Search

Two new species of the genus Dugesia from Southern China are described by applying an integrative approach, including morphological, karyological, histological, and molecular information. In the molecular phylogenetic tree, the two new species, Dugesia pendula Chen & Dong, sp. nov. and Dugesia musculosa Chen & Dong, sp. nov., fall into an Eastern Palearctic/Oriental clade and an Oriental/Australasian clade, respectively, while sharing only a rather distant relationship. The separate specific status of the two new species is supported also by their genetic distances. Dugesia pendula is characterized by the following features: symmetrical openings of the oviducts into the bursal canal, a duct between seminal vesicle and diaphragm, small diaphragm, dorsally located seminal vesicle, a penis papilla suspended from the dorsal wall of the male atrium, and mixoploid karyotype with diploid complements of 2n = 2x = 14 + 0 − 1 B-chromosome and triploid complements of 2n = 3x = 21 + 0 − 1 B-chromosome, with all chromosomes being metacentric. Dugesia musculosa is characterized by the following features: asymmetrical openings of the oviducts into the bursal canal; a ventrally displaced ejaculatory duct with a terminal opening; two diaphragms; a bursal canal provided with a strong, thick layer of circular muscle, which extends from the copulatory bursa to the common atrium and gonoduct; the left vas deferens opening at the midlateral wall of the seminal vesicle, while the right sperm duct opens at the dorsolateral wall of the seminal vesicle; and karyotype consisting of complicated diploid and aneuploid mosaicism, with diploid complements of 2n = 2x = 16 and 2n = 2x = 16 − 17th-18th, with all chromosomes being metacentric. The uncommon karyotypes, combined with the asexual reproduction of aneuploid animals, are evaluated in the context of the relationship between ploidy levels and reproductive modalities in the genus Dugesia.

Jiahui Ma,1– 4,&ast; Xue Yang,5,&ast; Zhiming Liu,1– 4 Hao Fu,1– 4 Sizhou Fan,1– 4 Kai Wang,1– 4 Yan Li,1– 4 Lvzhen Huang,1– 4 Mingwei Zhao1– 4 1Department of Ophthalmology, Peking University People’s Hospital, Beijing, People’s Republic of China; 2Eye Diseases and Optometry Institute, Peking University People’s Hospital, Beijing, People’s Republic of China; 3Beijing Key Laboratory of Diagnosis and Therapy of Retinal and Choroid Diseases, Beijing, People’s Republic of China; 4College of Optometry, Peking University Health Science Center, Beijing, People’s Republic of China; 5Department of Ophthalmology, Peking University International Hospital, Beijing, People’s Republic of China&ast;These authors contributed equally to this workCorrespondence: Kai Wang; Yan Li, Email wang_kai@bjmu.edu.cn; 13801153660@163.comPurpose: To investigate the impact of vergence dysfunction on myopia progression in children with Defocus incorporated multiple segments (DIMS) spectacle lenses.Patients and Methods: We retrospectively enrolled children prescribed DIMS spectacle lenses to slow myopic progression. Baseline vergence dysfunction was determined according to phoria at distance and near. Axial length (AL) measurement and cycloplegic subjective refraction were performed before fitting the lenses and at six-month and one-year follow-ups. The six-month and one-year AL and spherical equivalent (SE) change from baseline were calculated and compared in subgroups stratified with the type of vergence dysfunction.Results: Two hundred and ninety-two myopic children were included. Significant AL elongation and SE progression were observed at six months and one year (P < 0.05 for all comparisons). Multiple regression demonstrated that AL elongation at six months (P < 0.001) and one year (P < 0.001) was negatively correlated with age, and SE progression at six months was associated with age (P = 0.002). The AL elongation at six months in children

In the one-class recommendation problem, it's required to make recommendations basing on users' implicit feedback, which is inferred from their action and inaction. Existing works obtain representations of users and items by encoding positive and negative interactions observed from training data. However, these efforts assume that all positive signals from implicit feedback reflect a fixed preference intensity, which is not realistic. Consequently, representations learned with these methods usually fail to capture informative entity features that reflect various preference intensities. In this paper, we propose a multi-tasking framework taking various preference intensities of each signal from implicit feedback into consideration. Representations of entities are required to satisfy the objective of each subtask simultaneously, making them more robust and generalizable. Furthermore, we incorporate attentive graph convolutional layers to explore high-order relationships in the user-item bipartite graph and dynamically capture the latent tendencies of users toward the items they interact with. Experimental results show that our method performs better than state-of-the-art methods by a large margin on three large-scale real-world benchmark datasets., Comment: RecSys 2020 (ACM Conference on Recommender Systems 2020)

Document representation is the core of many NLP tasks on machine understanding. A general representation learned in an unsupervised manner reserves generality and can be used for various applications. In practice, sentiment analysis (SA) has been a challenging task that is regarded to be deeply semantic-related and is often used to assess general representations. Existing methods on unsupervised document representation learning can be separated into two families: sequential ones, which explicitly take the ordering of words into consideration, and non-sequential ones, which do not explicitly do so. However, both of them suffer from their own weaknesses. In this paper, we propose a model that overcomes difficulties encountered by both families of methods. Experiments show that our model outperforms state-of-the-art methods on popular SA datasets and a fine-grained aspect-based SA by a large margin., Comment: International ACM SIGIR Conference 2019

Recent advances in Out-of-Distribution (OOD) Detection is the driving force behind safe and reliable deployment of Convolutional Neural Networks (CNNs) in real world applications. However, existing studies focus on OOD detection through confidence score and deep generative model-based methods, without considering the impact of DNN structures, especially dense connectivity in architecture fabrications. In addition, existing outlier detection approaches exhibit high variance in generalization performance, lacking stability and confidence in evaluating and ranking different outlier detectors. In this work, we propose a novel paradigm, Dense Connectivity Search of Outlier Detector (DCSOD), that automatically explore the dense connectivity of CNN architectures on near-OOD detection task using Neural Architecture Search (NAS). We introduce a hierarchical search space containing versatile convolution operators and dense connectivity, allowing a flexible exploration of CNN architectures with diverse connectivity patterns. To improve the quality of evaluation on OOD detection during search, we propose evolving distillation based on our multi-view feature learning explanation. Evolving distillation stabilizes training for OOD detection evaluation, thus improves the quality of search. We thoroughly examine DCSOD on CIFAR benchmarks under OOD detection protocol. Experimental results show that DCSOD achieve remarkable performance over widely used architectures and previous NAS baselines. Notably, DCSOD achieves state-of-the-art (SOTA) performance on CIFAR benchmark, with AUROC improvement of $\sim$1.0%.

Detection of out-of-distribution (OOD) samples is crucial for safe real-world deployment of machine learning models. Recent advances in vision language foundation models have made them capable of detecting OOD samples without requiring in-distribution (ID) images. However, these zero-shot methods often underperform as they do not adequately consider ID class likelihoods in their detection confidence scoring. Hence, we introduce CLIPScope, a zero-shot OOD detection approach that normalizes the confidence score of a sample by class likelihoods, akin to a Bayesian posterior update. Furthermore, CLIPScope incorporates a novel strategy to mine OOD classes from a large lexical database. It selects class labels that are farthest and nearest to ID classes in terms of CLIP embedding distance to maximize coverage of OOD samples. We conduct extensive ablation studies and empirical evaluations, demonstrating state of the art performance of CLIPScope across various OOD detection benchmarks.

The ambiguous appearance, tiny scale, and fine-grained classes of objects in remote sensing imagery inevitably lead to the noisy annotations in category labels of detection dataset. However, the effects and treatments of the label noises are underexplored in modern oriented remote sensing object detectors. To address this issue, we propose a robust oriented remote sensing object detection method through dynamic loss decay (DLD) mechanism, inspired by the two phase ``early-learning'' and ``memorization'' learning dynamics of deep neural networks on clean and noisy samples. To be specific, we first observe the end point of early learning phase termed as EL, after which the models begin to memorize the false labels that significantly degrade the detection accuracy. Secondly, under the guidance of the training indicator, the losses of each sample are ranked in descending order, and we adaptively decay the losses of the top K largest ones (bad samples) in the following epochs. Because these large losses are of high confidence to be calculated with wrong labels. Experimental results show that the method achieves excellent noise resistance performance tested on multiple public datasets such as HRSC2016 and DOTA-v1.0/v2.0 with synthetic category label noise. Our solution also has won the 2st place in the "fine-grained object detection based on sub-meter remote sensing imagery" track with noisy labels of 2023 National Big Data and Computing Intelligence Challenge.

Localizing text in low-light environments is challenging due to visual degradations. Although a straightforward solution involves a two-stage pipeline with low-light image enhancement (LLE) as the initial step followed by detector, LLE is primarily designed for human vision instead of machine and can accumulate errors. In this work, we propose an efficient and effective single-stage approach for localizing text in dark that circumvents the need for LLE. We introduce a constrained learning module as an auxiliary mechanism during the training stage of the text detector. This module is designed to guide the text detector in preserving textual spatial features amidst feature map resizing, thus minimizing the loss of spatial information in texts under low-light visual degradations. Specifically, we incorporate spatial reconstruction and spatial semantic constraints within this module to ensure the text detector acquires essential positional and contextual range knowledge. Our approach enhances the original text detector's ability to identify text's local topological features using a dynamic snake feature pyramid network and adopts a bottom-up contour shaping strategy with a novel rectangular accumulation technique for accurate delineation of streamlined text features. In addition, we present a comprehensive low-light dataset for arbitrary-shaped text, encompassing diverse scenes and languages. Notably, our method achieves state-of-the-art results on this low-light dataset and exhibits comparable performance on standard normal light datasets. The code and dataset will be released.

In recent years, increasing attention has been devoted to semi empirical, data-driven models to tackle some aspects of the complex and still largely debated topic of galaxy formation and evolution. We here present a new semi empirical model whose marking feature is simplicity: it relies on solely two assumptions, one initial condition and two free parameters. Galaxies are connected to evolving dark matter haloes through abundance matching between specific halo accretion rate (sHAR) and specific star formation rate (sSFR). Quenching is treated separately, in a fully empirical way, to marginalize over quiescent galaxies and test our assumption on the sSFR evolution without contaminations from passive objects. Our flexible and transparent model is able to reproduce the observed stellar mass functions up to $z\sim 5$, giving support to our hypothesis of a monotonic relation between sHAR and sSFR. We then exploit the model to test a hypothesis on morphological evolution of galaxies. We attempt to explain the bulge/disk bimodality in terms of the two halo accretion modes: fast and slow accretion. Specifically, we speculate that bulge/spheroidal components might form during the early phase of fast halo growth, while disks form during the later phase of slow accretion. We find excellent agreement with both the observational bulge and elliptical mass functions., Comment: 22 pages, 13 Figures

Friction drive and wear control is a tough issue for linear standing-wave ultrasonic motors with intermittent contact and impact friction. For the widely recognized reduction of friction/wear, minimum quantity lubrication was adopted to improve the output performances and services for motors through friction regulation. Given different preload and driving voltages, the mechanical characteristics of motors with minimal quantity lubrication were investigated using a homemade test rig. Results show that output performances and driving efficiency under film lubrication differ from those of dry friction. The optimized driving voltage was reduced by 31.5% and the minimum startup voltage was reduced by 41.67% using film lubrication. Additionally, the output speed increased by 26.29%, and thrust decreased by 41.26% under uniform exciting conditions (e.g., 150 V at 39.14 kHz). The existence of film lubrication broadens the effective frictional contact boundary, and effective friction contribution enhances the driving efficiency (the maximum efficiency of motors increased by 14%). Furthermore, the singularity of the effect of preload is significantly improved after lubrication, and the friction interface of the stator/slider becomes more controllable. Suitable lubrication is critical to the improvement of startup performance and prone to realize low-voltage driving, and the combination of lubrication regulation and wear inhibition is conducive to the durability and reliability of motors. This study provides an additional alternative for performance improvement of linear standing-wave motors apart from frictional materials. © 2023 Society of Tribologists and Lubrication Engineers.

Hao Fu,1 Ping Li,2 Qianchao Xing,3 Hui Jiang,1 Hangshuo Sui4 1Nutrition Department, Affiliated Hospital of Chengde Medical University, Chengde, Heibei, People’s Republic of China; 2Gastroenterology, Affiliated Hospital of Chengde Medical University, Chengde, Heibei People’s Republic of China; 3Radiology Department, Affiliated Hospital of Chengde Medical University, Chengde, Heibei, People’s Republic of China; 4Nutrition Department, Chengde Central Hospital, Chengde, Heibei, People’s Republic of ChinaCorrespondence: Hangshuo Sui, Nutrition Department, Chengde Central Hospital, No. 11, Guangren Street, Chengde, Heibei, 067000, People’s Republic of China, Tel +86 0314 2028780, Email xyjw05@cdmc.edu.cnObjective: The Global Leadership Initiative on Malnutrition (GLIM) has proposed criteria for the diagnosis of malnutrition, one of which is reduced muscle mass. Computed tomography (CT) assessment of psoas muscle area (PMA) has been used to estimate muscle mass in patients, including those with acute pancreatitis (AP). The present study aimed to define the cutoff value of PMA indicative of reduced muscle mass in patients with AP and to assess the impact of reduced muscle mass on the severity and early complications of AP.Methods: Clinical data of 269 patients with AP were analyzed retrospectively. The severity of AP was determined according to the revised Atlanta classification. PMA was evaluated by CT and used to calculate the psoas muscle index (PMI). Cutoff values for reduced muscle mass were calculated and validated. Logistic regression analysis was performed to assess the relationship between PMA and the severity of AP.Results: PMA was a better indicator of reduced muscle mass than PMI, with cutoff values of 11.50 cm2 for men and 8.22 cm2 for women. Rates of local complications, splenic vein thrombosis, and organ failure were significantly higher in AP patients with low than high PMA (all p < 0.05). PMA showed good ability to predict splenic vein thrombos

Enduring surface technologies draw much attention to improving friction performance and prolonging the lifespan of multi-alternative contact pairs. Laser surface texturing is smart to modify effectively the microscopic surface geometries and mechanical performances for the service's improvement of friction pair. This study explored the formation mechanisms and morphology evolution of hierarchical microtextures, with a focus on the thermal field and phase transformation resulting from the laser heating effect on the alloy surface. The controlling variates of laser machining were analyzed considering their influences on microtextures' height and diameter, the pulse numbers are 3 times and 1.7 times of the unit laser power, 81 times and 82.5 times of the unit pulse width. We contributed to the development of laser manufacturing techniques for creating hierarchical microtextures' controllable morphology and smart surface design for tribology engineering and energy management applications. © 2023 The Society of Manufacturing Engineers

The social robot navigation is an open and challenging problem. In existing work, separate modules are used to capture spatial and temporal features, respectively. However, such methods lead to extra difficulties in improving the utilization of spatio-temporal features and reducing the conservative nature of navigation policy. In light of this, we present a spatio-temporal transformer-based policy optimization algorithm to enhance the utilization of spatio-temporal features, thereby facilitating the capture of human-robot interactions. Specifically, this paper introduces a gated embedding mechanism that effectively aligns the spatial and temporal representations by integrating both modalities at the feature level. Then Transformer is leveraged to encode the spatio-temporal semantic information, with hope of finding the optimal navigation policy. Finally, a combination of spatio-temporal Transformer and self-adjusting policy entropy significantly reduces the conservatism of navigation policies. Experimental results demonstrate the effectiveness of the proposed framework, where our method shows superior performance., Comment: The duplication rate is too high and the manuscript needs to be withdrawn

Embedding based retrieval has seen its usage in a variety of search applications like e-commerce, social networking search etc. While the approach has demonstrated its efficacy in tasks like semantic matching and contextual search, it is plagued by the problem of uncontrollable relevance. In this paper, we conduct an analysis of embedding-based retrieval launched in early 2021 on our social network search engine, and define two main categories of failures introduced by it, integrity and junkiness. The former refers to issues such as hate speech and offensive content that can severely harm user experience, while the latter includes irrelevant results like fuzzy text matching or language mismatches. Efficient methods during model inference are further proposed to resolve the issue, including indexing treatments and targeted user cohort treatments, etc. Though being simple, we show the methods have good offline NDCG and online A/B tests metrics gain in practice. We analyze the reasons for the improvements, pointing out that our methods are only preliminary attempts to this important but challenging problem. We put forward potential future directions to explore.

In-utero fetal MRI is emerging as an important tool in the diagnosis and analysis of the developing human brain. Automatic segmentation of the developing fetal brain is a vital step in the quantitative analysis of prenatal neurodevelopment both in the research and clinical context. However, manual segmentation of cerebral structures is time-consuming and prone to error and inter-observer variability. Therefore, we organized the Fetal Tissue Annotation (FeTA) Challenge in 2021 in order to encourage the development of automatic segmentation algorithms on an international level. The challenge utilized FeTA Dataset, an open dataset of fetal brain MRI reconstructions segmented into seven different tissues (external cerebrospinal fluid, gray matter, white matter, ventricles, cerebellum, brainstem, deep gray matter). 20 international teams participated in this challenge, submitting a total of 21 algorithms for evaluation. In this paper, we provide a detailed analysis of the results from both a technical and clinical perspective. All participants relied on deep learning methods, mainly U-Nets, with some variability present in the network architecture, optimization, and image pre- and post-processing. The majority of teams used existing medical imaging deep learning frameworks. The main differences between the submissions were the fine tuning done during training, and the specific pre- and post-processing steps performed. The challenge results showed that almost all submissions performed similarly. Four of the top five teams used ensemble learning methods. However, one team's algorithm performed significantly superior to the other submissions, and consisted of an asymmetrical U-Net network architecture. This paper provides a first of its kind benchmark for future automatic multi-tissue segmentation algorithms for the developing human brain in utero.

Robot crowd navigation has been gaining increasing attention and popularity in various practical applications. In existing research, deep reinforcement learning has been applied to robot crowd navigation by training policies in an online mode. However, this inevitably leads to unsafe exploration, and consequently causes low sampling efficiency during pedestrian-robot interaction. To this end, we propose an offline reinforcement learning based robot crowd navigation algorithm by utilizing pre-collected crowd navigation experience. Specifically, this algorithm integrates a spatial-temporal state into implicit Q-Learning to avoid querying out-of-distribution robot actions of the pre-collected experience, while capturing spatial-temporal features from the offline pedestrian-robot interactions. Experimental results demonstrate that the proposed algorithm outperforms the state-of-the-art methods by means of qualitative and quantitative analysis.

This paper proposes a data-efficient detection method for deep neural networks against backdoor attacks under a black-box scenario. The proposed approach is motivated by the intuition that features corresponding to triggers have a higher influence in determining the backdoored network output than any other benign features. To quantitatively measure the effects of triggers and benign features on determining the backdoored network output, we introduce five metrics. To calculate the five-metric values for a given input, we first generate several synthetic samples by injecting the input's partial contents into clean validation samples. Then, the five metrics are computed by using the output labels of the corresponding synthetic samples. One contribution of this work is the use of a tiny clean validation dataset. Having the computed five metrics, five novelty detectors are trained from the validation dataset. A meta novelty detector fuses the output of the five trained novelty detectors to generate a meta confidence score. During online testing, our method determines if online samples are poisoned or not via assessing their meta confidence scores output by the meta novelty detector. We show the efficacy of our methodology through a broad range of backdoor attacks, including ablation studies and comparison to existing approaches. Our methodology is promising since the proposed five metrics quantify the inherent differences between clean and poisoned samples. Additionally, our detection method can be incrementally improved by appending more metrics that may be proposed to address future advanced attacks., Comment: Published in the IEEE Transactions on Information Forensics and Security

For autonomous driving, traversability analysis is one of the most basic and essential tasks. In this paper, we propose a novel LiDAR-based terrain modeling approach, which could output stable, complete and accurate terrain models and traversability analysis results. As terrain is an inherent property of the environment that does not change with different view angles, our approach adopts a multi-frame information fusion strategy for terrain modeling. Specifically, a normal distributions transform mapping approach is adopted to accurately model the terrain by fusing information from consecutive LiDAR frames. Then the spatial-temporal Bayesian generalized kernel inference and bilateral filtering are utilized to promote the stability and completeness of the results while simultaneously retaining the sharp terrain edges. Based on the terrain modeling results, the traversability of each region is obtained by performing geometric connectivity analysis between neighboring terrain regions. Experimental results show that the proposed method could run in real-time and outperforms state-of-the-art approaches., Comment: accepted to Journal of Field Robotics

Discriminating the traversability of terrains is a crucial task for autonomous driving in off-road environments. However, it is challenging due to the diverse, ambiguous, and platform-specific nature of off-road traversability. In this paper, we propose a novel self-supervised terrain traversability learning framework, utilizing a contrastive label disambiguation mechanism. Firstly, weakly labeled training samples with pseudo labels are automatically generated by projecting actual driving experiences onto the terrain models constructed in real time. Subsequently, a prototype-based contrastive representation learning method is designed to learn distinguishable embeddings, facilitating the self-supervised updating of those pseudo labels. As the iterative interaction between representation learning and pseudo label updating, the ambiguities in those pseudo labels are gradually eliminated, enabling the learning of platform-specific and task-specific traversability without any human-provided annotations. Experimental results on the RELLIS-3D dataset and our Gobi Desert driving dataset demonstrate the effectiveness of the proposed method., Comment: 9 pages, 11 figures

Zinc metal anodes face several challenges, including the uncontrolled formation of dendrites, hydrogen evolution, and corrosion, which seriously hinder their application in practice. To address the above problems such as dendrite formation and corrosion, we present a simple and applicable immersion method that enables in situ formation of a zinc phytate (PAZ) coating on the surface of commercial Zn flakes via a substitution reaction. This protective coating mitigates corrosion of zinc flakes by the electrolyte, reduces the interfacial impedance, and accelerates the migration kinetics of zinc ions. Besides, this method can preferentially expose the (002) crystal plane with strong atomic bonding, which not only improves the corrosion resistance of the zinc flake, but can also guide the parallel deposition of zinc ions along the (002) crystal plane and reduce the formation of dendrites. Benefiting from the above advantages, the PAZ@Zn||Cu half-cell has shown over 900 cycles with average coulombic efficiency (CE) of 99.81% at 4 mA cm−2. Besides, the PAZ@Zn||PAZ@Zn symmetric cell operate stably for >1000 h at 5 mA cm−2 and >340 h at 10 mA cm−2. Furthermore, we demonstrated that this in situ chemical treatment enables the formation of a robust, well-bound protective coating. This method provides insights for advancing the commercialization of zinc anodes and other metal anodes.

Since the ($\beta$-deformed) hermitian one-matrix models can be represented as the integrated conformal field theory (CFT) expectation values, we construct the operators in terms of the generators of the Heisenberg algebra such that the constraints can be derived by inserting the constructed operators into the integrated expectation values. We also obtain the second order total derivative operators associating with the derived constraint operators and analyze their properties. We explore the intrinsic connection between the derived constraint operators and $W$-representations of some matrix models. For the Gaussian hermitian one-matrix model in the external field and $\beta$-deformed $N\times N$ complex matrix model, we investigate the superintegrability and derive the corresponding character expansions from their $W$-representations. Moreover a conjectured formula for the averages of Jack polynomials in the literature is proved., Comment: 24 pages. Revised version accepted for publication in Nuclear Physics B

Xiaolong Ma,1,&ast; Xiaodong Lv,1,&ast; Sihan Feng,1 Ruishan Liu,2,3 Hao Fu,2 Feng Gao,1 Hao Xu2 1Department of Respiratory Medicine, the First Hospital of Jiaxing (Affiliated Hospital of Jiaxing University), Jiaxing, People’s Republic of China; 2Collaborative Innovation Center for Diagnosis and Treatment of Infectious Diseases, State Key Laboratory for Diagnosis and Treatment of Infectious Diseases, the First Affiliated Hospital, College of Medicine, Zhejiang University, Hangzhou, People’s Republic of China; 3Department of Laboratory Medicine, the First Affiliated Hospital of Zhengzhou University, Zhengzhou, People’s Republic of China&ast;These authors have contributed equally to this workCorrespondence: Feng Gao, Department of Respiratory Medicine, the First Hospital of Jiaxing (Affiliated Hospital of Jiaxing University), No. 1882 South Zhonghuan Road, Jiaxing, 314000, People’s Republic of China, Tel +86 573 825 198 70, Fax +86 573 820 830 06, Email guti-gf@163.com Hao Xu, Collaborative Innovation Center for Diagnosis and Treatment of Infectious Diseases, State Key Laboratory for Diagnosis and Treatment of Infectious Diseases, the First Affiliated Hospital, College of Medicine, Zhejiang University, No. 79 Qing chun Road, Hangzhou, 310003, People’s Republic of China, Tel +86 571 872 364 23, Fax +86 571 872 364 21, Email xuhao0523@zju.edu.cnPurpose: To investigate the phenotypic and genomic characteristics of the multi-drug resistant and hypervirulent Klebsiella pneumoniae strain recovered from bacteremia.Methods: Antimicrobial susceptibility testing (AST) was performed by the microdilution method. Antimicrobial resistance genes, virulence-associated genes, multilocus sequence typing (MLST), and plasmid replicon were characterized by next-generation sequencing (NGS) and nanopore sequencing. S1 nuclease-pulsed field gel electrophoresis (S1-PFGE) and Southern blotting were performed to characterize the plasmid profile.Results: The hypervirulent c

This paper proposes an easy-to-compute upper bound for the overlap index between two probability distributions without requiring any knowledge of the distribution models. The computation of our bound is time-efficient and memory-efficient and only requires finite samples. The proposed bound shows its value in one-class classification and domain shift analysis. Specifically, in one-class classification, we build a novel one-class classifier by converting the bound into a confidence score function. Unlike most one-class classifiers, the training process is not needed for our classifier. Additionally, the experimental results show that our classifier can be accurate with only a small number of in-class samples and outperform many state-of-the-art methods on various datasets in different one-class classification scenarios. In domain shift analysis, we propose a theorem based on our bound. The theorem is useful in detecting the existence of domain shift and inferring data information. The detection and inference processes are both computation-efficient and memory-efficient. Our work shows significant promise toward broadening the applications of overlap-based metrics.

We propose a framework in which multiple entities collaborate to build a machine learning model while preserving privacy of their data. The approach utilizes feature embeddings from shared/per-entity feature extractors transforming data into a feature space for cooperation between entities. We propose two specific methods and compare them with a baseline method. In Shared Feature Extractor (SFE) Learning, the entities use a shared feature extractor to compute feature embeddings of samples. In Locally Trained Feature Extractor (LTFE) Learning, each entity uses a separate feature extractor and models are trained using concatenated features from all entities. As a baseline, in Cooperatively Trained Feature Extractor (CTFE) Learning, the entities train models by sharing raw data. Secure multi-party algorithms are utilized to train models without revealing data or features in plain text. We investigate the trade-offs among SFE, LTFE, and CTFE in regard to performance, privacy leakage (using an off-the-shelf membership inference attack), and computational cost. LTFE provides the most privacy, followed by SFE, and then CTFE. Computational cost is lowest for SFE and the relative speed of CTFE and LTFE depends on network architecture. CTFE and LTFE provide the best accuracy. We use MNIST, a synthetic dataset, and a credit card fraud detection dataset for evaluations.

Modeling the evolution of user preference is essential in recommender systems. Recently, dynamic graph-based methods have been studied and achieved SOTA for recommendation, majority of which focus on user's stable long-term preference. However, in real-world scenario, user's short-term preference evolves over time dynamically. Although there exists sequential methods that attempt to capture it, how to model the evolution of short-term preference with dynamic graph-based methods has not been well-addressed yet. In particular: 1) existing methods do not explicitly encode and capture the evolution of short-term preference as sequential methods do; 2) simply using last few interactions is not enough for modeling the changing trend. In this paper, we propose Long Short-Term Preference Modeling for Continuous-Time Sequential Recommendation (LSTSR) to capture the evolution of short-term preference under dynamic graph. Specifically, we explicitly encode short-term preference and optimize it via memory mechanism, which has three key operations: Message, Aggregate and Update. Our memory mechanism can not only store one-hop information, but also trigger with new interactions online. Extensive experiments conducted on five public datasets show that LSTSR consistently outperforms many state-of-the-art recommendation methods across various lines., Comment: 9 pages, 4 figures

In-utero fetal MRI is emerging as an important tool in the diagnosis and analysis of the developing human brain. Automatic segmentation of the developing fetal brain is a vital step in the quantitative analysis of prenatal neurodevelopment both in the research and clinical context. However, manual segmentation of cerebral structures is time-consuming and prone to error and inter-observer variability. Therefore, we organized the Fetal Tissue Annotation (FeTA) Challenge in 2021 in order to encourage the development of automatic segmentation algorithms on an international level. The challenge utilized FeTA Dataset, an open dataset of fetal brain MRI reconstructions segmented into seven different tissues (external cerebrospinal fluid, grey matter, white matter, ventricles, cerebellum, brainstem, deep grey matter). 20 international teams participated in this challenge, submitting a total of 21 algorithms for evaluation. In this paper, we provide a detailed analysis of the results from both a technical and clinical perspective. All participants relied on deep learning methods, mainly U-Nets, with some variability present in the network architecture, optimization, and image pre- and post-processing. The majority of teams used existing medical imaging deep learning frameworks. The main differences between the submissions were the fine tuning done during training, and the specific pre- and post-processing steps performed. The challenge results showed that almost all submissions performed similarly. Four of the top five teams used ensemble learning methods. However, one team's algorithm performed significantly superior to the other submissions, and consisted of an asymmetrical U-Net network architecture. This paper provides a first of its kind benchmark for future automatic multi-tissue segmentation algorithms for the developing human brain in utero., Comment: Results from FeTA Challenge 2021, held at MICCAI; Manuscript submitted

Collaborative filtering (CF) is one of the most successful and fundamental techniques in recommendation systems. In recent years, Graph Neural Network (GNN)-based CF models, such as NGCF [31], LightGCN [10] and GTN [9] have achieved tremendous success and significantly advanced the state-of-the-art. While there is a rich literature of such works using advanced models for learning user and item representations separately, item recommendation is essentially a link prediction problem between users and items. Furthermore, while there have been early works employing link prediction for collaborative filtering [5, 6], this trend has largely given way to works focused on aggregating information from user and item nodes, rather than modeling links directly. In this paper, we propose a new linkage (connectivity) score for bipartite graphs, generalizing multiple standard link prediction methods. We combine this new score with an iterative degree update process in the user-item interaction bipartite graph to exploit local graph structures without any node modeling. The result is a simple, non-deep learning model with only six learnable parameters. Despite its simplicity, we demonstrate our approach significantly outperforms existing state-of-the-art GNN-based CF approaches on four widely used benchmarks. In particular, on Amazon-Book, we demonstrate an over 60% improvement for both Recall and NDCG. We hope our work would invite the community to revisit the link prediction aspect of collaborative filtering, where significant performance gains could be achieved through aligning link prediction with item recommendations., Comment: Accepted by Graph Learning Workshop at WWW'22

Most IoT systems involve IoT devices, communication protocols, remote cloud, IoT applications, mobile apps, and the physical environment. However, existing IoT security analyses only focus on a subset of all the essential components, such as device firmware, and ignore IoT systems' interactive nature, resulting in limited attack detection capabilities. In this work, we propose Iota, a logic programming-based framework to perform system-level security analysis for IoT systems. Iota generates attack graphs for IoT systems, showing all of the system resources that can be compromised and enumerating potential attack traces. In building Iota, we design novel techniques to scan IoT systems for individual vulnerabilities and further create generic exploit models for IoT vulnerabilities. We also identify and model physical dependencies between different devices as they are unique to IoT systems and are employed by adversaries to launch complicated attacks. In addition, we utilize NLP techniques to extract IoT app semantics based on app descriptions. To evaluate vulnerabilities' system-wide impact, we propose two metrics based on the attack graph, which provide guidance on fortifying IoT systems. Evaluation on 127 IoT CVEs (Common Vulnerabilities and Exposures) shows that Iota's exploit modeling module achieves over 80% accuracy in predicting vulnerabilities' preconditions and effects. We apply Iota to 37 synthetic smart home IoT systems based on real-world IoT apps and devices. Experimental results show that our framework is effective and highly efficient. Among 27 shortest attack traces revealed by the attack graphs, 62.8% are not anticipated by the system administrator. It only takes 1.2 seconds to generate and analyze the attack graph for an IoT system consisting of 50 devices., Comment: This manuscript has been accepted by IoTDI 2022

(Abridged) We study the galaxy mass-size relation in CARLA spectroscopically confirmed clusters at $1.410.5$ are systematically $\gtrsim 0.2-0.3~{\rm dex}$ larger than field ETGs. The passive ETG average size evolution is slower at $1

The relative roles of mergers and star formation in regulating galaxy growth are still a matter of intense debate. We here present our DECODE, a new Discrete statistical sEmi-empiriCal mODEl specifically designed to predict rapidly and efficiently, in a full cosmological context, galaxy assembly and merger histories for any given input stellar mass-halo mass (SMHM) relation. DECODE generates object-by-object dark matter merger trees (hence discrete) from accurate subhalo mass and infall redshift probability functions (hence statistical) for all subhaloes, including those residing within other subhaloes, with virtually no resolution limits on mass or volume. Merger trees are then converted into galaxy assembly histories via an input, redshift dependent SMHM relation, which is highly sensitive to the significant systematics in the galaxy stellar mass function and on its evolution with cosmic time. DECODE can accurately reproduce the predicted mean galaxy merger rates and assembly histories of hydrodynamic simulations and semi-analytic models, when adopting in input their SMHM relations. In the present work we use DECODE to prove that only SMHM relations implied by stellar mass functions characterized by large abundances of massive galaxies and significant redshift evolution, at least at $M_\star \gtrsim 10^{11} \, M_\odot$, can simultaneously reproduce the local abundances of satellite galaxies, the galaxy (major merger) pairs since $z \sim 3$, and the growth of Brightest Cluster Galaxies. The same models can also reproduce the local fraction of elliptical galaxies, on the assumption that these are strictly formed by major mergers, but not the full bulge-to-disc ratio distributions, which require additional processes., Comment: MNRAS, accepted, 29 pages, 25 figures

Accurate segmentation of Anatomical brain Barriers to Cancer spread (ABCs) plays an important role for automatic delineation of Clinical Target Volume (CTV) of brain tumors in radiotherapy. Despite that variants of U-Net are state-of-the-art segmentation models, they have limited performance when dealing with ABCs structures with various shapes and sizes, especially thin structures (e.g., the falx cerebri) that span only few slices. To deal with this problem, we propose a High and Multi-Resolution Network (HMRNet) that consists of a multi-scale feature learning branch and a high-resolution branch, which can maintain the high-resolution contextual information and extract more robust representations of anatomical structures with various scales. We further design a Bidirectional Feature Calibration (BFC) block to enable the two branches to generate spatial attention maps for mutual feature calibration. Considering the different sizes and positions of ABCs structures, our network was applied after a rough localization of each structure to obtain fine segmentation results. Experiments on the MICCAI 2020 ABCs challenge dataset showed that: 1) Our proposed two-stage segmentation strategy largely outperformed methods segmenting all the structures in just one stage; 2) The proposed HMRNet with two branches can maintain high-resolution representations and is effective to improve the performance on thin structures; 3) The proposed BFC block outperformed existing attention methods using monodirectional feature calibration. Our method won the second place of ABCs 2020 challenge and has a potential for more accurate and reasonable delineation of CTV of brain tumors., Comment: 11 pages, 6 figures, Accepted by IEEE JBHI

Yuzhi Zhang,1,2 Hao Fu,1,2 Yongtao Zhang,1,2 Dongdong Wang,1,2 Dan Zhao,1– 3 Jiachan Zhang,1– 3 Meng Li,1,2 Changtao Wang1– 3 1Beijing Key Lab of Plant Resource Research and Development, College of Chemistry and Materials Engineering, Beijing Technology and Business University, Beijing, People’s Republic of China; 2Institute of Cosmetic Regulatory Science, Beijing Technology and Business University, Beijing, People’s Republic of China; 3Beijing Advanced Innovation Center for Food Nutrition and Human Health, Beijing Technology and Business University, Beijing, People’s Republic of ChinaCorrespondence: Meng Li; Changtao Wang, Beijing Technology and Business University, Beijing, 100048, People’s Republic of China, Tel +86 10-68984917, Fax +86 10-68984917, Email limeng@btbu.edu.cn; wangct@th.btbu.edu.cnObjective: To evaluate the efficacy of the dandelion fermentation broth in repairing UVB-induced skin inflammation.Methods: Detection of active ingredients in dandelion fermentation broth and water extract. The antioxidant capacity of dandelion fermentation broth was investigated by in vitro antioxidant experiments. The influence of the broth on the content of inflammatory factors interleukin-6 (IL-6), interleukin-8 (IL-8) and interleukin-1β (IL-1β), and tumor necrosis factor (TNF-α), in human immortalized epidermal cells (HaCaT) is discussed on the basis of a UVB-induced HaCaT damage model. The effects of the broth on the contents of skin barrier-related proteins kallikrein-7 (KLK-7), filaggrin (FLG) and aquaporin (AQP3) in the UVB-induced damage and repair of the HaCaT mechanism are also comprehensively discussed. The effect of DF on the activation of MAPK pathway proteins was detected by PCR. A chicken embryo chorioallantoic membrane test is used to explore the safety of the dandelion fermentation broth.Results: The results show that the dandelion fermentation broth is rich inTotal sugar, with good free radical scavenging ability and antioxidant effect

Velocity dispersion ($\sigma$) is a key driver for galaxy structure and evolution. We here present a comprehensive semi-empirical approach to compute $\sigma$ via detailed Jeans modelling assuming both a constant and scale-dependent mass-to-light ratio $M^*/L$. We compare with a large sample of local galaxies from MaNGA and find that both models can reproduce the Faber-Jackson (FJ) relation and the weak dependence of $\sigma$ on bulge-to-total ratio $B/T$ (for $B/T\gtrsim 0.25$). The dynamical-to-stellar mass ratio within $R\lesssim R_e$ can be fully accounted for by a gradient in $M^*/L$. We then build velocity dispersion evolutionary tracks $\sigma_{ap}[M^*,z]$ (within an aperture) along the main progenitor dark matter haloes assigning stellar masses, effective radii and Sersic indices via a variety of abundance matching and empirically motivated relations. We find: 1) clear evidence for downsizing in $\sigma_{ap}[M^*,z]$ along the progenitor tracks; 2) at fixed stellar mass $\sigma\propto(1+z)^{0.2-0.3}$ depending on the presence or not of a gradient in $M^*/L$. We extract $\sigma_{ap}[M^*,z]$ from the TNG50 hydrodynamic simulation and find very similar results to our models with constant $M^*/L$. The increasing dark matter fraction within $R_e$ tends to flatten the $\sigma_{ap}[M^*,z]$ along the progenitors at $z \gtrsim 1$ in constant $M^*/L$ models, while $\sigma_{ap}[M^*,z]$ have a steeper evolution in the presence of a stellar gradient. We then show that a combination of mergers and gas accretion are likely responsible for the constant or increasing $\sigma_{ap}[M^*,z]$ with time. Finally, our $\sigma_{ap}[M^*,z]$ are consistent with a nearly constant and steep $M_{bh}-\sigma$ relation at $z\lesssim 2$, with black hole masses derived from the $L_X-M^*$ relation., Comment: MNRAS accepted, 22 pages, 17 figures

Qiuting Mo, 1, 2 Hao Fu, 1, 2 Dan Zhao, 1– 3 Jiachan Zhang, 1– 3 Changtao Wang, 1– 3 Dongdong Wang, 1, 2 Meng Li 1, 2 1Beijing Key Laboratory of Plant Resource Research and Development, College of Chemistry and Materials Engineering, Beijing Technology and Business University, Beijing, People’s Republic of China; 2Institute of Cosmetic Regulatory Science, Beijing Technology and Business University, Beijing, People’s Republic of China; 3Beijing Advanced Innovation Center for Food Nutrition and Human Health, Beijing Technology and Business University, Beijing, People’s Republic of ChinaCorrespondence: Dongdong Wang; Meng Li Tel/Fax +86-010-68984917Email Wdd@btbu.edu.cn; limeng@btbu.edu.cnPurpose: Damage caused by oxidative stress leads to the premature aging of cells. Mogrosides, the main active components of Siraitia grosvenorii, have strong antioxidant activity; however, it is unclear whether mogroside V (MV) exerts these effects in skin cells. This was investigated in the present study by evaluating the protective effects of MV against oxidative damage induced by hydrogen peroxide (H 2O 2) in skin fibroblasts.Methods: Mouse skin fibroblasts (MSFs) were treated with H 2O 2 and cell viability, total antioxidant capacity, reactive oxygen species (ROS) production, malondialdehyde (MDA) content, and antioxidant enzyme activity were assessed.Results: Treatment with MV reduced the ROS level and MDA content in MSFs treated with H 2O 2. This was accompanied by increased superoxide dismutase (SOD), glutathione peroxidase (GSH-Px), and catalase (CAT) activities.Conclusion: MV reduces H 2O 2-induced oxidative stress and enhances endogenous antioxidant activity in skin fibroblasts. Thus, MV can potentially be used as an ingredient in anti-aging cosmetic products.Keywords: Siraitia grosvenorii, mogroside V, oxidative stress, antioxidant

The ability of a dialog system to express consistent language style during conversations has a direct, positive impact on its usability and on user satisfaction. Although previous studies have demonstrated that style transfer is feasible with a large amount of parallel data, it is often impossible to collect such data for different styles. In this paper, instead of manually constructing conversation data with a certain style, we propose a flexible framework that adapts a generic retrieval-based dialogue system to mimic the language style of a specified persona without any parallel data. Our approach is based on automatic generation of stylized data by learning the usage of jargon, and then rewriting the generic conversations to a stylized one by incorporating the jargon. In experiments we implemented dialogue systems with five distinct language styles, and the result shows our framework significantly outperforms baselines in terms of the average score of responses' relevance and style degree, and content diversity. A/B testing on a commercial chatbot shows that users are more satisfied with our system. This study demonstrates the feasibility of building stylistic dialogue systems by simple data augmentation.

For better user satisfaction and business effectiveness, more and more attention has been paid to the sequence-based recommendation system, which is used to infer the evolution of users' dynamic preferences, and recent studies have noticed that the evolution of users' preferences can be better understood from the implicit and explicit feedback sequences. However, most of the existing recommendation techniques do not consider the noise contained in implicit feedback, which will lead to the biased representation of user interest and a suboptimal recommendation performance. Meanwhile, the existing methods utilize item sequence for capturing the evolution of user interest. The performance of these methods is limited by the length of the sequence, and can not effectively model the long-term interest in a long period of time. Based on this observation, we propose a novel CTR model named denoising user-aware memory network (DUMN). Specifically, the framework: (i) proposes a feature purification module based on orthogonal mapping, which use the representation of explicit feedback to purify the representation of implicit feedback, and effectively denoise the implicit feedback; (ii) designs a user memory network to model the long-term interests in a fine-grained way by improving the memory network, which is ignored by the existing methods; and (iii) develops a preference-aware interactive representation component to fuse the long-term and short-term interests of users based on gating to understand the evolution of unbiased preferences of users. Extensive experiments on two real e-commerce user behavior datasets show that DUMN has a significant improvement over the state-of-the-art baselines. The code of DUMN model has been uploaded as an additional material.

Transformer-based models have led to significant innovation in classical and practical subjects as varied as speech processing, natural language processing, and computer vision. On top of the Transformer, attention-based end-to-end automatic speech recognition (ASR) models have recently become popular. Specifically, non-autoregressive modeling, which boasts fast inference and performance comparable to conventional autoregressive methods, is an emerging research topic. In the context of natural language processing, the bidirectional encoder representations from Transformers (BERT) model has received widespread attention, partially due to its ability to infer contextualized word representations and to enable superior performance for downstream tasks while needing only simple fine-tuning. Motivated by the success, we intend to view speech recognition as a downstream task of BERT, thus an ASR system is expected to be deduced by performing fine-tuning. Consequently, to not only inherit the advantages of non-autoregressive ASR models but also enjoy the benefits of a pre-trained language model (e.g., BERT), we propose a non-autoregressive Transformer-based end-to-end ASR model based on BERT. We conduct a series of experiments on the AISHELL-1 dataset that demonstrate competitive or superior results for the model when compared to state-of-the-art ASR systems.

To investigate the prevalence, probable mechanisms and serotype correlation of colistin resistance in clinical isolates of Salmonella from patients in China, Salmonella isolates were collected from fecal and blood samples of patients. In this study, 42.8% (136/318) clinical isolated Salmonella were resistant to colistin. MIC distribution for colistin at serotype level among the two most prevalent serotypes originating from humans in China indicated that Salmonella Enteritidis (83.9% resistance, 125/149) were significantly less susceptible than Salmonella Typhimurium (15.3% resistance, 9/59, P < 0.01). mcr genes and mutations in PmrAB confer little for rate of colistin resistant Salmonella isolated from human patients. Phylogenetic tree based on core-genome single nucleotide polymorphisms (SNPs) was separately by the serotypes and implied a diffused distribution of MICs in the same serotype isolates. Relatvie expression levels of colistin resistant related pmr genes were significantly higher in non-mcr colistin resistant S. Typhimurium than in colistin sensitive S. Typhimurium, but no discernable differences between colistin resistant and sensitive S. Enteritidis, indicating a different mechanism between colistin resistant S. Typhimurium and S. Enteritidis. In conclusion, colistin susceptibility and colistin resistant mechanism of clinical isolated Salmonella were closely associated with specific serotypes, at least in the two most prevalent serotype Enteritidis and Typhimurium. We suggest clinical microbiology laboratory interpreting Salmonella colistin MIC results in the serotype level., Funding Agencies|National Key R&D Program of China [2017YFC1600100]; National Natural Science Foundation of ChinaNational Natural Science Foundation of China (NSFC) [81702040]; National Science Foundation of Zhejiang province, China [LY20H190002]; Swedish Research Council for Environment, Agricultural Sciences and Spatial Planning (Formas)Swedish Research Council Formas [2016-00640]; Swedish Foundation for International Cooperate in Research and Higher Education (STINT) [CH2016-6707]

Measurements of the cosmic microwave background (CMB) spectral distortions (SDs) will open a new window on the very early universe, providing new information complementary to that gathered from CMB temperature and polarization anisotropies. In this paper, we study their synergy as a function of the characteristics of the considered experiments. In particular, we examine a wide range of sensitivities for possible SD measurements, spanning from FIRAS up to noise levels 1000 times better than PIXIE, and study their constraining power when combined with current or future CMB anisotropy experiments such as Planck or LiteBIRD plus CMB-S4. We consider a number of different cosmological models such as the $\Lambda$CDM, as well as its extensions with the running of the scalar spectral index, the decay or the annihilation of dark matter (DM) particles. While upcoming CMB anisotropy experiments will be able to decrease the uncertainties on inflationary parameters such as $A_s$ and $n_s$ by about a factor 2 in the $\Lambda$CDM case, we find that an SD experiment 100 times more sensitive than PIXIE (comparable to the proposed Super-PIXIE satellite) could potentially further contribute to constrain these parameters. This is even more significant in the case of the running of the scalar spectral index. Furthermore, as expected, constraints on DM particles decaying at redshifts probed by SDs will improve by orders of magnitude even with an experiment 10 times worse than PIXIE as compared to CMB anisotropies or Big Bang Nucleosynthesis bounds. On the contrary, DM annihilation constraints will not significantly improve over CMB anisotropy measurements. Finally, we forecast the constraints obtainable with sensitivities achievable either from the ground or from a balloon., Comment: 25+4 pages with 8 figures and 7 tables, published version

The lateral stability of ballasted track becomes more important because of the safety requirement under the demand of higher train speed and heavier axle load. To increase the lateral resistance of ballast bed, this paper proposes three types of new sleepers, frictional sleepers. The frictional sleepers are sleepers with different shapes of textures attached at the sleeper bottom. To study the application feasibility of the frictional sleepers, experimental tests (single sleeper pull-out test) and numerical simulation (discrete element modelling) are performed. The lateral resistances of the three types of frictional sleepers are compared with the traditional sleeper based on the experimental test, and the mechanism of the lateral resistance increase is revealed according to the numerical simulation. The results indicate that the frictional sleepers can increase the lateral resistance by 32% (maximum), due to the enhanced interaction between sleeper and ballast particles. More importantly, different types of frictional sleepers have different performances, and the optimal friction sleeper is confirmed. This study is helpful for the further research on sleeper design., Accepted Author Manuscript, Railway Engineering

COVID-19 is a severe global epidemic in human history. Even though there are particular medications and vaccines to curb the epidemic, tracing and isolating the infection source is the best option to slow the virus spread and reduce infection and death rates. There are three disadvantages to the existing contact tracing system: 1. User data is stored in a centralized database that could be stolen and tampered with, 2. User's confidential personal identity may be revealed to a third party or organization, 3. Existing contact tracing systems only focus on information sharing from one dimension, such as location-based tracing, which significantly limits the effectiveness of such systems. We propose a global COVID-19 information sharing and risk notification system that utilizes the Blockchain, Smart Contract, and Bluetooth. To protect user privacy, we design a novel Blockchain-based platform that can share consistent and non-tampered contact tracing information from multiple dimensions, such as location-based for indirect contact and Bluetooth-based for direct contact. Hierarchical smart contract architecture is also designed to achieve global agreements from users about how to process and utilize user data, thereby enhancing the data usage transparency. Furthermore, we propose a mechanism to protect user identity privacy from multiple aspects. More importantly, our system can notify the users about the exposure risk via smart contracts. We implement a prototype system to conduct extensive measurements to demonstrate the feasibility and effectiveness of our system., Comment: 11 pages, 7 figures, this work has been accepted by IEEE International Conference on Mobile Ad-Hoc and Smart Systems (MASS) 2021

As a massive number of the Internet of Things (IoT) devices are deployed, the security and privacy issues in IoT arouse more and more attention. The IoT attacks are causing tremendous loss to the IoT networks and even threatening human safety. Compared to traditional networks, IoT networks have unique characteristics, which make the attack detection more challenging. First, the heterogeneity of platforms, protocols, software, and hardware exposes various vulnerabilities. Second, in addition to the traditional high-rate attacks, the low-rate attacks are also extensively used by IoT attackers to obfuscate the legitimate and malicious traffic. These low-rate attacks are challenging to detect and can persist in the networks. Last, the attackers are evolving to be more intelligent and can dynamically change their attack strategies based on the environment feedback to avoid being detected, making it more challenging for the defender to discover a consistent pattern to identify the attack. In order to adapt to the new characteristics in IoT attacks, we propose a reinforcement learning-based attack detection model that can automatically learn and recognize the transformation of the attack pattern. Therefore, we can continuously detect IoT attacks with less human intervention. In this paper, we explore the crucial features of IoT traffics and utilize the entropy-based metrics to detect both the high-rate and low-rate IoT attacks. Afterward, we leverage the reinforcement learning technique to continuously adjust the attack detection threshold based on the detection feedback, which optimizes the detection and the false alarm rate. We conduct extensive experiments over a real IoT attack dataset and demonstrate the effectiveness of our IoT attack detection framework., Comment: 11 pages, 8 figures, 2 tables, to appear in the 21st IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks (IEEE WoWMoM 2020)

Internet of Things (IoT) has become the most promising technology for service automation, monitoring, and interconnection, etc. However, the security and privacy issues caused by IoT arouse concerns. Recent research focuses on addressing security issues by looking inside platform and apps. In this work, we creatively change the angle to consider security problems from a wireless context perspective. We propose a novel framework called IoTGaze, which can discover potential anomalies and vulnerabilities in the IoT system via wireless traffic analysis. By sniffing the encrypted wireless traffic, IoTGaze can automatically identify the sequential interaction of events between apps and devices. We discover the temporal event dependencies and generate the Wireless Context for the IoT system. Meanwhile, we extract the IoT Context, which reflects user's expectation, from IoT apps' descriptions and user interfaces. If the wireless context does not match the expected IoT context, IoTGaze reports an anomaly. Furthermore, IoTGaze can discover the vulnerabilities caused by the inter-app interaction via hidden channels, such as temperature and illuminance. We provide a proof-of-concept implementation and evaluation of our framework on the Samsung SmartThings platform. The evaluation shows that IoTGaze can effectively discover anomalies and vulnerabilities, thereby greatly enhancing the security of IoT systems., Comment: 9 pages, 11 figures, 3 tables, to appear in the IEEE International Conference on Computer Communications (IEEE INFOCOM 2020)

3D moving object detection is one of the most critical tasks in dynamic scene analysis. In this paper, we propose a novel Drosophila-inspired 3D moving object detection method using Lidar sensors. According to the theory of elementary motion detector, we have developed a motion detector based on the shallow visual neural pathway of Drosophila. This detector is sensitive to the movement of objects and can well suppress background noise. Designing neural circuits with different connection modes, the approach searches for motion areas in a coarse-to-fine fashion and extracts point clouds of each motion area to form moving object proposals. An improved 3D object detection network is then used to estimate the point clouds of each proposal and efficiently generates the 3D bounding boxes and the object categories. We evaluate the proposed approach on the widely-used KITTI benchmark, and state-of-the-art performance was obtained by using the proposed approach on the task of motion detection.

As the wide adoption of intelligent chatbot in human daily life, user demands for such systems evolve from basic task-solving conversations to more casual and friend-like communication. To meet the user needs and build emotional bond with users, it is essential for social chatbots to incorporate more human-like and advanced linguistic features. In this paper, we investigate the usage of a commonly used rhetorical device by human -- metaphor for social chatbot. Our work first designs a metaphor generation framework, which generates topic-aware and novel figurative sentences. By embedding the framework into a chatbot system, we then enables the chatbot to communicate with users using figurative language. Human annotators validate the novelty and properness of the generated metaphors. More importantly, we evaluate the effects of employing metaphors in human-chatbot conversations. Experiments indicate that our system effectively arouses user interests in communicating with our chatbot, resulting in significantly longer human-chatbot conversations.

Deep learning networks have shown promising performance for accurate object localization in medial images, but require large amount of annotated data for supervised training, which is expensive and expertise burdensome. To address this problem, we present a one-shot framework for organ and landmark localization in volumetric medical images, which does not need any annotation during the training stage and could be employed to locate any landmarks or organs in test images given a support (reference) image during the inference stage. Our main idea comes from that tissues and organs from different human bodies have a similar relative position and context. Therefore, we could predict the relative positions of their non-local patches, thus locate the target organ. Our framework is composed of three parts: (1) A projection network trained to predict the 3D offset between any two patches from the same volume, where human annotations are not required. In the inference stage, it takes one given landmark in a reference image as a support patch and predicts the offset from a random patch to the corresponding landmark in the test (query) volume. (2) A coarse-to-fine framework contains two projection networks, providing more accurate localization of the target. (3) Based on the coarse-to-fine model, we transfer the organ boundingbox (B-box) detection to locating six extreme points along x, y and z directions in the query volume. Experiments on multi-organ localization from head-and-neck (HaN) CT volumes showed that our method acquired competitive performance in real time, which is more accurate and 10^5 times faster than template matching methods with the same setting. Code is available: https://github.com/LWHYC/RPR-Loc., Comment: Early accepted by MICCAI 2021

The pre-training models such as BERT have achieved great results in various natural language processing problems. However, a large number of parameters need significant amounts of memory and the consumption of inference time, which makes it difficult to deploy them on edge devices. In this work, we propose a knowledge distillation method LRC-BERT based on contrastive learning to fit the output of the intermediate layer from the angular distance aspect, which is not considered by the existing distillation methods. Furthermore, we introduce a gradient perturbation-based training architecture in the training phase to increase the robustness of LRC-BERT, which is the first attempt in knowledge distillation. Additionally, in order to better capture the distribution characteristics of the intermediate layer, we design a two-stage training method for the total distillation loss. Finally, by verifying 8 datasets on the General Language Understanding Evaluation (GLUE) benchmark, the performance of the proposed LRC-BERT exceeds the existing state-of-the-art methods, which proves the effectiveness of our method.