检索结果-内蒙古大学图书馆

5th International Conference on Innovation in Artificial Intelligence (ICIAI)

作者： Gong, Peng Shi, Dianxi Xue, Chao Chen, Xucan Natl Univ Def Technol Coll Comp Changsha Peoples R China Natl Innovat Inst Def Technol NIIDT Tianjin Artificial Intelligence Innovat Ctr TAI Artificial Intelligence Res Ctr AIRC Beijing Peoples R China Natl Innovat Inst Def Technol NIIDT Artificial Intelligence Res Ctr AIRC Beijing Peoples R China

ISBN: (纸本)9781450388634

Transferring reinforcement learning policies trained in a physical simulator to the real world is a highly challenging problem, because the gap between the simulation and reality, usually causes the transferred model to perform poorly in the real world. Many algorithms including domain randomization, have been proposed to try to bridge the gap between simulation and reality. However, most of them are to change the value of the corresponding data by superimposing gaussian noise on robot dynamics parameters or environmental data. Such policies often fail to solve the problem of long-term/intermittent missing data patterns caused by sensor failures in the actual operation of the robot. Faced with this problem, we proposed a memory-enhanced domain data pattern randomization method. This method achieves data enhancement by randomizing the distribution pattern of data connection, at the same time, the memory mechanism based on recurrent neural network is introduced into the decision model, to alleviate the jitter of environmental distribution caused by data pattern changes, so as to improve the decision-making ability of the robot in some observable scenes triggered by the change of data pattern.

关键词： Deep Reinforcement Learning Sim to Real data pattern Domain Randomization Recurrent Neural Network

来源：评论

学校读者我要写书评

暂无评论

Investigation of Electron and Hole Lateral Migration in Silicon Nitride and data pattern Effects on ${V}_{{t}}$ Retention Loss in a Multilevel Charge Trap Flash Memory

引用

IEEE TRANSACTIONS ON ELECTRON DEVICES 2019年第12期66卷 5155-5161页

作者： Liu, Yu-Heng Zhan, Ting-Chien Wang, Tahui Tsai, Wen-Jer Lu, Tao-Cheng Chen, Kuang-Chao Lu, Chih-Yuan Natl Chiao Tung Univ Inst Elect Hsinchu 300 Taiwan Macronix Int Co Ltd Hsinchu 300 Taiwan

We investigate electron and hole lateral migration in retention loss in a multilevel charge trap flash memory. We use hot electron program and band-to-band tunneling hot hole erase to inject various amounts of electrons and holes at the two ends of a SONOS cell. A random telegraph signal (RTS) method is used to distinguish electron and hole lateral movements in silicon nitride. In retention measurement, we apply a voltage to the gate or the source/drain to enhance or retard trapped charge vertical loss and lateral migration. From the evolution characteristics of RTS and traces in retention, we are able to identify the separate roles of electron vertical loss, electron lateral migration, and hole lateral migration in different data patterns. Due to the interaction of stored electrons and holes, we find that retention loss in a program state exhibits a turnaround characteristic as program level increases. loss at low program levels is attributed to hole lateral migration from a neighboring bit. At higher program levels, the influence of hole lateral migration is reduced and loss is dominated by electron vertical loss and lateral migration.

关键词： data pattern electron and hole lateral migration multilevel flash memory random telegraph signal (RTS)

来源：评论

学校读者我要写书评

暂无评论

Diverse Water Quality data pattern Study of the Indian River Ganga: Correlation and Cluster Analysis 17

Diverse Water Quality Data Pattern Study of the Indian River...

引用

17th International Conference on ICT and Knowledge Engineering (IEEE ICT&KE)

作者： Shakhari, Swapan Verma, Aayush Kumar Ghosh, Debasmita Bhar, Kalyan Kumar Banerjee, Indrajit Indian Inst Engn Sci & Technol Dept Informat Technol Sibpur Howrah India Microsoft India R&D Pvt Ltd Dept Microsoft Serv Global Delivery Bangalore Karnataka India Univ Calcutta Dept Geog Sarsuna Coll Kolkata India Indian Inst Engn Sci & Technol Dept Civil Engn Sibpur Howrah India

ISBN: (纸本)9781728132099

Over the years, the growing concern for the most primary resource of life sustenance is reaching an acme. This work is aimed at providing a data pattern analysis using cluster and correlation methods. This research analyses the water quality of the river Ganga, for the various purposes of social work, based on the data of the molecular and non-molecular water quality parameters. Correlations are useful because they can indicate a predictive relationship and based on the data of the physio-chemical parameters of the River Ganga, we can find the year-wise correlation matrix. We found five clusters for DO, pH and BOD and another five clusters for Conductivity, Fecal Coliform and Total Coliform.

关键词： river water quality clustering correlation data pattern physicochemical parameters

来源：评论

学校读者我要写书评

暂无评论

data-pattern Enabled Self-Recovery Low-Power Storage System for Big Video data

引用

IEEE TRANSACTIONS ON BIG data 2019年第1期5卷 95-105页

作者： Edstrom, Jonathon Chen, Dongliang Gong, Yifu Wang, Jinhui Gong, Na North Dakota State Univ Dept Elect & Comp Engn Fargo ND 58108 USA

The growing popularity of powerful mobile devices such as smart phones and tablet devices has resulted in the exponential growth of demand for video applications. However, due to the large video data size and intensive computation, mobile video applications require frequent embedded memory access, which consumes a large amount of power and limits battery life. In this paper, we present a low-cost self-recovery video storage system by investigating meaningful data patterns hidden in big video data, by introducing data mining techniques to the hardware design process. We propose a two-dimensional data-pattern approach to explore horizontal data-association and vertical data-correlation characteristics. Such data relationship discovery and pattern identification enable a new dimension for the hardware design space and bring self-recovery ability to memories in the presence of bitcell failures. Based on the identified optimal data patterns, we present a low-cost and efficient SRAM design to enable data self-recovery at low voltages. A 45nm 32 kb SRAM is implemented that delivers good video quality at near-threshold voltage (0.5 V) with negligible area overhead (7.94 percent).

关键词： Videos data mining data pattern low-power self-recovery on-chip memory

来源：评论

学校读者我要写书评

暂无评论

data-pattern Driven Cache-Collision Timing Attacks Against AES-GCM 5

Data-Pattern Driven Cache-Collision Timing Attacks Against A...

引用

5th IEEE International Conference on Big data Intelligence and Computing, dataCom 2019

作者： Huang, James Li, Xiaoming University of Delaware Department of Electrical and Computer Engineering NewarkDE19716 United States

ISBN: (纸本)9781728141176

data security is an important issue in Big data applications. Even though the same problem has been extensively studied within other contexts, Big data applications present several unique challenges. Among them is actually the volume of data that typical Big data applications process. Just because there is so much data passing through, the sheer data volume provides way more opportunities for a potential attacker to observe and identify patterns in computation and data. In this paper, we reveal that the data/computation patterns derived from the observation of large volume of data can be associated with certain sensitive information, specifically the key used in the AES-GCM algorithm. The AES-GCM algorithm is one of the foundation algorithms in data security, therefore such data-pattern driven attack can potentially compromise the security of Big data application. We present an attack model and an implementation of the attack based on OpenSSL, a widely used library that provides security-related functions for many applications. In most cases, our attack methodology is able to converge and extract the hidden key. We also discuss potential counter measures against similar attacks. © 2019 IEEE.

关键词： AES-GCM Cache Collision data pattern

来源：评论

学校读者我要写书评

暂无评论

CyclicShift: A data Augmentation Method For Enriching data patterns 22

CyclicShift: A Data Augmentation Method For Enriching Data P...

引用

30th ACM International Conference on Multimedia (MM)

作者： Lu, Hui Cheng, Xuan Xia, Wentao Deng, Pan Liu, MingHui Xie, Tianshu Wang, XiaoMin Liu, Ming Univ Elect Sci & Technol China Chengdu Peoples R China Univ Elect Sci & Technol China Yangtze Delta Reg Inst Quzhou Quzhou Zhejiang Peoples R China

ISBN: (纸本)9781450392037

In this paper, we propose a simple yet effective data augmentation strategy, dubbed CyclicShift, to enrich data patterns. The idea is to shift the image in a certain direction and then circularly refill the resultant out-of-frame part to the other side. Compared with previous related methods, Translation, and Shuffle, our proposed method is able to avoid losing pixels of the original image and preserve its semantic information as much as possible. Visually and emprically, we show that our method indeed brings new data patterns and thereby improves the generalization ability as well as the performance of models. Extensive experiments demonstrate our method's effectiveness in image classification and fine-grained recognition over multiple datasets and various network architectures. Furthermore, our method can also be superimposed on other data augmentation methods in a very simple way. CyclicMix, the simultaneous use of CyclicShift and CutMix, hits a new high in most cases. Our code is open-source and available at https://***/dejavunHui/CyclicShift.

关键词： data augmentation data pattern classification generalization

来源：评论

学校读者我要写书评

暂无评论

Exploiting In-Memory data patterns for Performance Improvement on Crossbar Resistive Memory

引用

IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS 2020年第10期39卷 2347-2360页

作者： Wen, Wen Zhao, Lei Zhang, Youtao Yang, Jun Univ Pittsburgh Dept Elect & Comp Engn Pittsburgh PA 15261 USA Univ Pittsburgh Dept Comp Sci Pittsburgh PA 15260 USA

Resistive memory (ReRAM) has emerged as a promising nonvolatile memory technology that may replace a significant portion of DRAM in future computer systems. ReRAM has many advantages, such as high density, low standby power, and good scalability. When adopting crossbar architecture, ReRAM cell can achieve the smallest theoretical size in fabrication, which is ideal for constructing dense memory with large capacity. However, crossbar cell structure suffers from a variety of reliability issues, which come from large voltage drops on long wires. To ensure operation reliability, ReRAM writes conservatively use the worst-case access latency of all cells in ReRAM arrays, which leads to significant performance degradation and dynamic energy waste. In this article, we study the correlation between the ReRAM cell switching latency and the number of cells in low-resistance state (LRS) along bitlines, and propose to dynamically speed up write operations based on bitline data patterns, i.e., the number of LRS cells presented in bitlines. We leverage the intrinsic in-memory processing capability of ReRAM crossbar and propose a low-overhead runtime profiler that effectively tracks the data patterns in different bitlines. To achieve further write latency reduction, we employ data compression and row address dependent memory data layout to reduce the numbers of LRS cells on bitlines. Moreover, we further present two optimization techniques, i.e., selective profiling and fine-grained profiling, to mitigate energy overhead brought by bitline data patterns tracking. The experimental results show that, on average, our design improves system performance by 20.5% and 14.2%, and reduces memory dynamic energy by 20.3% and 12.6%, compared to the baseline and the state-of-the-art crossbar design, respectively.

关键词： Computer architecture Microprocessors Resistance Random access memory Correlation Switches Nonvolatile memory Crossbar array data pattern resistive memory (ReRAM) write performance

来源：评论

学校读者我要写书评

暂无评论

Nonstationary pattern-based signal-noise separation using adaptive prediction-error filter

引用

JOURNAL OF GEOPHYSICS AND ENGINEERING 2022年第1期19卷 14-27页

作者： Zheng, Zhisheng Liu, Yang Liu, Cai Jilin Univ Coll Geoexplorat Sci & Technol Changchun 130026 Peoples R China

Complex field conditions always create different interferences during seismic data acquisition, and there exist several types of noise in the recorded data, which affect the subsequent data processing and interpretation. To separate an effective signal from the noisy data, we adopted a pattern-based method with a two-step strategy, which involves two adaptive prediction-error filters (APEFs) corresponding to a nonstationary data pattern and noise pattern. By introducing shaping regularization, we first constructed a least-squares problem to estimate the filter coefficients of the APEF. Then, we solved another constrained least-square problem corresponding to the pattern-based signal-noise separation, and different pattern operators are adopted to characterize random noise and ground-roll noise. In comparison with traditional denoising methods, such as FXDECON, curvelet transform and local time-frequency (LTF) decomposition, we examined the ability of the proposed method by removing seismic random noise and ground-roll noise in several examples. Synthetic models and field data demonstrate the validity of the strategy for separating nonstationary signal and noise with different patterns.

关键词： nonstationary data pattern signal-noise separation adaptive prediction-error filter

来源：评论

学校读者我要写书评

暂无评论

Access Trends of In-network Cache for Scientific data 5

Access Trends of In-network Cache for Scientific Data

引用

5th International Workshop on Systems and Network Telemetry and Analytics (SNTA)

作者： Han, Ruize Sim, Alex Wu, Kesheng Monga, Inder Guok, Chin Wurthwein, Frank Davila, Diego Balcas, Justas Newman, Harvey Univ Calif Berkeley Berkeley CA 94720 USA Lawrence Berkeley Natl Lab Berkeley CA USA Energy Sci Network Berkeley CA USA Univ Calif San Diego La Jolla CA 92093 USA CALTECH Pasadena CA 91125 USA

ISBN: (纸本)9781450393157

Scientific collaborations are increasingly relying on large volumes of data for their work and many of them employ tiered systems to replicate the data to their worldwide user communities. Each user in the community often selects a different subset of data for their analysis tasks;however, members of a research group often are working on related research topics that require similar data objects. Thus, there is a significant amount of data sharing possible. In this work, we study the access traces of a federated storage cache known as the Southern California Petabyte Scale Cache. By studying the access patterns and potential for network traffic reduction by this caching system, we aim to explore the predictability of the cache uses and the potential for a more general in-network data caching. Our study shows that this distributed storage cache is able to reduce the network traffic volume by a factor of 2.35 during a part of the study period. We further show that machine learning models could predict cache utilization with an accuracy of 0.88. This demonstrates that such cache usage is predictable, which could be useful for managing complex networking resources such as in-network caching.

关键词： network cache resource utilization data pattern prediction xcache

来源：评论

学校读者我要写书评

暂无评论

Graph modelled system change detection in WSNs 11

Graph modelled system change detection in WSNs

引用

11th Mediterranean Conference on Embedded Computing (MECO) / 3rd Summer School on Cyber-Physical + Systems and Internet of Things (CPS and IoT)

作者： Zakrzewski, Robert Martin, Trevor Oikonomou, George Univ Bristol Commun Syst & Networks Bristol Avon England Univ Bristol Artificial Intelligence Grp Bristol Avon England

ISBN: (纸本)9781665468282

Graphs are suitable to model topology and data patterns in systems such as WSNs. To detect change, there is a need for graph comparison, a computationally demanding task difficult to run on constrained devices. For monitoring, the definition of normal patterns, and deviation from normal are required. In this contribution a flexible graph comparison method allowing monitoring of normal patterns and metrics providing measures of deviation from normal are proposed. In this manuscript, we apply the method to the system modelled by synthetic and random graphs. We demonstrate that the fingerprints of normal topology and data patterns can be acquired with the measures of deviation from normal. We discuss applicability of the method at the edge of WSNs.

关键词： Wireless sensor networks data pattern Topology Graph comparison Monitoring

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：