查看更多>>摘要：The Internet of Things(IoT)has grown rapidly due to artificial intelligence driven edge computing.While enabling many new functions,edge computing devices expand the vulnerability surface and have become the target of malware attacks.Moreover,attackers have used advanced techniques to evade defenses by transforming their malware into functionality-preserving variants.We systematically analyze such evasion attacks and conduct a large-scale empirical study in this paper to evaluate their impact on security.More specifically,we focus on two forms of evasion attacks:obfuscation and adversarial attacks.To the best of our knowledge,this paper is the first to investigate and contrast the two families of evasion attacks systematically.We apply 10 obfuscation attacks and 9 adversarial attacks to 2870 malware examples.The obtained findings are as follows.(1)Commercial Off-The-Shelf(COTS)malware detectors are vulnerable to evasion attacks.(2)Adversarial attacks affect COTS malware detectors slightly more effectively than obfuscated malware examples.(3)Code similarity detection approaches can be affected by obfuscated examples and are barely affected by adversarial attacks.(4)These attacks can preserve the functionality of original malware examples.
查看更多>>摘要：Energy management in smart homes is one of the most critical problems for the Quality of Life(QoL)and preserving energy resources.One of the relevant issues in this subject is environmental contamination,which threatens the world's future.Green computing-enabled Artificial Intelligence(Al)algorithms can provide impactful solutions to this topic.This research proposes using one of the Recurrent Neural Network(RNN)algorithms known as Long Short-Term Memory(LSTM)to comprehend how it is feasible to perform the cloud/fog/edge-enabled prediction of the building's energy.Four parameters of power electricity,power heating,power cooling,and total power in an office/home in cold-climate cities are considered as our features in the study.Based on the collected data,we evaluate the LSTM approach for forecasting parameters for the next year to predict energy consumption and online monitoring of the model's performance under various conditions.Towards implementing the Al predictive algorithm,several existing tools are studied.The results have been generated through simulations,and we find them promising for future applications.
查看更多>>摘要：As the power demand in data centers is increasing,the power capacity of the power supply system has become an essential resource to be optimized.Although many data centers use power oversubscription to make full use of the power capacity,there are unavoidable power supply risks associated with it.Therefore,how to improve the data center power capacity utilization while ensuring power supply security has become an important issue.To solve this problem,we first define it and propose a risk evaluation metric called Weighted Power Supply Risk(WPSRisk).Then,a method,named Hybrid Genetic Algorithm with Ant Colony System(HGAACS),is proposed to improve power capacity utilization and reduce power supply risks by optimizing the server placement in the power supply system.HGAACS uses historical power data of each server to find a better placement solution by population iteration.HGAACS possesses not only the remarkable local search ability of Ant Colony System(ACS),but also enhances the global search capability by incorporating genetic operators from Genetic Algorithm(GA).To verify the performance of HGAACS,we experimentally compare it with five other placement algorithms.The experimental results show that HGAACS can perform better than other algorithms in both improving power utilization and reducing the risk of power supply system.
Jingyun ZhangWenjie ZhuByoung Jin AhnYongsheng Zhou...
174-184页
查看更多>>摘要：With the ever-increasing diversification of people's interests and preferences,artwork has become one of the most popular commodities or investment goods in E-commerce,and it increasingly attracts the attention of the public.Currently,many real-world or virtual artworks can be found in E-commerce,and finding a means to recommend them to appropriate users has become a significant task to alleviate the heavy burden on artwork selection decisions by users.Existing research mainly studies the problem of single-artwork recommendation while neglecting the more practical but more complex composite recommendation of artworks in E-commerce,which considerably influences the quality of experience of potential users,especially when they need to select a set of artworks instead of a single artwork.Inspired by this limitation,we put forward a novel composite recommendation approach to artworks by a user keyword-driven correlation graph search named ARTcom-rec.Through ARTcom-rec,the recommender system can output a set of artworks(e.g.,an artwork composite solution)in E-commerce by considering the keywords typed by a user to indicate his or her personalized preferences.Finally,we validate the feasibility of the ARTcom-rec approach by a set of simulated experiments on a real-world PW dataset.
查看更多>>摘要：Personalized recommendation plays a critical role in providing decision-making support for product and service analysis in the field of business intelligence.Recently,deep neural network-based sequential recommendation models gained considerable attention.However,existing approaches pay little attention to users'dynamically evolving interests,which are influenced by product attributes,especially product category.To overcome these challenges,we propose a dynamic personalized recommendation model:DynaPR.Specifically,we first embed product information and attribute information into a unified data space.Then,we exploit long short-term memory(LSTM)networks to characterize sequential behavior over multiple time periods and seize evolving interests by hierarchical LSTM networks.Finally,similarity values between users are measured through pairwise interest features,and personalized recommendation lists are generated.A series of experiments reveal the superiority of the proposed method compared with other advanced methods.
查看更多>>摘要：Super-resolution reconstruction in medical imaging has become more demanding due to the necessity of obtaining high-quality images with minimal radiation dose,such as in low-field magnetic resonance imaging(MRI).However,image super-resolution reconstruction remains a difficult task because of the complexity and high textual requirements for diagnosis purpose.In this paper,we offer a deep learning based strategy for reconstructing medical images from low resolutions utilizing Transformer and generative adversarial networks(T-GANs).The integrated system can extract more precise texture information and focus more on important locations through global image matching after successfully inserting Transformer into the generative adversarial network for picture reconstruction.Furthermore,we weighted the combination of content loss,adversarial loss,and adversarial feature loss as the final multi-task loss function during the training of our proposed model T-GAN.In comparison to established measures like peak signal-to-noise ratio(PSNR)and structural similarity index measure(SSIM),our suggested T-GAN achieves optimal performance and recovers more texture features in super-resolution reconstruction of MRI scanned images of the knees and belly.
查看更多>>摘要：All-inorganic perovskite(CsPbX3)nanocrystals(NCs)have recently been widely investigated as versatile solution-processable light-emitting materials.Due to its wide-bandgap nature,the all-inorganic perovskite NC Light-Emitting Diode(LED)is limited to the visible region(400-700 nm).A particularly difficult challenge lies in the practical application of perovskite NCs in the infrared-spectrum region.In this work,a 980 nm NIR all-inorganic perovskite NC LED is demonstrated,which is based on an efficient energy transfer from wide-bandgap materials(CsPbCl3 NCs)to ytterbium ions(Yb3+)as an NIR emitter doped in perovskite NCs.The optimized CsPbCI3 NC with 15 mol％Yb3+doping concentration has the strongest 980 nm photoluminescence(PL)peak,with a PL quantum yield of 63％.An inverted perovskite NC LED is fabricated with the structure of ITO/PEDOT:PSS/poly-TPD/CsPbCI3:15 mol％Yb3+NCs/TPBi/LiF/Al.The LED has an External Quantum Efficiency(EQE)of 0.2％,a Full Width at Half Maximum(FWHM)of 47 nm,and a maximum luminescence of 182 cd/m2.The introduction of Yb3+doping in perovskite NCs makes it possible to expand its working wavelength to near-infrared band for next-generation light sources and shows potential applications for optoelectronic integration.
查看更多>>摘要：The problem of imbalanced data classification learning has received much attention.Conventional classification algorithms are susceptible to data skew to favor majority samples and ignore minority samples.Majority weighted minority oversampling technique(MWMOTE)is an effective approach to solve this problem,however,it may suffer from the shortcomings of inadequate noise filtering and synthesizing the same samples as the original minority data.To this end,we propose an improved MWMOTE method named joint sample position based noise filtering and mean shift clustering(SPMSC)to solve these problems.Firstly,in order to effectively eliminate the effect of noisy samples,SPMSC uses a new noise filtering mechanism to determine whether a minority sample is noisy or not based on its position and distribution relative to the majority sample.Note that MWMOTE may generate duplicate samples,we then employ the mean shift algorithm to cluster minority samples to reduce synthetic replicate samples.Finally,data cleaning is performed on the processed data to further eliminate class overlap.Experiments on extensive benchmark datasets demonstrate the effectiveness of SPMSC compared with other sampling methods.
查看更多>>摘要：Scene graphs of point clouds help to understand object-level relationships in the 3D space.Most graph generation methods work on 2D structured data,which cannot be used for the 3D unstructured point cloud data.Existing point-cloud-based methods generate the scene graph with an additional graph structure that needs labor-intensive manual annotation.To address these problems,we explore a method to convert the point clouds into structured data and generate graphs without given structures.Specifically,we cluster points with similar augmented features into groups and establish their relationships,resulting in an initial structural representation of the point cloud.Besides,we propose a Dynamic Graph Generation Network(DGGN)to judge the semantic labels of targets of different granularity.It dynamically splits and merges point groups,resulting in a scene graph with high precision.Experiments show that our methods outperform other baseline methods.They output reliable graphs describing the object-level relationships without additional manual labeled data.
查看更多>>摘要：Grasp detection plays a critical role for robot manipulation.Mainstream pixel-wise grasp detection networks with encoder-decoder structure receive much attention due to good accuracy and efficiency.However,they usually transmit the high-level feature in the encoder to the decoder,and low-level features are neglected.It is noted that low-level features contain abundant detail information,and how to fully exploit low-level features remains unsolved.Meanwhile,the channel information in high-level feature is also not well mined.Inevitably,the performance of grasp detection is degraded.To solve these problems,we propose a grasp detection network with hierarchical multi-scale feature fusion and inverted shuffle residual.Both low-level and high-level features in the encoder are firstly fused by the designed skip connections with attention module,and the fused information is then propagated to corresponding layers of the decoder for in-depth feature fusion.Such a hierarchical fusion guarantees the quality of grasp prediction.Furthermore,an inverted shuffle residual module is created,where the high-level feature from encoder is split in channel and the resultant split features are processed in their respective branches.By such differentiation processing,more high-dimensional channel information is kept,which enhances the representation ability of the network.Besides,an information enhancement module is added before the encoder to reinforce input information.The proposed method attains 98.9％and 97.8％in image-wise and object-wise accuracy on the Cornell grasping dataset,respectively,and the experimental results verify the effectiveness of the method.
NETL
NSTL
万方数据