检索结果-内蒙古大学图书馆

26th ACM SIGKDD International conference on Knowledge Discovery and Data Mining (KDD)

作者： Siddique, A. B. Oymak, Samet Hristidis, Vagelis Univ Calif Riverside Riverside CA 92521 USA

ISBN: (纸本)9781450379984

Paraphrasing is expressing the meaning of an input sentence in different wording while maintaining fluency (i.e., grammatical and syntactical correctness). Most existing work on paraphrasing use supervised models that are limited to specific domains (e.g., image captions). Such models can neither be straightforwardly transferred to other domains nor generalize well, and creating labeled training data for new domains is expensive and laborious. The need for paraphrasing across different domains and the scarcity of labeled training data in many such domains call for exploring unsupervised paraphrase generation methods. We propose Progressive Unsupervised Paraphrasing (PUP): a novel unsupervised paraphrase generation method based on deep reinforcement learning (DRL). PUP uses a variational autoencoder (trained using a non-parallel corpus) to generate a seed paraphrase that warm-starts the DRL model. Then, PUP progressively tunes the seed paraphrase guided by our novel reward function which combines semantic adequacy, language fluency, and expression diversity measures to quantify the quality of the generated paraphrases in each iteration without needing parallel sentences. Our extensive experimental evaluation shows that PUP outperforms unsupervised state-of-the-art paraphrasing techniques in terms of both automatic metrics and user studies on four real datasets. We also show that PUP outperforms domain-adapted supervised algorithms on several datasets. Our evaluation also shows that PUP achieves a great trade-off between semantic similarity and diversity of expression.

关键词： Unsupervised paraphrasing deep reinforcement learning natural language generation natural language processing

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Experiment to Enhance Multidisciplinary Engineering Ability via UAVs Visual Navigation

A Comprehensive Experiment to Enhance Multidisciplinary Engi...

引用

IEEE Frontiers in Education conference (FIE)

作者： li, Lu Luo, Xiaoyan Wan, Han Wu, Chengxi Zheng, Yu Zhou, Fugen Beihang Univ Image Proc Ctr Beijing Peoples R China Beihang Univ Sch Comp Sci & Engn Beijing Peoples R China

ISBN: (纸本)9781728189611

This Research to Practice WIP presents a UAVs visual navigation based comprehensive experiment to enhance multidisciplinary engineering ability in Aerospace engineering education. In traditional courses, aerospace-related disciplines are independently distributed in different courses, and there is rarely a hands-on platform which includes signal processing, control theory, and artificial intelligence into Aerospace engineering. Facing this problem, this paper designs a multidisciplinary comprehensive experiment, aiming to provide a hand-on platform and flexible project-based program to students of aerospace engineering professions. First of all, in order to let the students understand actual aerospace problems, a multidisciplinary simulation platform containing UAVs and remote objects scenarios is constructed for them to explore in the experiments. Second, the content of the experiment is designed into three stages including data acquisition and processing, conceptual design and simulation, in-flight validation, during which the multidisciplinary engineering ability runs through the whole process of the activities. Finally, Project Oriented Design Based Learning is also introduced here to combine engineering design education with innovation and creativity. Through the project demonstration and presentation at the end of the experiment, the multidisciplinary engineering ability of each student can be effectively evaluated. The UVN comprehensive experiment enables students to work on real-world aerospace engineering problems through a hardware-software integration framework, which may greatly stimulate their curiosity and interest in autonomously learning. It also provides students unprecedented opportunities to immerse themselves in projects that cross disciplinary boundaries, improve their professional ability and enhance their exploration competence in aerospace areas.

关键词： Multidisciplinary Engineering Ability Comprehensive Experiment Aerospace Engineering UAVs Visual Navigation

来源：评论

学校读者我要写书评

暂无评论

An OpenMP parallel Genetic Algorithm for Design Space Exploration of Heterogeneous Multi-processor Embedded Systems 2020

An OpenMP Parallel Genetic Algorithm for Design Space Explor...

引用

11th Workshop on parallel Programming and Run-Time Management Techniques for Many-Core Architectures / 9th Workshop on Design Tools and Architectures for Multicore Embedded Computing Platforms, PARMA-DITAM 2020

作者： Muttillo, Vittoriano Giammatteo, Paolo Fiorilli, Giuseppe Pomante, Luigi University of L’Aquila L’Aquila Italy

ISBN: (纸本)9781450375450

Heterogeneous multiprocessor platforms are becoming widespread in the embedded system domain, mainly for the opportunity to improve timing performance and to minimize energy/power consumption and costs. Therefore, when using such platforms, it is important to adopt a Design Space Exploration (DSE) strategy that considers compromises among different objectives. Existing DSE approaches are generally based on evolutionary algorithms to solve Multi-Objective Optimization Problems (MOOPs) by minimizing a linear combination of weighted cost functions (i.e., Weighted Sum Method, WSM). In this way, the main issues are related to reduce timing execution while trying to improve the evolutionary algorithm performance, introducing strategies that attempt to bring better solutions. Code parallelization is one of the most used approaches in this field, but no standard methods have been released since different aspects could affect the performance. This approach leads to exploit parallel and distributed processing elements in order to implement evolutionary algorithms. In the latter case, if we consider genetic algorithms, it is possible to talk about parallel Genetic Algorithms (PGA). Considering this context, this paper focuses on DSE for heterogeneous multi-processor embedded systems and introduces an improvement that reduces execution time using parallel programming languages (i.e., OpenMP) inside the main genetic algorithm approach, while trying to lead to better partitioning solutions. The descriptions of the adopted DSE activities and the OpenMP implementation, validated by means of a case study, represent the core of the paper. © 2020 Association for Computing Machinery.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Decentralized and Secure Cooperative Edge Node Grouping to Process IoT Applications in Heterogeneous Smart Cyber-Physical Systems 17

Decentralized and Secure Cooperative Edge Node Grouping to P...

引用

17th International Bhurban conference on Applied Sciences and Technology (IBCAST)

作者： Mudassar, Muhammad Zhai, Yanlong Liao, Lejian Zahid, Muhammad Noaman Afzal, Fatima Beijing Inst Technol Sch Comp Sci Beijing 100081 Peoples R China Beijing Inst Technol Sch Opt & Photon Beijing 100081 Peoples R China Virtual Univ Pakistan Dept Comp Sci & Informat Technol Lahore Pakistan

ISBN: (纸本)9781728146768

Smart Cyber-Physical Systems (SCPS) has enhanced use of smart devices with numerous applications including smart cities, smart traffic management, smart cars, smart health care and smart grids. Core logic behind these applications usually require huge processing or massive data handling which are normally performed at cloud but the application will suffer from latency. Edge computing offers solution for latency aware computations at edge of the network but with limited resources available at edge nodes. This problem can be resolved by leveraging edge resources in a group and executing resource intensive task. Most previous studies deploy centralized methods for clustering but comes with overhead of cluster formation and management. In this article, key idea is to group heterogeneous edge nodes on task arrival in a decentralize way, and handle task allocation and execution in parallel on group devices to achieve its deadline. Our methodology will help to reduce traffic amount travelling towards cloud in case of resource intensive big tasks of SCPS applications. We have proposed an algorithm for decentralized group formation and presented task division and allocation methodology for parallel execution. Our results show that our technique is working while providing desired goals of reducing overall latency, and limiting network traffic as well as achieving higher ratio for number of tasks meeting their deadline.

关键词： Edge Computing distributed Computing Internet of Things Smart Cyber-Physical Systems Collaborative Computing

来源：评论

学校读者我要写书评

暂无评论

引用

IEEE International conference on Big Data and Cloud Computing (BdCloud)

作者： Lei Zhang Xuefei Chen Yuxiang Ma School of Computer and Information Engineering Henan University Kaifeng China Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng China

Mobile devices face the problem of handover signal sources in mobile communication networks. It is particularly difficult to address this problem in 5G networks, because the coverage area of 5G base stations is smaller than that of traditional mobile communication networks, e.g., 4G networks. Therefore, when a device is moving, it needs to frequently handover base stations to maintain the connection with the network in the 5G network. Given that 5G networks have high requirements for low latency and high reliability, new methods need to be proposed to optimize the selection of gNBs for devices. The prediction of the UEs’ trajectory can reduce redundant handovers between devices and base stations. However, the prediction of the UEs’ movement trajectory requires sufficient user movement data to achieve the desired prediction accuracy. For users with less trajectory data, inaccurate predictions may cause negative effects and even increase the number of handovers. In this paper, we propose a gNB handover model based on user similarity. The evaluation results show that our method can reduce the number of handovers by 50% compared with existing related solutions, which means that the proposed method will effectively reduce the transmission delay and enhance the robustness of the gNB.

关键词： Base stations 5G mobile communication Handover Predictive models Prediction algorithms Data models Robustness

来源：评论

学校读者我要写书评

暂无评论

HTtext: A TextCNN-based pre-silicon detection for hardware Trojans

HTtext: A TextCNN-based pre-silicon detection for hardware T...

引用

IEEE International conference on Big Data and Cloud Computing (BdCloud)

作者： Yi Xu Zhenyi Chen Binhong Huang Ximeng Liu Chen Dong College of Computer and Data Science Fuzhou University Fuzhou China University of South Floride Tampa USA Key Lab of Information Security of Network Systems (Fuzhou University) Fujian Key Laboratory of Network Computing and Intelligent Information Processing (Fuzhou University)

With the advent of the intelligence era, the usage and investment for chips have risen year by year, causing the demand for chip security. Machine learning (ML) analysis has made progress as a pre-silicon hardware Trojan (HT) detection technology. Whereas the performance of existing methods almost relies on the accuracy of multi-feature representation, moreover, it is difficult to extract features manually and easily cause unstable classifier performance (namely uncertainty). In this paper, an automatic feature extraction detecting model is first proposed, named HTtext, which generates simple path sentences from chip netlists and employs TextCNN, a deep learning algorithm, to distinguish HT circuits. The pre-training for TextCNN only uses the automatic single-feature calculation to avoid the uncertainty problem. Additionally, the model can obtain non-repetitive HT component information expression, which satisfies the stable detection performance. To measure the efficiency and balance of the model, the paper proposes the concept of the Stability Efficiency Index (SEI). In the experimental results for the benchmark netlists, not only the average accuracy (ACC) in TextCNN is as high as 99.26%, but also its SEI value ranks first in all comparison classifiers, which proves that the proposed HTtext model has high stability in generality.

关键词： Ports (computers) Semiconductor device measurement Uncertainty Stability criteria Feature extraction Hardware Circuit stability

来源：评论

学校读者我要写书评

暂无评论

基于动态称量和图像识别技术的井下煤矸石智能分选装置研发

引用

矿业研究与开发 2023年第2期43卷 178-183页

作者：陈佳鑫赵国贞程伟常枫懿太原理工大学矿业工程学院山西太原030024 太原理工大学原位改性采矿教育部重点实验室山西太原030024

井下煤矸石分选是实现井下矸石“不升井”的重要技术措施。以干法选煤为基础,提出了间断煤流硐室式煤矸石分选和连续煤流皮带式煤矸石分选两种方法,以智能图像识别和动态称量技术为核心,设计了适用于井下硐室分选的紧凑式煤矸石分选装... 详细信息

井下煤矸石分选是实现井下矸石“不升井”的重要技术措施。以干法选煤为基础,提出了间断煤流硐室式煤矸石分选和连续煤流皮带式煤矸石分选两种方法,以智能图像识别和动态称量技术为核心,设计了适用于井下硐室分选的紧凑式煤矸石分选装置以及适用于顺槽或大巷的分布式煤矸石分选装置。前者使用了多级筛网结构,弥补了粒径差异对物体识别的影响;采用大角度传送带,有效减小了设备尺寸。后者使用小皮带轮作为原料运输的主要动力转换装置,减小了能源消耗,通过转盘装置使煤矸石识别和分选并行处理,提高了工作效率。装置的研发对推动煤炭绿色开采具有一定的意义。

关键词：井下煤矸石分选干法选煤智能分选装置

来源：评论

学校读者我要写书评

暂无评论

PRED: A parallel NETWORK FOR HANDLING MULTIPLE DEGRADATIONS VIA SINGLE MODEL IN SINGLE image SUPER-RESOLUTION 26

PRED: A PARALLEL NETWORK FOR HANDLING MULTIPLE DEGRADATIONS ...

引用

26th IEEE International conference on image processing (ICIP)

作者： Wu, Guangyang Zhao, Lili Wang, Wenyi Zeng, Liaoyuan Chen, Jianwen Univ Elect Sci & Technol China Sch Informat & Commun Engn Chengdu 611731 Sichuan Peoples R China

ISBN: (纸本)9781538662496

Existing SISR (single image super-resolution) methods mostly assume that a low-resolution (LR) image is bicubicly down-sampled from its high-resolution (HR) counterpart, which inevitably give rise to poor performance when the degradation is out of assumption. To address this issue, we propose a framework PRED (parallel residual and encoder-decoder network) with an innovative training strategy to enhance the robustness to multiple degradations. Consequently, the network can handle spatially variant degradations, which significantly improves the practicability of the proposed method. Extensive experimental results on real LR images show that the proposed method can not only produce favorable results on multiple degradations, but also reconstruct visually plausible HR images.

关键词： SISR multiple degradation CNN PRED

来源：评论

学校读者我要写书评

暂无评论

An Efficient DFT Implementation using Modified Group distributed Arithmetic 6

An Efficient DFT Implementation using Modified Group Distrib...

引用

6th International conference on Signal processing and Integrated Networks (SPIN)

作者： Kumar, Santhosh S. R. Veeramachaneni, Sreehari Mahammad, Noor Sk Indian Inst Informat Technol Design & Mfg Kanchee Dept ECE Chennai Tamil Nadu India Gokaraju Rangaraju Inst Engn & Technol Dept ECE Hyderabad Telangana India Indian Inst Informat Technol Design & Mfg Kanchee Dept CSE Chennai Tamil Nadu India

ISBN: (纸本)9781728113807

Many of the modern signal/ image processing applications use Discrete Fourier Transform (DFT) as one of the core functional elements to process the input signal/image from one domain to another. Hardware design of the DFT is complex and many researchers have proposed variety of methods to implement it. Computational complexity of ID, N-point DFT is O(N-2). distributed arithmetic is one of the promising and efficient technique to implement any discrete orthogonal transform. This paper proposes an efficient approach to implement DFT using distributed arithmetic. The proposed technique exploits the repetitive pattern of coefficients and stores efficiently in the memory and reduces the storage by 75% compared to the existing group distributed arithmetic for 8-point DFT. The proposed approach uses the property of group distributed arithmetic efficiently in the architecture.

关键词： Discrete Fourier Transform distributed Arithmetic Discrete Orthogonal Transform Signal processing image processing

来源：评论

学校读者我要写书评

暂无评论

A Large-Scale parallel Network Intrusion Detection Model Based on K-Means in Security Audit System 6th

A Large-Scale Parallel Network Intrusion Detection Model Bas...

引用

6th International conference on Artificial Intelligence and Security,ICAIS 2020

作者： Qiao, Xueming Zhang, Yuan Liu, Yanhong Hu, Hao Zhu, Dongjie Qiu, Zhi Liu, Chenglin State Grid Weihai Power Supply Company Weihai China School of Computer Science and Technology Harbin Institute of Technology Weihai China State Grid Rushan County Electric Power Supply Company Weihai China

ISBN: (纸本)9789811580857

With the gradual entry of 5G communication technology into the commercial stage, the era of the Internet of Thing is coming, bringing great convenience to people’s lives. However, there are potential threats to security audit data interaction in the IoT environment. Traditional network intrusion detection methods cannot meet the requirements of parallel processing of massive data. Therefore, network intrusion detection should consider parallelizing data processing and predicting abnormal behavior ahead. In this paper, we propose a large-scale parallel network intrusion detection method based on k-means. Firstly, the Isolation Forest algorithm is used to filter and segment the sample data;Secondly, the clusters is obtained by the k-means algorithm in a distributed manner;Finally, the generated cluster is weighted and voted for abnormality determination. The experimental results of KDDCUP dataset shows that the algorithm improves the recognition accuracy and speeds up the training time and prediction time compared with the traditional k-means algorithm. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：