.

A novel context-aware feature extraction method for convolutional neural network-based intrusion detection systems

To create a safe and secure cyberspace, many researchers have created and proposed Intrusion Detection Systems (IDSs). Different types of IDSs are either designed to address only a single kind of intrusion or multiple variants. In this paper, we proposed a new context-aware feature extraction method as a pre-processing step for Convolutional Neural Network (CNN)-based multiclass intrusion detection. Feature selection is also used to reduce the feature space and classification time. For attack-type classification, we used CNN which is generally well-known for its better classification ability on image recognition tasks. We have exploited this ability to develop an IDS that can identify different types of intrusions ranging from 4 to 12 types. In our study, we evaluated our proposed Context-aware Feature Extraction-based CNN IDS on different datasets with multiple classes where it was able to successfully improve classification accuracy compared to the models with no preprocessing steps and other existing methods. We carried out the performance evaluation and comparison using four different datasets, NSL-KDD, CICIDS2017, ADFA-LD, and ADFA-WD. These datasets have either host-based or network-based features, which is another area that we investigated in this paper.

WBC-Net: A white blood cell segmentation network based on UNet++ and ResNet

The counting and identification of white blood cells (WBCs, i.e., leukocytes) in blood smear images play a crucial role in the diagnosis of certain diseases, including leukemia, infections, and COVID-19 (corona virus disease 2019). WBC image segmentation lays a firm foundation for automatic WBC counting and identification. However, automated WBC image segmentation is challenging due to factors such as background complexity and variations in appearance caused by histological staining conditions. To improve WBC image segmentation accuracy, we propose a deep learning network called WBC-Net, which is based on UNet++ and ResNet. Specifically, WBC-Net designs a context-aware feature encoder with residual blocks to extract multi-scale features, and introduces mixed skip pathways on dense convolutional blocks to obtain and fuse image features at different scales. Moreover, WBC-Net uses a decoder incorporating convolution and deconvolution to refine the WBC segmentation mask. Furthermore, WBC-Net defines a loss function based on cross-entropy and the Tversky index to train the network. Experiments on four image datasets show that the proposed WBC-Net achieves better WBC segmentation performance than several state-of-the-art methods.