Search | Engineering

Subscribe Submit

Home Journals Focus Achievement Fronts About Us 中文版

Resource Type

Journal Article 13

Year

2023 1

2022 2

2019 1

2018 1

2017 5

2016 1

2011 1

2007 1

open ︾

Keywords

AAC 1

Answer selection 1

Attention 1

Attention mechanism 1

Brain encoding and decoding 1

Carbon neutrality 1

Cities 1

Climate change mitigation 1

Congestion control 1

Cross-layer design 1

Datacenter network 1

Deep generative models 1

Deep learning 1

Deep neural networks 1

Dual learning 1

Efficient decoding 1

Encoder– 1

End-to-end 1

FFC 1

open ︾

Search scope:

排序： Display mode:

Secrecy outage performance for wireless-powered relaying systems with nonlinear energy harvesters Article

继亮张,高峰潘,宜原解

Frontiers of Information Technology & Electronic Engineering 2017, Volume 18, Issue 2, Pages 246-252 doi: 10.1631/FITEE.1601352

Abstract: 在考虑解码转发和功率分配接收器的场景中，本文选择第K个最优中继来协助信源−中继−信宿链路的传输。同时，本文还推导了保密中断概率的解析表达式，并用通过仿真验证了分析结果。

Keywords：解码转发能量收集非线性保密中断概率

HTML PDF Collect

认知中继三跳网络联合优化 Article

澄赵,万良王,信威姚,双华杨

Frontiers of Information Technology & Electronic Engineering 2017, Volume 18, Issue 2, Pages 253-261 doi: 10.1631/FITEE.1601414

Abstract: 认知中继网络中，传输的吞吐量和传输距离一直是衡量性能的重要指标。现有的研究多数都集中在两跳网络的优化，但其也存在着传输距离不长，只能进行单项传输等缺点。本文提出了一种新的使用认知中继的三跳网络传输方案，通过三阶段的传输过程，实现了次级用户之间的双向传输。同时，引入了叠加编码技术来处理网络中双接收节点的情况。本文将这个三阶段的联合优化问题转化为一个非线性的优化问题，并进行了求解。仿真结果表明，本文提出的优化方法可以在不增加中继跳数的情况下，延长主用户传输距离，并同时提高次级用户的传输吞吐量。

Keywords：解码转发；三跳；认知中继网络；时间功率分配；叠加编码

HTML PDF Collect

Efficient decoding self-attention for end-to-end speech synthesis Research Article

Wei ZHAO, Li XU

Frontiers of Information Technology & Electronic Engineering 2022, Volume 23, Issue 7, Pages 1127-1138 doi: 10.1631/FITEE.2100501

Abstract: has been innovatively applied to text-to-speech (TTS) because of its parallel structure and superior strength in modeling sequential data. However, when used in with an autoregressive decoding scheme, its inference speed becomes relatively low due to the quadratic complexity in sequence length. This problem becomes particularly severe on devices without graphics processing units (GPUs). To alleviate the dilemma, we propose an (EDSA) module as an alternative. Combined with a dynamic programming decoding procedure, TTS model inference can be effectively accelerated to have a linear computation complexity. We conduct studies on Mandarin and English datasets and find that our proposed model with EDSA can achieve 720% and 50% higher inference speed on the central processing unit (CPU) and GPU respectively, with almost the same performance. Thus, this method may make the deployment of such models easier when there are limited GPU resources. In addition, our model may perform better than the baseline Transformer TTS on out-of-domain utterances.

Keywords： Efficient decoding End-to-end Self-attention Speech synthesis

HTML PDF Collect

A forwarding graph embedding algorithm exploiting regional topology information Article

Hong-chao HU, Fan ZHANG, Yu-xing MAO, Zhen-peng WANG

Frontiers of Information Technology & Electronic Engineering 2017, Volume 18, Issue 11, Pages 1854-1866 doi: 10.1631/FITEE.1601404

Abstract: Network function virtualization (NFV) is a newly proposed technique designed to construct and manage network functions dynamically and efficiently. Allocating physical resources to the virtual network function forwarding graph is a critical issue in NFV. We formulate the forwarding graph embedding (FGE) problem as a binary integer programming problem, which aims to increase the revenue and decrease the cost to a service provider (SP) while considering limited network resources and the requirements of virtual functions. We then design a novel regional resource clustering metric to quantify the embedding potential of each substrate node and propose a topology-aware FGE algorithm called ‘regional resource clustering FGE’ (RRC-FGE). After implementing our algorithms in C++, simulation results showed that the total revenue was increased by more than 50 units and the acceptance ratio by more than 15%, and the cost of the service provider was decreased by more than 60 units.

Keywords： Network function virtualization Virtual network function Forwarding graph embedding

HTML PDF Collect

Brain Encoding and Decoding in fMRI with Bidirectional Deep Generative Models Review

Changde Du, Jinpeng Li, Lijie Huang, Huiguang He

Engineering 2019, Volume 5, Issue 5, Pages 948-953 doi: 10.1016/j.eng.2019.03.010

Abstract:

Brain encoding and decoding via functional magnetic resonance imaging (fMRI) are two important aspects of visual perception neuroscience. Although previous researchers have made significant advances in brain encoding and decoding models, existing methods still require improvement using advanced machine learning techniques. For example, traditional methods usually build the encoding and decoding models separately, and are prone to overfitting on a small dataset. In fact, effectively unifying the encoding and decoding procedures may allow for more accurate predictions. In this paper, we first review the existing encoding and decoding methods and discuss
the potential advantages of a "bidirectional" modeling strategy. Next, we show that there are correspondences between deep neural networks and human visual streams in terms of the architecture and computational rules Furthermore, deep generative models (e.g., variational autoencoders (VAEs) and generative adversarial networks (GANs)) have produced promising results in studies on brain encoding and decoding. Finally, we propose that the dual learning method, which was originally designed for machine translation tasks, could help to improve the performance of encoding and decoding models by leveraging large-scale unpaired data.

Keywords： Brain encoding and decoding Functional magnetic resonance imaging Deep neural networks Deep generative models Dual learning

HTML PDF Collect

Anovel forwarding and routing mechanism design in SDN-basedNDNarchitecture None

Jia LI, Ren-chao XIE, Tao HUANG, Li SUN

Frontiers of Information Technology & Electronic Engineering 2018, Volume 19, Issue 9, Pages 1135-1150 doi: 10.1631/FITEE.1700698

Abstract:

Combining named data networking (NDN) and software-defined networking (SDN) has been considered as an important trend and attracted a lot of attention in recent years. Although much work has been carried out on the integration of NDN and SDN, the forwarding mechanism to solve the inherent problems caused by the flooding scheme and discard of interest packets in traditional NDN is not well considered. To fill this gap, by taking advantage of SDN, we design a novel forwarding mechanism in NDN architecture with distributed controllers, where routing decisions are made globally. Then we show how the forwarding mechanism is operated for interest and data packets. In addition, we propose a novel routing algorithm considering quality of service (QoS) applied in the proposed forwarding mechanism and carried out in controllers. We take both resource consumption and network load balancing into consideration and introduce a genetic algorithm (GA) to solve the QoS constrained routing problem using global network information. Simulation results are presented to demonstrate the performance of the proposed routing scheme.

Keywords： SDN-based NDN Forwarding mechanism QoS routing Genetic algorithm

HTML PDF Collect

Optimization Strategy of MPEG-4 AAC Decoder on a Low-cost SoC

Gao Gugang,Shi Longxing,Pu Hanlai,Zhou Fan

Strategic Study of CAE 2007, Volume 9, Issue 10, Pages 60-64

Abstract:

This paper proposes software optimization strategies using a low-cost SoC which include float-point to fix-point conversion scheme based on statistical analysis and performance oriented customizing scheme for on-chip memory's capacity, and presents optimization methodology based on these strategies for computation intensive applications. the MPEG-4 AAC decoding in real-time is implemented as a case study to illustrate the efficiency of the proposed optimization strategy in both performance and cost. The strategy and methodology also can be used to optimize other DSP applications.

Keywords： software optimization SoC FFC on-chip memory AAC

HTML PDF Collect

Attention-based encoder-decoder model for answer selection in question answering Article

Yuan-ping NIE, Yi HAN, Jiu-ming HUANG, Bo JIAO, Ai-ping LI

Frontiers of Information Technology & Electronic Engineering 2017, Volume 18, Issue 4, Pages 535-544 doi: 10.1631/FITEE.1601232

Abstract: One of the key challenges for question answering is to bridge the lexical gap between questions and answers because there may not be any matching word between them. Machine translation models have been shown to boost the performance of solving the lexical gap problem between question-answer pairs. In this paper, we introduce an attention-based deep learning model to address the answer selection task for question answering. The proposed model employs a bidirectional long short-term memory (LSTM) encoder-decoder, which has been demonstrated to be effective on machine translation tasks to bridge the lexical gap between questions and answers. Our model also uses a step attention mechanism which allows the question to focus on a certain part of the candidate answer. Finally, we evaluate our model using a benchmark dataset and the results show that our approach outperforms the existing approaches. Integrating our model significantly improves the performance of our question answering system in the TREC 2015 LiveQA task.

Keywords： Question answering Answer selection Attention Deep learning

HTML PDF Collect

Toward Carbon-Neutral Water Systems: Insights from Global Cities Article

Ka Leung Lam, Gang Liu, Anne Marieke Motelica-Wagenaar, Jan Peter van der Hoek

Engineering 2022, Volume 14, Issue 7, Pages 77-85 doi: 10.1016/j.eng.2022.04.012

Abstract:

Many cities have pledged to achieve carbon neutrality. The urban water industry can also contribute its share to a carbon-neutral future. Using a multi-city time-series analysis approach, this study aims to assess the progress and lessons learned from the greenhouse gas (GHG) emissions management of urban water systems in four global cities: Amsterdam, Melbourne, New York City, and Tokyo. These cities are advanced in setting GHG emissions reduction targets and reporting GHG emissions in their water industries. All four cities have reduced the GHG emissions in their water industries, compared with those from more than a decade ago (i.e., the latest three-year moving averages are 13%–32% lower), although the emissions have "rebounded" multiple times over the years. The emissions reductions were mainly due to various engineering opportunities such as solar and mini-hydro power generation, biogas valorization, sludge digestion and incineration optimization, and aeration system optimization. These cities have recognized the many challenges in reaching carbon-neutrality goals, which include fluctuating water demand and rainfall, more carbon-intensive flood-prevention and water-supply strategies, meeting new air and water quality standards, and revising GHG emissions accounting methods. This study has also shown that it is difficult for the water industry to achieve carbon neutrality on its own. A collaborative approach with other sectors is needed when aiming toward the city's carbon-neutrality goal. Such an approach involves expanding the usual system boundary of the water industry to externally tap into both engineering and non-engineering opportunities.

Keywords： Urban water Greenhouse gas emissions Cities Climate change mitigation Carbon neutrality

HTML PDF Collect

Cross-layer QoS routing algorithm of metric-based cooperative relay in WSNs

Xu Nan,Sun Yamin,Yu Jiming,Wang Hua

Strategic Study of CAE 2011, Volume 13, Issue 3, Pages 45-49

Abstract:

We proposed a cross-layer QoS routing algorithm which is metric-based cooperative relay initiative forwarding(MCRICQR). Nodes form a metric according to energy, channel, congestion and distance to sink. The node with maximal metric forwards or relays or leapfrogs the data in term of it's own states. Simulation results show that MCRICQR can prolong the lifetime of network and guarantee the required QoS. It also can transmit data in time and load balance which improve the reliability and energy efficiency and throughput of WSN(wireless sensor network).

Keywords： quality of service cross-layer design cooperative relay initiative forwarding wireless sensor network

HTML PDF Collect

Attention-based efficient robot grasp detection network Research Article

Xiaofei QIN, Wenkai HU, Chen XIAO, Changxiang HE, Songwen PEI, Xuedian ZHANG,xiaofei.qin@usst.edu.cn,obmmd_zxd@163.com

Frontiers of Information Technology & Electronic Engineering 2023, Volume 24, Issue 10, Pages 1430-1444 doi: 10.1631/FITEE.2200502

Abstract: To balance the inference speed and detection accuracy of a grasp detection algorithm, which are both important for robot grasping tasks, we propose an ; structured pixel-level grasp detection named the attention-based efficient network (AE-GDN). Three spatial attention modules are introduced in the encoder stages to enhance the detailed information, and three channel attention modules are introduced in the stages to extract more semantic information. Several lightweight and efficient DenseBlocks are used to connect the encoder and paths to improve the feature modeling capability of AE-GDN. A high intersection over union (IoU) value between the predicted grasp rectangle and the ground truth does not necessarily mean a high-quality grasp configuration, but might cause a collision. This is because traditional IoU loss calculation methods treat the center part of the predicted rectangle as having the same importance as the area around the grippers. We design a new IoU loss calculation method based on an hourglass box matching mechanism, which will create good correspondence between high IoUs and high-quality grasp configurations. AE-GDN achieves the accuracy of 98.9% and 96.6% on the Cornell and Jacquard datasets, respectively. The inference speed reaches 43.5 frames per second with only about 1.2×10 parameters. The proposed AE-GDN has also been deployed on a practical robotic arm grasping system and performs grasping well. Codes are available at https://github.com/robvincen/robot_gradethttps://github.com/robvincen/robot_gradet.

Keywords： Robot grasp detection Attention mechanism Encoder– decoder Neural network

HTML PDF Collect

Jointly optimized congestion control, forwarding strategy, and link scheduling in a named-data multihop wireless network

Cheng-cheng Li, Ren-chao Xie, Tao Huang, Yun-jie Liu,lengcangche@bupt.edu.cn,renchao_xie@bupt.edu.cn,htao@bupt.edu.cn

Frontiers of Information Technology & Electronic Engineering 2017, Volume 18, Issue 10, Pages 1573-1590 doi: 10.1631/FITEE.1601585

Abstract: As a promising future network architecture, named data networking (NDN) has been widely considered as a very appropriate network protocol for the (MWN). In named-data MWNs, is a critical issue. Independent optimization for may cause severe performance degradation if it can not cooperate well with protocols in other layers. Cross-layer is a potential method to enhance performance. There have been many cross-layer mechanisms for MWN with Internet Protocol (IP). However, these cross-layer mechanisms for MWNs with IP are not applicable to named-data MWNs because the communication characteristics of NDN are different from those of IP. In this paper, we study the joint , forwarding strategy, and link scheduling problem for named-data MWNs. The problem is modeled as a network utility maximization (NUM) problem. Based on the approximate subgradient algorithm, we propose an algorithm called ‘jointly optimized , forwarding strategy, and link scheduling (JOCFS)’ to solve the NUM problem distributively and iteratively. To the best of our knowledge, our proposal is the first cross-layer mechanism for named-data MWNs. By comparison with the existing mechanism, JOCFS can achieve a better performance in terms of network throughput, fairness, and the pending interest table (PIT) size.

Keywords： Information-centric networking Congestion control Cross-layer design Multihop wireless network

HTML PDF Collect

AnOpenFlow-based performance-orientedmultipath forwarding scheme in datacenters Project supported by the National Basic Research Program (973) of China (No. 2012CB315806), the National Natural Science Foundation of China (Nos. 61103225 and 61379149), the Jiangsu Provincial Natural Science Foundation (No. BK20140070), and the Jiangsu Future Networks Innovation Institute Prospective Research Project on Future Networks, China (No. BY2013095-1-06) Article

Bo LIU,Ming CHEN,Bo XU,Hui HU,Chao HU,Qing-yun ZUO,Chang-you XING

Frontiers of Information Technology & Electronic Engineering 2016, Volume 17, Issue 7, Pages 647-660 doi: 10.1631/FITEE.1601059

Abstract: Although dense interconnection datacenter networks (DCNs) (e.g., FatTree) provide multiple paths and high bisection bandwidth for each server pair, the widely used single-path Transmission Control Protocol (TCP) and equal-cost multipath (ECMP) transport protocols cannot achieve high resource utilization due to poor resource excavation and allocation. In this paper, we present LESSOR, a performance-oriented multipath forwarding scheme to improve DCNs’ resource utilization. By adopting an OpenFlow-based centralized control mechanism, LESSOR computes near-optimal transmission path and bandwidth provision for each flow according to the global network view while maintaining nearly real-time network view with the performance-oriented flow observing mechanism. Deployments and comprehensive simulations show that LESSOR can efficiently improve the network throughput, which is higher than ECMP by 4.9%–38.3% under different loads. LESSOR also provides 2%–27.7% improvement of throughput compared with Hedera. Besides, LESSOR decreases the average flow completion time significantly.

Keywords： Datacenter network Traffic engineering OpenFlow Multipath transmission