Jointly Part-of-Speech Tagging and Semantic Role Labeling Using Auxiliary Deep Neural Network Model

Previous studies have shown that there is potential semantic dependency between part-of-speech and semantic roles.At the same time,the predicate-argument structure in a sentence is important information for semantic role labeling task.In this work,we introduce the auxiliary deep neural network model,which models semantic dependency between part-of-speech and semantic roles and incorporates the information of predicate-argument into semantic role labeling.Based on the framework of joint learning,part-of-speech tagging is used as an auxiliary task to improve the result of the semantic role labeling.In addition,we introduce the argument recognition layer in the training process of the main task-semantic role labeling,so the argument-related structural information selected by the predicate through the attention mechanism is used to assist the main task.Because the model makes full use of the semantic dependency between part-of-speech and semantic roles and the structural information of predicate-argument,our model achieved the F1 value of 89.0%on the WSJ test set of CoNLL2005,which is superior to existing state-of-the-art model about 0.8%.

Evolutionary genetics of wheat mitochondrial genomes

The Triticum-Aegilops complex provides ideal models for the study of polyploidization,and mitochondrial genomes(mtDNA)can be used to trace cytoplasmic inheritance and energy production following polyploidization.In this study,gapless mitochondrial genomes for 19 accessions of five Triticum or Aegilops species were assembled.Comparative genomics confirmed that the BB-genome progenitor donated mtDNA to tetraploid T.turgidum(genome formula AABB),and that this mtDNA was then passed on to the hexaploid T.aestivum(AABBDD).T urartu(AA)was the paternal parent of T.timopheevii(AAGG),and an earlier Ae.tauschii(DD)was the maternal parent of Ae.cylindrica(CCDD).Genic sequences were highly conserved within species,but frequent rearrangements and nuclear or chloroplast DNA insertions occurred during speciation.Four highly variable mitochondrial genes(atp6,cob,nad6,and nad9)were established as marker genes for Triticum and Aegilops species identification.The BB/GG-specific atp6 and cob genes,which were imported from the nuclear genome,could facilitate identification of their diploid progenitors.Genic haplotypes and repeat-sequence patterns indicated that BB was much closer to GG than to Ae.speltoides(SS).These findings provide novel insights into the polyploid evolution of the Triticum/Aegilops complex from the perspective of mtDNA,advancing understanding of energy supply and adaptation in wheat species。

A New Partial Task Offloading Method in a Cooperation Mode under Multi-Constraints for Multi-UE

In Multi-access Edge Computing(MEC),to deal with multiple user equipment(UE)’s task offloading problem of parallel relationships under the multi-constraints,this paper proposes a cooperation partial task offloading method(named CPMM),aiming to reduce UE’s energy and computation consumption,while meeting the task completion delay as much as possible.CPMM first studies the task offloading of single-UE and then considers the task offloading ofmulti-UE based on single-UE task offloading.CPMMuses the critical path algorithmto divide the modules into key and non-key modules.According to some constraints of UE-self when offloading tasks,it gives priority to non-key modules for offloading and uses the evaluation decision method to select some appropriate key modules for offloading.Based on fully considering the competition between multiple UEs for communication resources and MEC service resources,CPMM uses the weighted queuing method to alleviate the competition for communication resources and uses the branch decision algorithm to determine the location of module offloading by BS according to the MEC servers’resources.It achieves its goal by selecting reasonable modules to offload and using the cooperation ofUE,MEC,andCloudCenter to determine the execution location of themodules.Extensive experiments demonstrate that CPMM obtains superior performances in task computation consumption reducing around 6%on average,task completion delay reducing around 5%on average,and better task execution success rate than other similar methods.

Solving Multitrip Pickup and Delivery Problem With Time Windows and Manpower Planning Using Multiobjective Algorithms

The multitrip pickup and delivery problem with time windows and manpower planning(MTPDPTW-MP)determines a set of ambulance routes and finds staff assignment for a hospital. It involves different stakeholders with diverse interests and objectives. This study firstly introduces a multiobjective MTPDPTW-MP(MO-MTPDPTWMP) with three objectives to better describe the real-world scenario. A multiobjective iterated local search algorithm with adaptive neighborhood selection(MOILS-ANS) is proposed to solve the problem. MOILS-ANS can generate a diverse set of alternative solutions for decision makers to meet their requirements. To better explore the search space, problem-specific neighborhood structures and an adaptive neighborhood selection strategy are carefully designed in MOILS-ANS. Experimental results show that the proposed MOILS-ANS significantly outperforms the other two multiobjective algorithms. Besides, the nature of objective functions and the properties of the problem are analyzed. Finally, the proposed MOILS-ANS is compared with the previous single-objective algorithm and the benefits of multiobjective optimization are discussed.

A Deletable and Modifiable Blockchain Scheme Based on Record Verification Trees and the Multisignature Mechanism

As one of the most valuable technologies,blockchains have received extensive attention from researchers and industry circles and are widely applied in various scenarios.However,data on a blockchain cannot be deleted.As a result,it is impossible to clean invalid and sensitive data and correct erroneous data.This,to a certain extent,hinders the application of blockchains in supply chains and Internet of Things.To address this problem,this study presents a deletable and modifiable blockchain scheme(DMBlockChain)based on record verification trees(RVTrees)and the multisignature scheme.(1)In this scheme,an RVTree structure is designed and added to the block structure.The RVTree can not only ensure that a record is true and valid but,owing to its unique binary structure,also verify whether modification and deletion requests are valid.(2)In DMBlockChain,the multisignature mechanism is also introduced.This mechanism requires the stakeholders’signatures for each modification or deletion request and thus ensures that a record will not be modified arbitrarily.A user’s request is deemed valid only if it is dually verified by the RVTree and the multisignature mechanism.The analysis finds that DMBlockChain can provide a secure and valid means for modifying and deleting records in a block while ensuring the integrity of the block and that DMBlockChain can effectively save space in some scenarios that require frequent records modification.

Mining Bytecode Features of Smart Contracts to Detect PonziScheme on Blockchain

The emergence of smart contracts has increased the attention of industry and academia to blockchain technology,which is tamper-proofing,decentralized,autonomous,and enables decentralized applications to operate in untrustworthy environments.However,these features of this technology are also easily exploited by unscrupulous individuals,a typical example of which is the Ponzi scheme in Ethereum.The negative effect of unscrupulous individuals writing Ponzi scheme-type smart contracts in Ethereum and then using these contracts to scam large amounts of money has been significant.To solve this problem,we propose a detection model for detecting Ponzi schemes in smart contracts using bytecode.In this model,our innovation is shown in two aspects:We first propose to use two bytes as one characteristic,which can quickly transform the bytecode into a high-dimensional matrix,and this matrix contains all the implied characteristics in the bytecode.Then,We innovatively transformed the Ponzi schemes detection into an anomaly detection problem.Finally,an anomaly detection algorithm is used to identify Ponzi schemes in smart contracts.Experimental results show that the proposed detection model can greatly improve the accuracy of the detection of the Ponzi scheme contracts.Moreover,the F1-score of this model can reach 0.88,which is far better than those of other traditional detection models.

Multi-Cluster Feature Selection Based on Isometric Mapping

Dear editor,This letter presents an unsupervised feature selection method based on machine learning.Feature selection is an important component of artificial intelligence,machine learning,which can effectively solve the curse of dimensionality problem.Since most of the labeled data is expensive to obtain.

An Experimental Study of Text Representation Methods forCross-Site Purchase Preference Prediction Using the Social Text Data

Nowadays, many e-commerce websites allow users to login with their existing social networking accounts. When a new user comes to an e-commerce website, it is interesting to study whether the information from external social media platforms can be utilized to alleviate the cold-start problem. In this paper, we focus on a specific task on cross-site information sharing, i.e., leveraging the text posted by a user on the social media platform (termed as social text) to infer his/her purchase preference of product categories on an e-commerce platform. To solve the task, a key problem is how to effectively represent the social text in a way that its information can be utilized on the e-commerce platform. We study two major kinds of text representation methods for predicting cross-site purchase preference, including shallow textual features and deep textual features learned by deep neural network models. We conduct extensive experiments on a large linked dataset, and our experimental results indicate that it is promising to utilize the social text for predicting purchase preference. Specially, the deep neural network approach has shown a more powerful predictive ability when the number of categories becomes large.

Enabling QoE-aware Mobile Cloud Video Recording over Roadside Vehicular Networks

Most of previous video recording devices in mobile vehicles commonly store captured video contents locally. With the rapid development of 4G/Wi Fi networks, there emerges a new trend to equip video recording devices with wireless interfaces to enable video uploading to the cloud for video playback in a later time point. In this paper, we propose a QoE-aware mobile cloud video recording scheme in the roadside vehicular networks, which can adaptively select the proper wireless interface and video bitrate for video uploading to the cloud. To maximize the total utility, we need to design a control strategy to carefully balance the transmission cost and the achieved QoE for users. To this purpose, we investigate the tradeoff between cost incurred by uploading through cellular networks and the achieved QoE of users. We apply the optimization framework to solve the formulated problem and design an online scheduling algorithm. We also conduct extensive trace-driven simulations and our results show that our algorithm achieves a good balance between the transmission cost and user QoE.

Rotating Stomata Measurement Based on Anchor-Free Object Detection and Stomata Conductance Calculation

Stomata play an essential role in regulating water and carbon dioxide levels in plant leaves,which is important for photosynthesis.Previous deep learning-based plant stomata detection methods are based on horizontal detection.The detection anchor boxes of deep learning model are horizontal,while the angle of stomata is randomized,so it is not possible to calculate stomata traits directly from the detection anchor boxes.Additional processing of image(e.g.,rotating image)is required before detecting stomata and calculating stomata traits.This paper proposes a novel approach,named DeepRSD(deep learning-based rotating stomata detection),for detecting rotating stomata and calculating stomata basic traits at the same time.Simultaneously,the stomata conductance loss function is introduced in the DeepRSD model training,which improves the efficiency of stomata detection and conductance calculation.The experimental results demonstrate that the DeepRSD model reaches 94.3%recognition accuracy for stomata of maize leaf.The proposed method can help researchers conduct large-scale studies on stomata morphology,structure,and stomata conductance models.

Unsupervised social network embedding via adaptive specific mappings

In this paper,we address the problem of unsuperised social network embedding,which aims to embed network nodes,including node attributes,into a latent low dimensional space.In recent methods,the fusion mechanism of node attributes and network structure has been proposed for the problem and achieved impressive prediction performance.However,the non-linear property of node attributes and network structure is not efficiently fused in existing methods,which is potentially helpful in learning a better network embedding.To this end,in this paper,we propose a novel model called ASM(Adaptive Specific Mapping)based on encoder-decoder framework.In encoder,we use the kernel mapping to capture the non-linear property of both node attributes and network structure.In particular,we adopt two feature mapping functions,namely an untrainable function for node attributes and a trainable function for network structure.By the mapping functions,we obtain the low dimensional feature vectors for node attributes and network structure,respectively.Then,we design an attention layer to combine the learning of both feature vectors and adaptively learn the node embedding.In encoder,we adopt the component of reconstruction for the training process of learning node attributes and network structure.We conducted a set of experiments on seven real-world social network datasets.The experimental results verify the effectiveness and efficiency of our method in comparison with state-of-the-art baselines.

CATIRI:An Efficient Method for Content-and-Text Based Image Retrieval

The combination of visual and textual information in image retrieval remarkably alleviates the semantic gap of traditional image retrieval methods,and thus it has attracted much attention recently.Image retrieval based on such a combination is usually called the content-and-text based image retrieval(CTBIR).Nevertheless,existing studies in CTBIR mainly make efforts on improving the retrieval quality.To the best of our knowledge,little attention has been focused on how to enhance the retrieval efficiency.Nowadays,image data is widespread and expanding rapidly in our daily life.Obviously,it is important and interesting to investigate the retrieval efficiency.To this end,this paper presents an efficient image retrieval method named CATIRI(content-and-text based image retrieval using indexing).CATIRI follows a three-phase solution framework that develops a new indexing structure called MHIM-tree.The MHIM-tree seamlessly integrates several elements including Manhattan Hashing,Inverted index,and M-tree.To use our MHIM-tree wisely in the query,we present a set of important metrics and reveal their inherent properties.Based on them,we develop a top-k query algorithm for CTBIR.Experimental results based on benchmark image datasets demonstrate that CATIRI outperforms the competitors by an order of magnitude.

LQTTrack:Multi-Object Tracking by Focusing on Low-Quality Targets Association

Multi-object tracking(MOT)has seen rapid improvements in recent years.However,frequent occlusion remains a significant challenge in MOT,as it can cause targets to become smaller or disappear entirely,resulting in lowquality targets,leading to trajectory interruptions and reduced tracking performance.Different from some existing methods,which discarded the low-quality targets or ignored low-quality target attributes.LQTTrack,with a lowquality association strategy(LQA),is proposed to pay more attention to low-quality targets.In the association scheme of LQTTrack,firstly,multi-scale feature fusion of FPN(MSFF-FPN)is utilized to enrich the feature information and assist in subsequent data association.Secondly,the normalized Wasserstein distance(NWD)is integrated to replace the original Inter over Union(IoU),thus overcoming the limitations of the traditional IoUbased methods that are sensitive to low-quality targets with small sizes and enhancing the robustness of low-quality target tracking.Moreover,the third association stage is proposed to improve the matching between the current frame’s low-quality targets and previously interrupted trajectories from earlier frames to reduce the problem of track fragmentation or error tracking,thereby increasing the association success rate and improving overall multi-object tracking performance.Extensive experimental results demonstrate the competitive performance of LQTTrack on benchmark datasets(MOT17,MOT20,and DanceTrack).

Crowd-Guided Entity Matching with Consolidated Textual Data

Entity matching (EM) identifies records referring to the same entity within or across databases. Existing methods using structured attribute values (such as digital, date or short string values) may fail when the structured information is not enough to reflect the matching relationships between records. Nowadays more and more databases may have some unstructured textual attribute containing extra consolidated textual information (CText) of the record, but seldom work has been done on using the CText for EM. Conventional string similarity metrics such as edit distance or bag-of-words are unsuitable for measuring the similarities between CText since there are hundreds or thousands of words with each piece of CText, while existing topic models either cannot work well since there are no obvious gaps between topics in CText. In this paper, we propose a novel cooccurrence-based topic model to identify various sub-topics from each piece of CText, and then measure the similarity between CText on the multiple sub-topic dimensions. To avoid ignoring some hidden important sub-topics, we let the crowd help us decide weights of different sub-topics in doing EM. Our empirical study on two real-world datasets based on Amzon Mechanical Turk Crowdsourcing Platform shows that our method outperforms the state-of-the-art EM methods and Text Understanding models.

Sparse Deep Neural Network for Nonlinear Partial Differential Equations

More competent learning models are demanded for data processing due to increasingly greater amounts of data available in applications.Data that we encounter often have certain embedded sparsity structures.That is,if they are represented in an appropriate basis,their energies can concentrate on a small number of basis functions.This paper is devoted to a numerical study of adaptive approximation of solutions of nonlinear partial differential equations whose solutions may have singularities,by deep neural networks(DNNs)with a sparse regularization with multiple parameters.Noting that DNNs have an intrinsic multi-scale structure which is favorable for adaptive representation of functions,by employing a penalty with multiple parameters,we develop DNNs with a multi-scale sparse regularization(SDNN)for effectively representing functions having certain singularities.We then apply the proposed SDNN to numerical solutions of the Burgers equation and the Schrödinger equation.Numerical examples confirm that solutions generated by the proposed SDNN are sparse and accurate.

The most tenuous group query

Rtecently a lot of works have been investigating to find the tenuous groups,i.e.,groups with few social interactions and weak relationships among members,for reviewer selection and psycho-educational group formation.However,the metrics(e.g.,k-triangle,k-line,and k-tenuity)used to measure the tenuity,require a suitable k value to be specified which is difficult for users without background knowledge.Thus,in this paper we formulate the most tenuous group(MTG)query in terms of the group distance and average group distance of a group measuring the tenuity to eliminate the influence of parameter k on the tenuity of the group.To address the MTG problem,we first propose an exact algorithm,namely MTGVDIS,which takes priority to selecting those vertices whose vertex distance is large,to generate the result group,and also utilizes effective filtering and pruning strategies.Since MTGVDIS is not fast enough,we design an efficient exact algorithm,called MTG-VDGE,which exploits the degree metric to sort the vertexes and proposes a new combination order,namely degree and reverse based branch and bound(DRBB).MTG-VDGE gives priority to those vertices with small degree.For a large p,we further develop an approximation algorithm,namely MTG-VDLT,which discards candidate attendees with high degree to reduce the number of vertices to be considered.The experimental results on real datasets manifest that the proposed algorithms outperform existing approaches on both efficiency and group tenuity.

Improved Dota2 Lineup Recommendation Model Based on a Bidirectional LSTM

In recent years,e-sports has rapidly developed,and the industry has produced large amounts of data with specifications,and these data are easily to be obtained.Due to the above characteristics,data mining and deep learning methods can be used to guide players and develop appropriate strategies to win games.As one of the world’s most famous e-sports events,Dota2 has a large audience base and a good game system.A victory in a game is often associated with a hero’s match,and players are often unable to pick the best lineup to compete.To solve this problem,in this paper,we present an improved bidirectional Long Short-Term Memory(LSTM)neural network model for Dota2 lineup recommendations.The model uses the Continuous Bag Of Words(CBOW)model in the Word2 vec model to generate hero vectors.The CBOW model can predict the context of a word in a sentence.Accordingly,a word is transformed into a hero,a sentence into a lineup,and a word vector into a hero vector,the model applied in this article recommends the last hero according to the first four heroes selected first,thereby solving a series of recommendation problems.

Type-Aware Question Answering over Knowledge Base with Attention-Based Tree-Structured Neural Networks

Question answering (QA) over knowledge base (KB) aims to provide a structured answer from a knowledge base to a natural language question. In this task, a key step is how to represent and understand the natural language query. In this paper, we propose to use tree-structured neural networks constructed based on the constituency tree to model natural language queries. We identify an interesting observation in the constituency tree: different constituents have their own semantic characteristics and might be suitable to solve different subtasks in a QA system. Based on this point, we incorporate the type information as an auxiliary supervision signal to improve the QA performance. We call our approach type-aware QA. We jointly characterize both the answer and its answer type in a unified neural network model with the attention mechanism. Instead of simply using the root representation, we represent the query by combining the representations of different constituents using task-specific attention weights. Extensive experiments on public datasets have demonstrated the effectiveness of our proposed model. More specially, the learned attention weights are quite useful in understanding the query. The produced representations for intermediate nodes can be used for analyzing the effectiveness of components in a QA system.

Non-SPF routing algorithm based on ordered semi-group preference algebra

Layer 2 network technology is extending beyond its traditional local area implementation and finding wider acceptance in provider＇s metropolitan area networks and large-scale cloud data center networks. This is mainly due to its plug-and-play capability and native mobility support. Many efforts have been put to increase the bisection bandwidth in layer 2 network, which has been constrained by the spanning tree protocol （STP） that layer 2 network uses for preventing looping. The recent trend is to incorporate layer 3＇s routing approach into layer 2 network so that multiple paths can be used for forwarding traffic between any source-destination （S-D） node pair. Equal cost multipath （ECMP） is one such example. However, ECMP may still be limited in generating multiple paths due to its shortest path （lowest cost） requirement. In this paper, we consider a non-shortest-path routing approach, called equal preference multipath （EPMP） based on ordered semi group theory, which can generate more paths than ECMP. In EPMP routing, all the paths with different traditionally-defined costs, such as hops, bandwidth, etc., can be determined equally now and thus they become equal candidate paths. By the comparative tests with ECMP, EPMP routing not only generates more paths, provides 15% higher bisection bandwidth, but also identifies bottleneck links in a hierarchical network when different traffic patterns are applied EPMP is more flexible in controlling the number and length of multipath generation. Simulation results indicate the effectiveness of the proposed algorithm. It is a good reference for non-blocking running of big datacenter networks.

Phase spectrum based automatic ship detection in synthetic aperture radar images

This paper proposes an automatic ship detection approach in Synthetic Aperture Radar(SAR)Images using phase spectrum.The proposed method mainly contains two stages:Firstly,sea-land segmentation of SAR Images is one of the key stages for SAR image application such as sea-targets detection and recognition,which are easily detected only in sea regions.In order to eliminate the influence of land regions in SAR images,a novel land removing method is explored.The removing method employs a Harris corner detector to obtain some image patches belonging to land,and the probability density function(PDF)of land area can be estimated by these patches.Thus,an appropriate land segmentation threshold is accordingly obtained.Secondly,an automatic ship detector based on phase spectrum is proposed.The proposed detector is free from various idealized assumptions and can accurately detect ships in SAR images.Experimental results demonstrate the efficiency of the proposed ship detection algorithm in diversified SAR images.