Search

In VANETs, it is important to support fast and reliable multi-hop broadcast for safety-related applications. The performance of multi-hop broadcast schemes is greatly affected by relay selection strategies. However, the relationship between the relay selection strategies and the expected broadcast performance has not been fully characterized yet. Furthermore, conventional broadcast schemes usually attempt to minimize the waiting time difference between adjacent relay candidates to reduce the waiting time overhead, which makes the relay selection process vulnerable to internal interference, occurring due to retransmissions from previous forwarders and transmissions from redundant relays. In this paper, we jointly take both of the relay selection and the internal interference mitigation into account and propose a fast, reliable, opportunistic multi-hop broadcast scheme, in which we utilize a novel metric called the expected broadcast speed in relay selection and propose a delayed retransmission mechanism to mitigate the adverse effect of retransmissions from previous forwarders and an expected redundancy probability based mechanism to mitigate the adverse effect of redundant relays. The performance evaluation results show that the proposed scheme yields the best broadcast performance among the four schemes in terms of the broadcast coverage ratio and the end-to-end delivery latency.

The goal of hyperspectral image fusion (HIF) is to reconstruct high spatial resolution hyperspectral images (HR-HSI) via fusing low spatial resolution hyperspectral images (LR-HSI) and high spatial resolution multispectral images (HR-MSI) without loss of spatial and spectral information. Most existing HIF methods are designed based on the assumption that the observation models are known, which is unrealistic in many scenarios. To address this blind HIF problem, we propose a deep learning-based method that optimizes the observation model and fusion processes iteratively and alternatively during the reconstruction to enforce bidirectional data consistency, which leads to better spatial and spectral accuracy. However, general deep neural network inherently suffers from information loss, preventing us to achieve this bidirectional data consistency. To settle this problem, we enhance the blind HIF algorithm by making part of the deep neural network invertible via applying a slightly modified spectral normalization to the weights of the network. Furthermore, in order to reduce spatial distortion and feature redundancy, we introduce a Content-Aware ReAssembly of FEatures module and an SE-ResBlock model to our network. The former module helps to boost the fusion performance, while the latter make our model more compact. Experiments demonstrate that our model performs favorably against compared methods in terms of both nonblind HIF fusion and semiblind HIF fusion.

Continues field monitoring and searching sensor data remains an imminent element emphasizes the influence of the Internet of Things (IoT). Most of the existing systems are concede spatial coordinates or semantic keywords to retrieve the entail data, which are not comprehensive constraints because of sensor cohesion, unique localization haphazardness. To address this issue, we propose deep learning inspired sensor-rank consolidation (DLi-SRC) system that enables 3-set of algorithms. First, sensor cohesion algorithm based on Lyapunov approach to accelerate sensor stability. Second, sensor unique localization algorithm based on rank-inferior measurement index to avoid redundancy data and data loss. Third, a heuristic directive algorithm to improve entail data search efficiency, which returns appropriate ranked sensor results as per searching specifications. We examined thorough simulations to describe the DLi-SRC effectiveness. The outcomes reveal that our approach has significant performance gain, such as search efficiency, service quality, sensor existence rate enhancement by 91%, and sensor energy gain by 49% than benchmark standard approaches.

A common drawback of EEG-based emotion recognition is that volume conduction effects of the human head introduce interchannel dependence and result in highly correlated information among most EEG features. These highly correlated EEG features cannot provide extra useful information, and they actually reduce the performance of emotion recognition. However, the existing feature selection methods, commonly used to remove redundant EEG features for emotion recognition, ignore the correlation between the EEG features or utilize a greedy strategy to evaluate the interdependence, which leads to the algorithms retaining the correlated and redundant features with similar feature scores in the EEG feature subset. To solve this problem, we propose a novel EEG feature selection method for emotion recognition, termed global redundancy minimization in orthogonal regression (GRMOR). GRMOR can effectively evaluate the dependence among all EEG features from a global view and then select a discriminative and nonredundant EEG feature subset for emotion recognition. To verify the performance of GRMOR, we utilized three EEG emotional data sets (DEAP, SEED, and HDED) with different numbers of channels (32, 62, and 128). The experimental results demonstrate that GRMOR is a promising tool for redundant feature removal and informative feature selection from highly correlated EEG features.

The way Data Science and Machine Learning have set modern trends for automation. It is thoughtful to simplify our day to day activities which are related to these domains. One such task is the repetitive submission of the same personal details while submitting any online form regarding academic or other purposes. The repetitiveness seems a bit dilatory. Plus, the involvement of machine learning further espouses the concept to automate re-iteration of personal details each time we fill a form, instead of manual entry. To obviate the above redundancy, we have proposed to implement “Exam Form Automation Using Facial Recognition” which includes real time face recognition with the help of webcam, pre-storing data on web servers with Panda and NumPy library of Python and then automating the entries on form using selenium library of python. The system captures a real time image of a user and collects the particular details from data hosted on a web server. Thus, precluding the monotonous procedure of manual entry.

Compared with traditional convolutions, grouped convolutional neural networks are promising for both model performance and network parameters. However, existing models with the grouped convolution still have parameter redundancy. In this article, concerning the grouped convolution, we propose a sharing grouped convolution structure to reduce parameters. To efficiently eliminate parameter redundancy and improve model performance, we propose a Bayesian sharing framework to transfer the vanilla grouped convolution to be the sharing structure. Intragroup correlation and intergroup importance are introduced into the prior of the parameters. We handle the Maximum Type II likelihood estimation problem of the intragroup correlation and intergroup importance by a group LASSO-type algorithm. The prior mean of the sharing kernels is iteratively updated. Extensive experiments are conducted to demonstrate that on different grouped convolutional neural networks, the proposed sharing grouped convolution structure with the Bayesian sharing framework can reduce parameters and improve prediction accuracy. The proposed sharing framework can reduce parameters up to 64.17%. For ResNeXt-50 with the sharing grouped convolution on ImageNet dataset, network parameters can be reduced by 96.875% in all grouped convolutional layers, and accuracies are improved to 78.86% and 94.54% for top-1 and top-5, respectively.

CNN-based salient object detection (SOD) methods achieve impressive performance. However, the way semantic information is encoded in them and whether they are category-agnostic is less explored. One major obstacle in studying these questions is the fact that SOD models are built on top of the ImageNet pre-trained backbones which may cause information leakage and feature redundancy. To remedy this, here we first propose an extremely light-weight holistic model tied to the SOD task that can be freed from classification backbones and trained from scratch, and then employ it to study the semantics of SOD models. With the holistic network and representation redundancy reduction by a novel dynamic weight decay scheme, our model has only 100K parameters, ∼ 0.2% of parameters of large models, and performs on par with SOTA on popular SOD benchmarks. Using CSNet, we find that a) SOD and classification methods use different mechanisms, b) SOD models are category insensitive, c) ImageNet pre-training is not necessary for SOD training, and d) SOD models require far fewer parameters than the classification models. The source code is publicly available at https://mmcheng.net/sod100k/.

Feature selection has attracted a lot of attention in obtaining discriminative and non-redundant features from high-dimension data. Compared with traditional filter and wrapper methods, embedded methods can obtain a more informative feature subset by fully considering the importance of features in the classification tasks. However, the existing embedded methods emphasize the above importance of features and mostly ignore the correlation between the features, which leads to retain the correlated and redundant features with similar scores in the feature subset. To solve the problem, we propose a novel supervised embedded feature selection framework, called feature selection under global redundancy minimization in orthogonal regression (GRMOR). The proposed framework can effectively recognize redundant features from a global view of redundancy among the features. We also incorporate the large margin constraint into GRMOR for robust multi-class classification. Compared with the traditional embedded methods based on least square regression, the proposed framework utilizes orthogonal regression to preserve more discriminative information in the subspace, which can help accurately rank the importance of features in the classification tasks. Experimental results on twelve public datasets demonstrate that the proposed framework can obtain superior classification performance and redundancy removal performance than twelve other feature selection methods.

Traditional decision making in a vehicle network includes uploading vehicle sensing data to faraway cloud platforms and then returning correlated results to the vehicles. The data have features of large quantity and high redundancy, which causes high communication latency and vehicle applications to deteriorate. Vehicular fog computing (VFC) is a new network paradigm that uses local fog nodes for decision making. However, how to achieve distributed information exchange with low latency is a challenging issue because the connectivity of the vehicle network is low due to vehicle mobility. In this paper, a distributed information exchange scheme with low latency in VFC is proposed. First, considering the frequent changes in vehicle positions and the randomness in driving routes, public transportation facilities with a wider driving range such as buses and taxis are used as fog nodes to increase the probability of uploading data. Then, the fog nodes should dynamically adjust the data sampling frequency according to the time-space correlation of the data to ensure that only nonredundant data are received. To minimize the interruption latency caused by accidents during an exchange, the fog nodes evaluate and predict connection states among them and their neighboring vehicles when establishing exchanges. If a fog node finds that a vehicle cannot complete information exchange because the vehicle may move outside its communication range in a future period, it will recalculate an optimized relay route for the vehicle by using mixed integer programming. Theoretical analysis and simulation results show that compared with the existing work, the proposed scheme can completely exchange all vehicle data with lower latency.

Wireless Multimedia Sensor Network (WMSN) is increasingly being deployed for surveillance, monitoring and Internet-of-Things (IoT) sensing applications where a set of cameras capture and compress local images and then transmit the data to a remote controller. Such captured local images may also be compressed in a multi-view fashion to reduce the redundancy among overlapping views. In this paper, we present a novel paradigm for compressed-sensing-enabled multi-view coding and streaming in WMSN. We first propose a new encoding and decoding architecture for multi-view video systems based on Compressed Sensing (CS) principles, composed of cooperative sparsity-aware block-level rate-adaptive encoders, feedback channels and independent decoders. The proposed architecture leverages the properties of CS to overcome many limitations of traditional encoding techniques, specifically massive storage requirements and high computational complexity. Then, we present a modeling framework that exploits the aforementioned coding architecture. The proposed mathematical problem minimizes the power consumption by jointly determining the encoding rate and multi-path rate allocation subject to distortion and energy constraints. Extensive performance evaluation results show that the proposed framework is able to transmit multi-view streams with guaranteed video quality at lower power consumption.

Software projects capture information in various kinds of artifacts, including source code, tests, and documentation. Such artifacts routinely encode information that is redundant, i.e., when a specification encoded in the source code is also separately tested and documented. Without supporting technology, such redundancy easily leads to inconsistencies and a degradation of documentation quality. We designed a tool-supported technique, called DScribe, that leverages redundancy between tests and documentation to generate consistent and checkable documentation and unit tests based on a single source of information. DScribe generates unit tests and documentation fragments based on a novel template and artifact generation technology. By pairing tests and documentation generation, DScribe provides a mechanism to automatically detect and replace outdated documentation. Our evaluation of the Apache Commons IO library revealed that of 835 specifications about exception handling, 85% of them were not tested or correctly documented, and DScribe could be used to automatically generate 97% of the tests and documentation.

Large deep neural network (DNN) models pose the key challenge to energy efficiency due to the significantly higher energy consumption of off-chip DRAM accesses than arithmetic or SRAM operations. It motivates the intensive research on model compression with two main approaches. Weight pruning leverages the redundancy in the number of weights and can be performed in a non-structured, which has higher flexibility and pruning rate but incurs index accesses due to irregular weights, or structured manner, which preserves the full matrix structure with a lower pruning rate. Weight quantization leverages the redundancy in the number of bits in weights. Compared to pruning, quantization is much more hardware-friendly and has become a "must-do" step for FPGA and ASIC implementations. Thus, any evaluation of the effectiveness of pruning should be on top of quantization. The key open question is, with quantization, what kind of pruning (non-structured versus structured) is most beneficial? This question is fundamental because the answer will determine the design aspects that we should really focus on to avoid the diminishing return of certain optimizations. This article provides a definitive answer to the question for the first time. First, we build ADMM-NN-S by extending and enhancing ADMM-NN, a recently proposed joint weight pruning and quantization framework, with the algorithmic supports for structured pruning, dynamic ADMM regulation, and masked mapping and retraining. Second, we develop a methodology for fair and fundamental comparison of non-structured and structured pruning in terms of both storage and computation efficiency. Our results show that ADMM-NN-S consistently outperforms the prior art: 1) it achieves 348× , 36× , and 8× overall weight pruning on LeNet-5, AlexNet, and ResNet-50, respectively, with (almost) zero accuracy loss and 2) we demonstrate the first fully binarized (for all layers) DNNs can be lossless in accuracy in many cases. These results provide a strong baseline and credibility of our study. Based on the proposed comparison framework, with the same accuracy and quantization, the results show that non-structured pruning is not competitive in terms of both storage and computation efficiency. Thus, we conclude that structured pruning has a greater potential compared to non-structured pruning. We encourage the community to focus on studying the DNN inference acceleration with structured sparsity.

Due to the advantage of flexible and quick movement, unmanned aerial vehicles (UAVs) have been widely utilized in assisting wireless communications. A challenging problem is how to deploy UAVs to provide communication services for more user devices for a long term while minimizing the number of UAVs. In this article, we propose a UAV network system with UAV deletion due to redundancy or energy exhaustion and UAV insertion to provide long-lasting communication services. Then, a distributed algorithm based on the virtual Coulomb force and Voronoi diagram is proposed to deploy UAVs improving the communication coverage and turning redundant UAVs off. On the one hand, in order to improve the communication coverage, we propose two moving schemes to move UAVs. On the other hand, in order to save energy, we propose a sleeping scheme to turn several redundant UAVs off. Particularly, the redundancy of a UAV is evaluated according to a proposed definition of the average local coverage rate. Simulation results demonstrate that the proposed algorithm can deploy a minimal number of UAVs to provide enough communication coverage and the presented network system can offer long-lasting service.

It is often tricky in real-life classification applications to select model features that would ensure an adequate sample classification, given a large number of candidate features. Our main contribution is threefold: (1) Evaluate the relevance and redundancy of feature. (2) Define the feature selection problem as eigenvalue computation problem with linear constraint. (3) Select the best features in an efficient way. We considered 20 UCI benchmark datasets to validate and test our approach. The results were compared with those obtained using one of the more widely used approaches, namely mRMR, the conventional features and two moderns state-of-the-art approaches. The experimental results revealed that our approach could improve the classification task, using only 20 % of the conventional features.

Aiming at the problem of effectively selecting relevant features from heterogeneous data without decision, a novel feature selection approach is studied based on fuzzy mutual information in fuzzy rough set theory. First, the fuzzy relevance of each feature is defined by using fuzzy mutual information, and then the fuzzy conditional relevance is further given. Next, the fuzzy redundancy is defined by using the difference between the fuzzy relevance and the fuzzy conditional relevance. Thereby the evaluation index of the feature importance is obtained by using the idea of unsupervised minimum redundancy and maximum relevance. Finally, a fuzzy mutual information-based unsupervised feature selection (FMIUFS) algorithm is designed to select feature sequences. Extensive experiments are conducted on public datasets and six unsupervised feature selection algorithms are compared. The selected features are evaluated by classification, clustering, and outlier detection methods. Experimental results show that the proposed algorithm can select fewer heterogeneous features to maintain or improve the performance of learning algorithms.

In the natural language processing family, learning representations is a pioneering study, especially in sequence-to-sequence tasks where outputs are generated, totally relying on the learning representations of source sequence. Generally, classic methods infer that each word occurring in the source sequence, having more or less influence on the target sequence, should all be considered when generating outputs. As the summarization task requires the output sequence to only retain the essence, classic full consideration of the source sequence may not work well on it, which calls for more suitable methods with the ability to discard the misleading noise words. Motivated by this, with both relevance retaining and redundancy removal in mind, we propose a summarization learning model by implementing an encoder with copious contextual information represented and a decoder with a selecting mechanism integrated. Specifically, we equip the encoder with an asynchronous bi directional parallel structure, in order to obtain abundant semantic representation. The decoder, different from the classic attention-based works, employs a self-aware context selecting mechanism to generate summary in a more productive way. We evaluate the proposed methods on three benchmark summarization corpora. The experimental results demonstrate the effectiveness and applicability of the proposed framework in relation to several well-practiced and state-of-the-art summarization methods.

Cloud storage attracts a lot of clients to join the paradise. For a high data availability, some clients require their files to be replicated and stored on multiple servers. Because clients are generally charged based on the redundancy level required by them, it is critical for clients to obtain convincing evidence that all replicas are stored correctly and are updated to the up-to-date version. In this paper, we propose a dynamic proof of data possession and replication (DPDPR) scheme, which is proved to be secure in the defined security model. Our scheme shares a single authenticated tree across multiple replicas, which reduces the tree's storage cost significantly. Our scheme allows for batch verification for multiple challenged leaves and can verify multiple replicas in a single batch way, which considerably save bandwidth and computation resources during audit process. We also evaluate the DPDPR's performance and compare it with the most related scheme. The evaluation results show that our scheme saves almost 66% tree's storage cost for three replicas, and obtains almost 60% and 80% efficiency improvements in terms of the overall bandwidth and computation costs, respectively, when three replicas are checked and each challenged with 460 blocks.

It's common practice to speed up machine learning (ML) training by distributing it across a cluster of computing nodes. Data-parallel distributed ML (DML) training relieves the pressure of computing node; however, the communication traffic introduced during parameter synchronization becomes bottleneck of DML training. Regarding communication bottleneck, we identify two primary causes: high contention of concurrent communication and large volume of redundant transmission in the push and pull stage while synchronizing parameters. To address these issues, we propose a novel Group Stale Synchronous Parallel (GSSP) scheme, which divides the nodes into groups and coordinates groups to synchronize in a circular order. GSSP mitigates network contention and is proven to converge. We provide analysis of the optimal group's number based on bandwidth and buffer size. For reducing traffic redundancy, we propose a multicast-based scheme, which generates multicast trees by minimizing links overlap and allocates transmission rate to multicast flows by solving the min-max optimization problem. Finally, we conduct extensive simulations to evaluate the performance of our proposals. We simulate parameter transmission of All-Reduce and parameter server in Fat-Tree with traffics trace of ML models. Simulation results show that our proposals provide communication-efficiency for DML training by mitigating contention and reducing redundancy.

The day-to-day growth of online information necessitates intensive research in automatic text summarization (ATS). The ATS software produces summary text by extracting important information from the original text. With the help of summaries, users can easily read and understand the documents of interest. Most of the approaches for ATS used only local properties of text. Moreover, the numerous properties make the sentence selection difficult and complicated. So this article uses a graph based summarization to utilize structural and global properties of text. It introduces maximal clique based sentence selection (MCBSS) algorithm to select important and non-redundant sentences that cover all concepts of the input text for summary. The MCBSS algorithm finds novel information using maximal cliques (MCs). The experimental results of recall oriented understudy for gisting evaluation (ROUGE) on Timeline dataset show that the proposed work outperforms the existing graph algorithms Bushy Path (BP), Aggregate Similarity (AS), and TextRank (TR).

Message-Locked Encryption (MLE) is a useful tool to enable deduplication over encrypted data in cloud storage. It can significantly improve the cloud service quality by eliminating redundancy to save storage resources, and hence user cost, and also providing defense against different types of attacks, such as duplicate faking attack and brute-force attack. A typical MLE scheme only focuses on deduplication. On the other hand, supporting search operations on stored content is another essential requirement for cloud storage. In this paper, we present a message-locked searchable encryption (MLSE) scheme in a dual-server setting, which achieves simultaneously the desirable features of supporting deduplication and enabling users to perform search operations over encrypted data. In addition, it supports both multi-keyword and negative keyword searches. We formulate the security notions of MLSE and prove our scheme satisfies all the security requirements. Moreover, we provide an interesting extension of our construction to support Proof of Storage (PoS). Compared with the existing solutions, MLSE achieves better functionalities and efficiency, and hence enables more versatile and efficient cloud storage service.

Multi-access Edge Computing (MEC) is booming as a promising paradigm to push the computation and communication resources from cloud to the network edge to provide services and to perform computations. With container technologies, mobile devices with small memory footprint can run composite microservice-based applications without time-consuming backbone. Service placement at the edge is of importance to put MEC from theory into practice. However, current state-of-the-art research does not sufficiently take the composite property of services into consideration. Besides, although Kubernetes has certain abilities to heal container failures, high availability cannot be ensured due to heterogeneity and variability of edge sites. To deal with these problems, we propose a distributed redundant placement framework SAA-RP and a GA-based Server Selection (GASS) algorithm for microservice-based applications with sequential combinatorial structure. We formulate a stochastic optimization problem with the uncertainty of microservice request considered, and then decide for each microservice, how it should be deployed and with how many instances as well as on which edge sites to place them. Benchmark policies are implemented in two scenarios, where redundancy is allowed and not, respectively. Numerical results based on a real-world dataset verify that GASS significantly outperforms all the benchmark policies.

The stochastic cloud cover on photovoltaic (PV) panels affects the solar power outputs, producing high instability in the integrated power systems. It is an effective approach to track cloud motion during short-term PV power forecasting based on data sources of satellite images. However, since temporal variations of these images are noisy and non-stationary, pixel-sensitive prediction methods are critically needed in order to seek a balance between forecast precision and huge computation burden due to a large image size. Hence, a graphical learning framework is proposed for intra-hour PV power prediction. By simulating the cloud motion using bi-directional extrapolation, a directed graph is generated representing the pixel values from multiple frames of historical images. The nodes and edges in the graph denote the shapes and motion directions of the regions of interest (ROIs) in satellite images. A spatial-temporal graph neural network (GNN) is then proposed to deal with the graph. Comparing with conventional deep-learning-based models, GNN is more flexible for varying sizes of input, in order to be able to handle dynamic ROIs. Referring to the comparative studies, the proposed method greatly reduces the redundancy of image inputs without sacrificing the visual scope, and slightly improves the prediction accuracy.

Deep neural networks (DNNs) have become a widely deployed model for numerous machine learning applications. However, their fixed architecture, substantial training cost, and significant model redundancy make it difficult to efficiently update them to accommodate previously unseen data. To solve these problems, we propose an incremental learning framework based on a grow-and-prune neural network synthesis paradigm. When new data arrive, the neural network first grows new connections based on the gradients to increase the network capacity to accommodate new data. Then, the framework iteratively prunes away connections based on the magnitude of weights to enhance network compactness, and hence recover efficiency. Finally, the model rests at a lightweight DNN that is both ready for inference and suitable for future grow-and-prune updates. The proposed framework improves accuracy, shrinks network size, and significantly reduces the additional training cost for incoming data compared to conventional approaches, such as training from scratch and network fine-tuning. For the LeNet-300-100 (LeNet-5) neural network architectures derived for the MNIST dataset, the framework reduces training cost by up to 64% (67%), 63% (63%), and 69% (73%) compared to training from scratch, network fine-tuning, and grow-and-prune from scratch, respectively. For the ResNet-18 architecture derived for the ImageNet dataset (DeepSpeech2 for the AN4 dataset), the corresponding training cost reductions against training from scratch, network fine-tunning, and grow-and-prune from scratch are 64% (67%), 60% (62%), and 72% (71%), respectively. Our derived models contain fewer network parameters but achieve higher accuracy relative to conventional baselines.

Recently, data-driven industrial monitoring systems have been rapidly developed and significantly improved the performance on industrial monitoring tasks. However, the widely deployed data-driven models expose industrial data to more unsecured links, increasing the safety risk of safe-critical industrial systems. The research about adversarial attacks has shown that the potential attackers can utilize tiny crafted perturbations on the input data to mislead the machine learning model outputs. In this paper, a novel cross-domain data protection scheme named Data Guardian is proposed to authenticate and correct industrial data under potential attacks on data-driven monitoring systems. Data Guardian embeds designed redundancy information into the data least significant bits (LSB), based on q-ary low density parity-codes (LDPC) over Galois field (finite field). The data is encoded at the secured industrial sites, then decoded before being input into the data-driven monitoring systems, where the security risk is usually higher. The decoding capability of q-ary LDPC codes is improved by the data statistical characteristics, with a new proposed prior estimation method. In the experiments, the Data Guardian is tested under the attacks to the fault diagnosis models on Tennessee Eastman process (TEP) and rolling element bearing (REB) from Case Western Reserve University. The results show that Data Guardian can efficiently reduce the success rate of adversarial attacks, especially when the attack variable ratio is small.

The plethora of ways of data representation and their applications to system modeling is inherently associated with dimensionality reduction. In a nutshell, the result of dimensionality reduction should support efficient ways of constructing ensuing models (classifiers, predictors) as well as an interpretation of the data themselves. Furthermore, there should be a suitable measure quantifying the quality of data positioned in the reduced space. We advocate that what makes the reduced data interpretable, goes hand in hand with revealing a logic fabric of the data, suppressing redundancy, and finally arriving at a logic description of data. The anticipation is that the reduced data can be described in the form of logic expressions formed over the original highly dimensional data. Evidently, having these above stated points in mind, the aim of this study is two-fold: (i) to develop a logic-oriented data representation, and (ii) to quantify the quality of results of dimensionality reduction by incorporating a facet of information granularity. In other words, we argue that the result of dimensionality reduction gives rise to information granules whose level of granularity associates with the quality of processing completed by the autoencoder. In light of the recent surge of architectures of deep learning, the study is focused on the construction and analysis of logic-oriented autoencoders. We propose a two-level architecture composed of the logic-oriented processing units (and processing carried out at the first layer of the autoencoder) followed by the or processing completed at the second layer. As data representation provided by the autoencoder is not ideal, we augment the original architecture by granular parameters which give rise to granular logic-oriented autoencoders. A suite of experiments is also reported.

Band selection is one of the most effective methods to reduce the band redundancy of hyperspectral images (HSIs). Most existing band selection methods tend to regard each band as a whole, and then explore the band redundancy with the pixel-wise features directly. However, since the regions of HSIs corresponding to different objects have diverse spectral properties and spatial structure, such above scheme limits the performance of hyperspectral band selection due to the lack of spatial information. To address above issues, a novel band selection method via region-aware latent features fusion based clustering (RLFFC) is proposed. Specifically, we employ the superpixel segmentation to segment HSIs into multiple regions so that the spatial information of HSIs can be fully preserved. In order to capture the priori information, we construct its corresponding Laplacian matrix from which a group of low dimensional latent features are generated to further enhance the separability among different bands. Then, a shared latent feature representation of HSIs is obtained by fusing region-aware latent features to effectively capture the band redundancy of HSIs. Finally, the k -means clustering algorithm is utilized to obtain the index of the selected bands from the shared latent feature representation. As a result, the spectral and spatial properties are well exploited in the proposed method. Extensive experiments on four public hyperspectral datasets show that the proposed method achieves superior performance when compared with other state-of-the-art ones.

Crowdsourcing is a hotspot research field which can facilitate machine learning by collecting labels to train models. Consequently, the state-of-the-art research efforts in crowdsourcing focus on truth inference or label integration, to remove inconsistent labels or to alleviate biased labeling. In turn, the integrated labels will be used to fine-tune machine learning models. Particularly, in this paper, we change the target of truth inference in crowdsourcing from discrete labels to multiple comments given by online participants, that is, the integration of the crowdsourced comments. For such a goal, we propose a Self-play and Sentiment-Emphasized Comment Integration Framework (SSECIF), based on deep Q-learning, with three unique features. First, our framework SSECIF can generate the comment integration in a totally self-play way, without relying on the ground truth generated by human effort. Second, the integrated comment generated by SSECIF can include salient content with low redundancy. Third, the proposed framework SSECIF has emphasized, with a higher intensity, the sentiment in the integrated comment, in order to reflect the attitude or opinion more obviously. Extensive evaluation on real-world datasets demonstrates that SSECIF has achieved the best overall performance in terms of both effectiveness and efficiency, compared with the state-of-the-art methods. Index Terms: Crowdsourcing; Comment Integration; Reinforcement Learning; Deep Q-Learning; Sentiment Analysis.

Visual grounding (VG) aims to locate the most relevant object or region in an image, based on a natural language query. Generally, it requires the machine to first understand the query, identify the key concepts in the image, and then locate the target object by specifying its bounding box. However, in many real-world visual grounding applications, we have to face with ambiguous queries and images with complicated scene structures. Identifying the target based on highly redundant and correlated information can be very challenging, and often leading to unsatisfactory performance. To tackle this, in this paper, we exploit an attention module for each kind of information to reduce internal redundancies. We then propose an accumulated attention (A-ATT) mechanism to reason among all the attention modules jointly. In this way, the relation among different kinds of information can be explicitly captured. Moreover, to improve the performance and robustness of our VG models, we additionally introduce some noises into the training procedure to bridge the distribution gap between the human-labeled training data and the real-world poor quality data. With this "noised" training strategy, we can further learn a bounding box regressor, which can be used to refine the bounding box of the target object. We evaluate the proposed methods on four popular datasets (namely ReferCOCO, ReferCOCO+, ReferCOCOg, and GuessWhat?!). The experimental results show that our methods significantly outperform all previous works on every dataset in terms of accuracy.

Artificial Neural networks (ANNs) are widely used to solve classification problems for many machine learning applications. When errors occur in the computational units of an ANN implementation due to for example radiation effects, the result of an arithmetic operation can be changed, and therefore, the predicted classification class may be erroneously affected. This is not acceptable when ANNs are used in many safety-critical applications, because the incorrect classification may result in a system failure. Existing error-tolerant techniques usually rely on physically replicating parts of the ANN implementation or incurring in a significant computation overhead. Therefore, efficient protection schemes are needed for ANNs that are run on a processor and used in resource-limited platforms. A technique referred to as Selective Neuron Re-Computation (SNRC), is proposed in this paper. As per the ANN structure and algorithmic properties, SNRC can identify the cases in which the errors have no impact on the outcome; therefore, errors only need to be handled by re-computation when the classification result is detected as unreliable. Compared with existing temporal redundancy-based protection schemes, SNRC saves more than 60 percent of the re-computation (more than 90 percent in many cases) overhead to achieve complete error protection as assessed over a wide range of datasets. Different activation functions are also evaluated. This research was supported by the National Science Foundation Grants CCF-1953961 and 1812467, by the ACHILLES project PID2019-104207RB-I00 and the Go2Edge network RED2018-102585-T funded by the Spanish Ministry of Science and Innovation and by the Madrid Community research project TAPIR-CM P2018/TCS-4496. Publicado

The gastrointestinal polyp (GIP) is the abnormal growth of tissues in digestive organs. Identifying these polyps from endoscopy video or image is a tremendous task to reduce the future risk of gastrointestinal cancer. This paper proposes a proper diagnosis method of polyp using a fusion of contourlet transform and fine-tuned VGG19 pre-trained model from enhanced endoscopic 224 × 224 patch images. This study has used different fine-tuned models (Alexnet, ResNet50, VGG16, VGG19) as well as a few scratch models while fine-tuned VGG19 works better. Also, this research has used Principal Component Analysis (PCA) and Minimum Redundancy Maximum Relevance (MRMR) dimensionality reduction methods to collect the intuitive features for classification. In Support Vector Machine (SVM) based polyp detection, the prior method (PCA) performs better. Besides, a proposed algorithm marks polyp region from identified polyp patches and uses a binning strategy to process video. A set of experiments are performed on standard public data sets and found comparative improved performance with an accuracy of 99.59%, sensitivity of 99.74% and specificity of 99.44%. This work can be instrumental for the radiologist for diagnosis of polyps during real-time endoscopy.

In the presence of distributed energy resources (DERs), distribution networks (DNs) operate in multiple configurations. Maintaining complete observability is essential for the monitoring of the network during operation in any configuration. This article proposes a methodology for the optimal deployment of micro-phasor measurement units ( $\mu$ PMUs) in a DN operating in multiple configurations. A composite objective function has been formulated to minimize the number of $\mu$ PMUs while maximizing measurement redundancy. The optimal solution has been obtained considering the $\mu$ PMU with or without channel limits. The constraints have been formed simultaneously to cover all operational configuration of the network while eliminating repetition. The proposed methodology has been illustrated on an eight-node reconfigurable network. It has also been verified on several reconfigurable DNs, having 33, 34, 69, 118, 123, and 167 nodes. A comparison between the proposed methodology and recently published approaches has been made. The constraints for zero-injection nodes with various network configuration has also been considered to find optimal $\mu$ PMU deployment. The obtained optimal deployment of $\mu$ PMUs with or without channel limit satisfies the criteria of complete topological observability, topological in-dependency, and maximizes the sum of topology measurement redundancy.

Quantitative ultrasound (QUS), which is commonly used to extract quantitative features from the ultrasound radiofrequency (RF) data or the RF envelope signals for tissue characterization, is becoming a promising technique for noninvasive assessments of liver fibrosis. However, the number of feature variables examined and finally used in the existing QUS methods is typically small, to some extent limiting the diagnostic performance. Therefore, this paper devises a new multiparametric QUS (MP-QUS) method which enables the extraction of a large number of feature variables from US RF signals and allows for the use of feature-engineering and machinelearning based algorithms for liver fibrosis assessment. In the MP-QUS, eighty-four feature variables were extracted from multiple QUS parametric maps derived from the RF signals and the envelope data. Afterwards, feature reduction and selection were performed in turn to remove the feature redundancy and identify the best combination of features in the reduced feature set. Finally, a variety of machine-learning algorithms were tested for classifying liver fibrosis with the selected features, based on the results of which the optimal classifier was established and used for final classification. The performance of the proposed MPQUS method for staging liver fibrosis was evaluated on an animal model, with histologic examination as the reference standard. The mean accuracy, sensitivity, specificity and area under the receiver-operating-characteristic curve achieved by MP-QUS are respectively 83.38%, 86.04%, 80.82% and 0.891 for recognizing significant liver fibrosis, and 85.50%, 88.92%, 85.24% and 0.924 for diagnosing liver cirrhosis. The proposed MP-QUS method paves a way for its future extension to assess liver fibrosis in human subjects.

Single image dehazing, which aims at restoring a haze-free image from its correspondingly unconstrained hazy scene, is highly challenging and has gained immense popularity in recent years. However, the images generated using existing haze-removal methods often contain haze, artifacts, and color distortions, which severely degrade the visual quality of the final images. To this end, we propose a network combining multi-scale hierarchical feature fusion and mixed convolution attention to progressively and adaptively enhance the dehazing performance. The haze levels and image structure information are accurately estimated by fusing multi-scale hierarchical features, thus the model restores images with less remaining haze. The proposed attention mechanism is capable of reducing feature redundancy, learning compact internal representations, highlighting task-relevant features and further helping the model to estimate images with sharper textural details and more vivid colors. Therefore, with the application of multi-scale features extracted from both diverse layers and filters, the dehazing performance is significantly improved. Furthermore, a deep semantic loss function is proposed to highlight more semantic information in deep features. The experimental results show that the proposed method outperforms state-of-the-art haze removal algorithms.

Unlike theoretical distributed learning (DL), DL over wireless edge networks faces the inherent dynamics/uncertainty of wireless connections and edge nodes, making DL less efficient or even inapplicable under the highly dynamic wireless edge networks (e.g., using mmW interfaces). This article addresses these problems by leveraging recent advances in coded computing and the deep dueling neural network architecture. By introducing coded structures/redundancy, a distributed learning task can be completed without waiting for straggling nodes. Unlike conventional coded computing that only optimizes the code structure, coded distributed learning over the wireless edge also requires to optimize the selection/scheduling of wireless edge nodes with heterogeneous connections, computing capability, and straggling effects. However, even neglecting the aforementioned dynamics/uncertainty, the resulting joint optimization of coding and scheduling to minimize the distributed learning time turns out to be NP-hard. To tackle this and to account for the dynamics and uncertainty of wireless connections and edge nodes, we reformulate the problem as a Markov Decision Process and then design a novel deep reinforcement learning algorithm that employs the deep dueling neural network architecture to find the jointly optimal coding scheme and the best set of edge nodes for different learning tasks without explicit information about the wireless environment and edge nodes' straggling parameters. Simulations show that the proposed framework reduces the average learning delay in wireless edge computing up to 66% compared with other DL approaches. The jointly optimal framework in this article is also applicable to any distributed learning scheme with heterogeneous and uncertain computing nodes.

Inter prediction is a crucial part of hybrid video coding frameworks, utilized to exploit the temporal redundancy in video sequences and improve the coding performance. During inter prediction, a predicted block is typically derived from reference pictures using motion estimation and motion compensation. To improve the coding performance of inter prediction, a neural network based enhancement to inter prediction (NNIP) is proposed in this paper. NNIP is composed of three networks, namely residue estimation network, combination network, and deep refinement network. Specifically, first, a residue estimation network is designed to estimate the residue between current block and its predicted block using their available spatial neighbors. Second, the feature maps of the estimated residue and the predicted block are extracted and concatenated in a combination network. Finally, the concatenated feature maps are fed into a deep refinement network to generate a refined residue, which is added back to the predicted block to derive a more accurate predicted block. NNIP is integrated in HEVC to evaluate its efficiency. The experimental results demonstrate that NNIP can achieve 4.6%, 3.0%, and 2.7% BD-rate reduction on average under LDP, LDB, and RA configurations compared to HEVC.

In high-power industrial installations, instead of a single shunt active harmonic filter (SAHF), parallel-connected multiple modular units of SAHF having lower current rating are generally preferred. In order to ensure that these modules share the compensating current in proportion to their individual current ratings, an intermodular communication network is generally being employed. This intermodular communication network reduces the overall reliability of the system, and it can be avoided if every individual module can autonomously estimate the compensating current to be shared by it. In case of voltage-source inverters operating in parallel, a droop-based current control scheme is generally employed to achieve the aforesaid requirement. However, in the SAHF, the inverters are operated in the current control mode, and hence, the existing droop-based control scheme needs appropriate modification. In this article, a modified droop-based scheme is proposed for a multimodular SAHF operating in the current control mode. The principle of operation of the proposed control scheme and its detailed mathematical analysis are presented. The feasibility of the scheme is verified by performing detailed simulation studies. A laboratory prototype having two SAHF modules, each having a VA rating of 30 kVA, is fabricated. Detailed experimental studies are carried out utilizing the laboratory prototype to confirm the viability of the proposed scheme.

The Internet of Things (IoT) has significantly increased the number of terminals and network traffic. It is necessary to exploit the full capacity of the network and optimize content transfer. Despite the powerful processing and storage capabilities of base stations in 5G technology, edge caching effectively reduces content access time and duplicate traffic, thus optimizing content transfer for more storage resources. The limited memory resources and the dynamic nature of the requested content have necessitated the use of smart caching methods. Sending the required data to central servers can cause additional network overload and learning disabilities due to private data. For this reason, a hierarchical federated deep learning (HFDRL) is proposed in this paper that uses the FDRL method to predict the user’s future requests and to determine the appropriate content replacement strategy. In addition, to perform learning and collaborate caching, the method by which partner devices are determined plays a key role in edge caching performance. HFDRL categorizes edge devices hierarchically, thus avoids the disadvantages of very small or large clusters, takes advantage of both. By minimizing the redundancy of content storage and latency, HFDRL improves the performance for each local base station network individually and the global network. Simulation results of the proposed method show that the hit rate and delay have improved, respectively, by an average of 55% and 67% compared to traditional methods, 40% and 56% compared to the collaborative method, and 14% and 15% compared to one-level FDRL without using hierarchical edge devices clustering.

The use of deep learning methods in hyperspectral image (HSI) classification has been a promising approach due to its powerful ability to automatically extract features in recent years. This article proposes a novel deep framework for HSI classification problems, referred to as feature-grouped network based on spectral-spatial connected attention mechanism (FG-SSCA). Different from the existing deep learning methods, the proposed framework integrates the spectral attention module and spatial attention module continuously from the raw HSI input, which is embedded into convolutional neural networks and could enhance the distinguishing ability of spectral bands and learn the spatial relevance between the neighboring pixels together. Meanwhile, the generating feature maps are sliced into a series of small groups in sequence along the direction of spectral bands and each group sequentially extracts spatial-spectral features through multiple spectral and spatial residual blocks. This feature-grouped strategy could fully utilize the redundancy and difference of bands and obtain more available and valuable information. The proposed FG-SSCA method could greatly improve generalization performance and make tremendous successes in HSI classification. Experimental results on several HSI benchmark data sets verify the effectiveness and superiority of the proposed method in comparison with the state-of-the-art approaches for HSI classification.

A synthetic air data system (SADS) is an analytical redundancy technique that is crucial for unmanned aerial vehicles (UAVs) and is used as a backup system during air data sensor failures. Unfortunately, the existing state-of-the-art approaches for SADS require GPS signals or high-fidelity dynamic UAV models. To address this problem, a novel synthetic airspeed estimation method that leverages deep learning and an unscented Kalman filter (UKF) for analytical redundancy is proposed. Our novel fusion-based method only requires an inertial measurement unit (IMU), elevator control input, and airflow angles while GPS, lift/drag coefficients, and complex aircraft dynamic models are not required. Additionally, we demonstrate that our proposed temporal convolutional network (TCN) is a more efficient model for airspeed estimation than the renowned models, such as ResNet or bidirectional long short-term memory (LSTM). Our deep learning-aided UKF was experimentally verified on long-duration real flight data and has promising performance compared with the state-of-the-art methods. In particular, it is confirmed that our proposed method robustly estimates the airspeed even under dynamic flight conditions where the performance of conventional methods is degraded.

Neuromorphic vision sensors (NVS) can enable energy savings due to their event-driven that exploits the temporal redundancy in video streams from a stationary camera. However, noise-driven events lead to the false triggering of the object recognition processor. Image denoise operations require memoryintensive processing leading to a bottleneck in energy and latency. In this paper, we present in-memory filtering (IMF), a 6TSRAM in-memory computing based image denoising for eventbased binary image (EBBI) frame from an NVS. We propose a non-overlap median filter (NOMF) for image denoising. An inmemory computing framework enables hardware implementation of NOMF leveraging the inherent read disturb phenomenon of 6T-SRAM. To demonstrate the energy-saving and effectiveness of the algorithm, we fabricated the proposed architecture in a 65nm CMOS process. As compared to fully digital implementation, IMF enables > 70x energy savings and a > 3x improvement of processing time when tested with the video recordings from a DAVIS sensor and achieves a peak throughput of 134.4 GOPS. Furthermore, the peak energy efficiencies of the NOMF is 51.3 TOPS/W, comparable with state of the art inmemory processors. We also show that the accuracy of the images obtained by NOMF provide comparable accuracy in tracking and classification applications when compared with images obtained by conventional median filtering., 13 pages

Bubble size distribution (BSD) is a crucial indicator of operating conditions in froth flotation. However, current BSD-based recognition methods have some limitations in the BSD estimation and don't achieve satisfactory results. Therefore, an alternative operating condition recognition method is proposed. Firstly, the temporal cumulative distribution function (TCDF) is designed to represent the BSD on the froth video. Then, the piecewise basis function is established to fit the TCDF. Secondly, the TCDF-Minimum Redundancy Maximum Relevancy (MRMR) feature is generated by MRMR to increase the sensitivity of TCDF features to the operating conditions. Lastly, the proposed TCDF-MRMR feature together with froth velocity and texture features are fed into an AdaBoost-extreme learning machine (ELM) model to recognize the operating conditions. Experiments in a zinc flotation process demonstrate that the TCDF-MRMR feature is more effective than other BSD-based features, and the AdaBoost-ELM shows better performance than traditional single recognition models.

Many pioneering approaches have verified the effectiveness of utilizing the global temporal and local object information for video understanding tasks and have achieved significant progress. However, existing methods utilize object detectors to extract all objects overall video frames. This may bring performance degradation due to the information redundancy both spatially and temporally. To address this problem, we propose an adaptive spatial location module for the video captioning task which dynamically predicts an important position of each video frame in the procedure of generating the description sentence. The proposed adaptive spatial location method not only makes our model focus on local object information, but also reduces time and memory consumption brought by the temporal redundancy in extensive video frames and improves the accuracy of generated description. Besides, we propose a balanced loss function to address the class imbalance problem existing in training data. The proposed balanced loss assigns different weight to each word of ground-truth sentence in the training process which can generate more diversified description sentences. Extensive experimental results on the MSVD and MSR-VTT dataset show that the proposed method achieves competitive performance compared to state-of-the-art methods.

Hyperspectral image (HSI) registers hundreds of spectral bands, whose intraclass variability and interclass similarity are resourceful information to be mined. Intraclass variability reflects the nonuniform and redundancy of the spatial and semantic features extracted from HSI. Interclass similarity represents the inherent relationship between adjacent features and snapshots. Existing models extract the superficial correlation representation for HSI to tackle the classification task but fail to embed the interclass and intraclass correlations due to these models' intrinsic bottlenecks. Confronting the challenges of capturing interrelation for complex data in practice, we propose a Context-Aware Attentional Graph U-Net (CAGU) to improve these two modes of representation, which is more flexible in feature enhancement. In this method, attentional Graph U-Net is capable of extracting the intraclass embeddings within a non-Euclidean space by combining similar distributing feature vertices. The gated recurrent unit (GRU) is another critical component of our model to capture the context-aware dynamic interclass embeddings. Extensive experiments demonstrate that our model can efficiently outperform state-of-the-art methods across-the-board on five wide-adopted public data sets, namely, Pavia University, Indian Pines, Salinas Scene-show, Houston 2013, and Houston 2018, on par with the same scale of model parameters.

Reliable network-policy specification requires abstractions that can naturally model policies together with rigorous formal foundations to reason about these policies. Current specifications satisfy one of these requirements or the other, but not both. A Metagraph is a generalized graph theoretic structure that overcomes this limitation. They are a natural way of expressing high-level end-to-end network policies. The rich formal foundations provided by metagraph algebra help analyze important network-policy properties such as reachability, redundancy and consistency. These features make metagraphs a clear choice for modeling and reasoning about policies in Formally-Verifiable Policy-Defined Networking (FV-PDN): a network-programming paradigm that has verifiability built-in. In this paper, we demonstrate the use of metagraphs in policy specification by modeling and analyzing real policies from a large university network. We show their benefit in FV-PDN by developing a prototype solution which automatically refines metagraph-based high-level policies to device configurations and deploys them to a SDN-based emulated network.

A massive core computing architecture is developed for accelerating arbitrary calculations in fully parallel with high speed and low cost. The proposed architecture is reconfigurable in fine-grained (arbitrary functions), mid-grained (flexible function feature, accuracy, and number of operands), and coarse-grained (organization of cores). By implementing a large scale of novel bisection neural network (BNN) on hardware, the re-configuration is conducted by partitioning entire BNN into any specific pieces without redundancy. Each piece of BNN retrieves the arbitrary function approximately. By reconfiguring the BNN topology in software, we can easily adjust dimensions of the computing kernel without rewiring, and achieve a wide range of trade-offs between accuracy and efficiency in hardware. In this manner, the multi-grained reconfigurable accelerator (MuGRA) is achieved. Since MuGRA is flexible in all grained levels, various configurations for each validation are demonstrated with rich options of performance-cost matrix. From the FPGA implementation results, compared with other traditional function approximation methods, our method provides fewer parameter storage requirements. The comparison against related works proves that our accelerator effectively reduces the calculation latency with slight accuracy loss.

Reliability requirement assurance is an important quality of service (QoS) for workflow execution in cloud-based services. For a workflow with a reliability requirement, the enough replication for redundancy minimization (ERRM) and quantitative fault-tolerance with minimum execution cost + (QFEC+) algorithms are state-of-the-art algorithms to reduce the redundancy and cost, respectively. In this work, we define the reliability increment ratio (RIR) and propose the redundancy minimization using RIR (R_RIR) algorithm. In addition, we introduce the geometric mean and propose the cost reduction using geometric mean (C_GM) algorithm based on redundancy minimization. Experimental results show the proposed R_RIR and C_GM algorithms are superior to state-of-the-art algorithms: (1) although both R_RIR and ERRM show the same redundancy results, R_RIR is proven to generate minimal redundancy, whereas ERRM cannot; (2) R_RIR only consumes a few seconds to achieve minimal redundancy for large-scale workflows, and it has much higher time efficiency than ERRM; and (3) C_GM generates less cost than QFEC+ in a large part of cases.

We address the problem of storing and analyzing large datasets of passenger trips over public transportation networks that are of interest to network administrators trying to balance transportation offers (e.g., frequency of vehicles) according to the historical demand. We exploit the fact that all passenger trips made within the same vehicle share the same trajectories to reduce their redundancy and provide a representation, based on well-known compact data structures, that not only reduces the space requirements of the original passenger’s trajectories but also efficiently supports querying. Our solution uses two complementary representations: T-Matrices which excels at querying the aggregated network load, and TTCTR which represents all passenger trips and aims at counting the trips following a given pattern (i.e., how many passengers started/ended a trip at a given location or moved from a given location to another). In addition, we propose XCTR, a variant of TTCTR, which efficiently answers a wider range of queries at the cost of a moderate performance loss for some queries and some space overhead. Overall, our representation can handle a dataset of ten million trips within approximately 65% of its original size while supporting a wide range of queries in the order of microseconds.

The key to efficient person search is jointly localizing pedestrians and learning discriminative representation for person re-identification (re-ID). Some recently developed models are built with separate detection and re-ID branches on top of shared region feature extraction networks. There are two factors that are detrimental to re-ID feature learning. One is the background information redundancy resulting from the large receptive field of neurons. The other is the body part missing and background clutter caused by inaccurate localization. In this work, a bottom-up fusion (BUF) subnet is proposed to fuse the bounding box features pooled from multiple network stages. With a few parameters introduced, BUF leverages the multi-level features with various sizes of receptive fields to mitigate the background-bias problem. To further suppress the non-pedestrian regions, the newly introduced segmentation head generates a foreground probability map as guidance for the network to focus on the foreground regions. The resulting foreground attention module (FAM) enhances the foreground features. Moreover, for robust feature learning in practical person search, we propose to adaptively smooth the labels of the pedestrian boxes with consideration of the detection quality. Extensive experiments on PRW and CUHK-SYSU validate the effectiveness of the proposals. Our Bottom-Up Foreground-Aware Feature Fusion (BUFF) network with ALS achieves considerable gains over the state-of-the-art on PRW and competitive performance on CUHK-SYSU.